├── 3dthinker ├── stage1 │ ├── deepspeed_config.json │ ├── envs │ │ └── trl │ │ │ ├── .github │ │ │ ├── ISSUE_TEMPLATE │ │ │ │ ├── bug-report.yml │ │ │ │ ├── feature-request.yml │ │ │ │ └── new-trainer-addition.yml │ │ │ ├── PULL_REQUEST_TEMPLATE.md │ │ │ ├── codeql │ │ │ │ └── custom-queries.qls │ │ │ └── workflows │ │ │ │ ├── build_documentation.yml │ │ │ │ ├── build_pr_documentation.yml │ │ │ │ ├── clear_cache.yml │ │ │ │ ├── codeQL.yml │ │ │ │ ├── docker-build.yml │ │ │ │ ├── issue_auto_labeller.yml │ │ │ │ ├── pr_style_bot.yml │ │ │ │ ├── publish.yml │ │ │ │ ├── slow-tests.yml │ │ │ │ ├── tests.yml │ │ │ │ ├── tests_latest.yml │ │ │ │ ├── trufflehog.yml │ │ │ │ └── upload_pr_documentation.yml │ │ │ ├── .gitignore │ │ │ ├── .pre-commit-config.yaml │ │ │ ├── CITATION.cff │ │ │ ├── CODE_OF_CONDUCT.md │ │ │ ├── CONTRIBUTING.md │ │ │ ├── LICENSE │ │ │ ├── MANIFEST.in │ │ │ ├── Makefile │ │ │ ├── README.md │ │ │ ├── RELEASE.md │ │ │ ├── VERSION │ │ │ ├── commands │ │ │ ├── run_dpo.sh │ │ │ └── run_sft.sh │ │ │ ├── docker │ │ │ ├── trl-latest-gpu │ │ │ │ └── Dockerfile │ │ │ └── trl-source-gpu │ │ │ │ └── Dockerfile │ │ │ ├── docs │ │ │ └── source │ │ │ │ ├── _toctree.yml │ │ │ │ ├── alignprop_trainer.md │ │ │ │ ├── bco_trainer.md │ │ │ │ ├── best_of_n.md │ │ │ │ ├── callbacks.md │ │ │ │ ├── clis.md │ │ │ │ ├── community_tutorials.md │ │ │ │ ├── cpo_trainer.md │ │ │ │ ├── customization.md │ │ │ │ ├── data_utils.md │ │ │ │ ├── dataset_formats.md │ │ │ │ ├── ddpo_trainer.md │ │ │ │ ├── deepspeed_integration.md │ │ │ │ ├── detoxifying_a_lm.md │ │ │ │ ├── distributing_training.md │ │ │ │ ├── dpo_trainer.md │ │ │ │ ├── example_overview.md │ │ │ │ ├── gkd_trainer.md │ │ │ │ ├── grpo_trainer.md │ │ │ │ ├── how_to_train.md │ │ │ │ ├── index.md │ │ │ │ ├── installation.md │ │ │ │ ├── iterative_sft_trainer.md │ │ │ │ ├── jobs_training.md │ │ │ │ ├── judges.md │ │ │ │ ├── kto_trainer.md │ │ │ │ ├── liger_kernel_integration.md │ │ │ │ ├── logging.md │ │ │ │ ├── model_utils.md │ │ │ │ ├── models.md │ │ │ │ ├── multi_adapter_rl.md │ │ │ │ ├── nash_md_trainer.md │ │ │ │ ├── online_dpo_trainer.md │ │ │ │ ├── orpo_trainer.md │ │ │ │ ├── others.md │ │ │ │ ├── paper_index.md │ │ │ │ ├── peft_integration.md │ │ │ │ ├── ppo_trainer.md │ │ │ │ ├── prm_trainer.md │ │ │ │ ├── quickstart.md │ │ │ │ ├── reducing_memory_usage.md │ │ │ │ ├── reward_trainer.md │ │ │ │ ├── rewards.md │ │ │ │ ├── rloo_trainer.md │ │ │ │ ├── script_utils.md │ │ │ │ ├── sentiment_tuning.md │ │ │ │ ├── sft_trainer.md │ │ │ │ ├── speeding_up_training.md │ │ │ │ ├── trackio_integration.md │ │ │ │ ├── unsloth_integration.md │ │ │ │ ├── use_model.md │ │ │ │ ├── using_llama_models.md │ │ │ │ ├── vllm_integration.md │ │ │ │ └── xpo_trainer.md │ │ │ ├── examples │ │ │ ├── README.md │ │ │ ├── accelerate_configs │ │ │ │ ├── deepspeed_zero1.yaml │ │ │ │ ├── deepspeed_zero2.yaml │ │ │ │ ├── deepspeed_zero3.yaml │ │ │ │ ├── fsdp1.yaml │ │ │ │ ├── fsdp2.yaml │ │ │ │ ├── multi_gpu.yaml │ │ │ │ └── single_gpu.yaml │ │ │ ├── cli_configs │ │ │ │ └── example_config.yaml │ │ │ ├── datasets │ │ │ │ ├── hh-rlhf-helpful-base.py │ │ │ │ ├── llava_instruct_mix.py │ │ │ │ ├── lm-human-preferences-descriptiveness.py │ │ │ │ ├── lm-human-preferences-sentiment.py │ │ │ │ ├── math_shepherd.py │ │ │ │ ├── prm800k.py │ │ │ │ ├── rlaif-v.py │ │ │ │ ├── tldr.py │ │ │ │ ├── tldr_preference.py │ │ │ │ ├── ultrafeedback-prompt.py │ │ │ │ └── ultrafeedback.py │ │ │ ├── notebooks │ │ │ │ ├── README.md │ │ │ │ ├── best_of_n.ipynb │ │ │ │ ├── gpt2-sentiment-control.ipynb │ │ │ │ └── gpt2-sentiment.ipynb │ │ │ ├── research_projects │ │ │ │ ├── README.md │ │ │ │ ├── layer_skip │ │ │ │ │ ├── README.md │ │ │ │ │ └── scripts │ │ │ │ │ │ ├── benchmark_layer_skip.py │ │ │ │ │ │ ├── config.py │ │ │ │ │ │ ├── custom_trainer.py │ │ │ │ │ │ └── layer_skip_sft.py │ │ │ │ ├── stack_llama │ │ │ │ │ └── scripts │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── merge_peft_adapter.py │ │ │ │ │ │ ├── reward_modeling.py │ │ │ │ │ │ ├── rl_training.py │ │ │ │ │ │ └── supervised_finetuning.py │ │ │ │ ├── stack_llama_2 │ │ │ │ │ └── scripts │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── dpo_llama2.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ └── sft_llama2.py │ │ │ │ └── toxicity │ │ │ │ │ ├── README.md │ │ │ │ │ └── scripts │ │ │ │ │ ├── evaluate-toxicity.py │ │ │ │ │ └── gpt-j-6b-toxicity.py │ │ │ └── scripts │ │ │ │ ├── alignprop.py │ │ │ │ ├── bco.py │ │ │ │ ├── cpo.py │ │ │ │ ├── ddpo.py │ │ │ │ ├── dpo.py │ │ │ │ ├── dpo_online.py │ │ │ │ ├── dpo_vlm.py │ │ │ │ ├── evals │ │ │ │ └── judge_tldr.py │ │ │ │ ├── gkd.py │ │ │ │ ├── grpo_vlm.py │ │ │ │ ├── gspo.py │ │ │ │ ├── gspo_vlm.py │ │ │ │ ├── kto.py │ │ │ │ ├── mpo_vlm.py │ │ │ │ ├── nash_md.py │ │ │ │ ├── orpo.py │ │ │ │ ├── ppo │ │ │ │ ├── ppo.py │ │ │ │ └── ppo_tldr.py │ │ │ │ ├── prm.py │ │ │ │ ├── reward_modeling.py │ │ │ │ ├── rloo.py │ │ │ │ ├── sft.py │ │ │ │ ├── sft_gemma3.py │ │ │ │ ├── sft_gpt_oss.py │ │ │ │ ├── sft_video_llm.py │ │ │ │ ├── sft_vlm.py │ │ │ │ ├── sft_vlm_gemma3.py │ │ │ │ └── xpo.py │ │ │ ├── pyproject.toml │ │ │ ├── requirements.txt │ │ │ ├── scripts │ │ │ ├── add_copyrights.py │ │ │ ├── generate_harmony_dataset.py │ │ │ ├── generate_tiny_models.py │ │ │ ├── generate_toolcall_dataset.py │ │ │ ├── generate_zen_dataset.py │ │ │ ├── generate_zen_image_dataset.py │ │ │ ├── generate_zen_multi_image_dataset.py │ │ │ ├── log_example_reports.py │ │ │ └── log_reports.py │ │ │ ├── setup.cfg │ │ │ ├── setup.py │ │ │ ├── tests │ │ │ ├── __init__.py │ │ │ ├── data │ │ │ │ └── template.jinja │ │ │ ├── slow │ │ │ │ ├── __init__.py │ │ │ │ ├── test_dpo_slow.py │ │ │ │ ├── test_grpo_slow.py │ │ │ │ ├── test_sft_slow.py │ │ │ │ └── testing_constants.py │ │ │ ├── test_activation_offloading.py │ │ │ ├── test_alignprop_trainer.py │ │ │ ├── test_bco_trainer.py │ │ │ ├── test_best_of_n_sampler.py │ │ │ ├── test_callbacks.py │ │ │ ├── test_cli.py │ │ │ ├── test_cli_utils.py │ │ │ ├── test_collators.py │ │ │ ├── test_core.py │ │ │ ├── test_cpo_trainer.py │ │ │ ├── test_data_utils.py │ │ │ ├── test_dataset_formatting.py │ │ │ ├── test_ddpo_trainer.py │ │ │ ├── test_dpo_trainer.py │ │ │ ├── test_gkd_trainer.py │ │ │ ├── test_grpo_trainer.py │ │ │ ├── test_iterative_sft_trainer.py │ │ │ ├── test_judges.py │ │ │ ├── test_kto_trainer.py │ │ │ ├── test_modeling_geometric_mixture_wrapper.py │ │ │ ├── test_modeling_value_head.py │ │ │ ├── test_nash_md_trainer.py │ │ │ ├── test_online_dpo_trainer.py │ │ │ ├── test_orpo_trainer.py │ │ │ ├── test_peft_models.py │ │ │ ├── test_ppo_trainer.py │ │ │ ├── test_prm_trainer.py │ │ │ ├── test_reward_trainer.py │ │ │ ├── test_rewards.py │ │ │ ├── test_rich_progress_callback.py │ │ │ ├── test_rloo_trainer.py │ │ │ ├── test_sft_trainer.py │ │ │ ├── test_trainers_args.py │ │ │ ├── test_utils.py │ │ │ ├── test_vllm_client_server.py │ │ │ ├── test_xpo_trainer.py │ │ │ ├── testing_constants.py │ │ │ └── testing_utils.py │ │ │ └── trl │ │ │ ├── __init__.py │ │ │ ├── accelerate_configs │ │ │ ├── fsdp1.yaml │ │ │ ├── fsdp2.yaml │ │ │ ├── multi_gpu.yaml │ │ │ ├── single_gpu.yaml │ │ │ ├── zero1.yaml │ │ │ ├── zero2.yaml │ │ │ └── zero3.yaml │ │ │ ├── cli.py │ │ │ ├── core.py │ │ │ ├── data_utils.py │ │ │ ├── extras │ │ │ ├── __init__.py │ │ │ ├── best_of_n_sampler.py │ │ │ ├── dataset_formatting.py │ │ │ ├── profiling.py │ │ │ └── vllm_client.py │ │ │ ├── import_utils.py │ │ │ ├── mergekit_utils.py │ │ │ ├── models │ │ │ ├── __init__.py │ │ │ ├── activation_offloading.py │ │ │ ├── auxiliary_modules.py │ │ │ ├── modeling_base.py │ │ │ ├── modeling_sd_base.py │ │ │ ├── modeling_value_head.py │ │ │ ├── sd_utils.py │ │ │ └── utils.py │ │ │ ├── py.typed │ │ │ ├── rewards │ │ │ ├── __init__.py │ │ │ ├── format_rewards.py │ │ │ └── other_rewards.py │ │ │ ├── scripts │ │ │ ├── __init__.py │ │ │ ├── dpo.py │ │ │ ├── env.py │ │ │ ├── grpo.py │ │ │ ├── kto.py │ │ │ ├── rloo.py │ │ │ ├── sft.py │ │ │ ├── utils.py │ │ │ └── vllm_serve.py │ │ │ ├── templates │ │ │ └── lm_model_card.md │ │ │ └── trainer │ │ │ ├── __init__.py │ │ │ ├── alignprop_config.py │ │ │ ├── alignprop_trainer.py │ │ │ ├── bco_config.py │ │ │ ├── bco_trainer.py │ │ │ ├── callbacks.py │ │ │ ├── cpo_config.py │ │ │ ├── cpo_trainer.py │ │ │ ├── ddpo_config.py │ │ │ ├── ddpo_trainer.py │ │ │ ├── dpo_config.py │ │ │ ├── dpo_trainer.py │ │ │ ├── gkd_config.py │ │ │ ├── gkd_trainer.py │ │ │ ├── grpo_config.py │ │ │ ├── grpo_trainer.py │ │ │ ├── iterative_sft_config.py │ │ │ ├── iterative_sft_trainer.py │ │ │ ├── judges.py │ │ │ ├── kto_config.py │ │ │ ├── kto_trainer.py │ │ │ ├── model_config.py │ │ │ ├── nash_md_config.py │ │ │ ├── nash_md_trainer.py │ │ │ ├── online_dpo_config.py │ │ │ ├── online_dpo_trainer.py │ │ │ ├── orpo_config.py │ │ │ ├── orpo_trainer.py │ │ │ ├── ppo_config.py │ │ │ ├── ppo_trainer.py │ │ │ ├── prm_config.py │ │ │ ├── prm_trainer.py │ │ │ ├── reward_config.py │ │ │ ├── reward_trainer.py │ │ │ ├── rloo_config.py │ │ │ ├── rloo_trainer.py │ │ │ ├── sft_config.py │ │ │ ├── sft_trainer.py │ │ │ ├── utils.py │ │ │ ├── xpo_config.py │ │ │ └── xpo_trainer.py │ ├── src │ │ ├── __pycache__ │ │ │ ├── task.cpython-310.pyc │ │ │ ├── trainer_single.cpython-310.pyc │ │ │ └── utils.cpython-310.pyc │ │ ├── main.py │ │ ├── main_deepspeed.py │ │ ├── main_multi.py │ │ ├── multimodal_projector │ │ │ ├── __pycache__ │ │ │ │ ├── builder.cpython-310.pyc │ │ │ │ ├── builder.cpython-39.pyc │ │ │ │ ├── mmprojector.cpython-310.pyc │ │ │ │ ├── pooler_projector.cpython-310.pyc │ │ │ │ └── pooler_projector.cpython-39.pyc │ │ │ ├── builder.py │ │ │ ├── mmprojector.py │ │ │ └── pooler_projector.py │ │ ├── task.py │ │ ├── test.py │ │ ├── trainer_deepspeed.py │ │ ├── trainer_multi.py │ │ ├── trainer_single.py │ │ └── utils.py │ ├── train.sh │ ├── train_deepspeed.sh │ ├── train_multi.sh │ └── transformers │ │ ├── .circleci │ │ ├── TROUBLESHOOT.md │ │ ├── config.yml │ │ ├── create_circleci_config.py │ │ └── parse_test_outputs.py │ │ ├── .gitattributes │ │ ├── .github │ │ ├── ISSUE_TEMPLATE │ │ │ ├── bug-report.yml │ │ │ ├── config.yml │ │ │ ├── feature-request.yml │ │ │ ├── i18n.md │ │ │ ├── migration.yml │ │ │ └── new-model-addition.yml │ │ ├── PULL_REQUEST_TEMPLATE.md │ │ ├── conda │ │ │ ├── build.sh │ │ │ └── meta.yaml │ │ ├── scripts │ │ │ ├── assign_reviewers.py │ │ │ └── codeowners_for_review_action │ │ └── workflows │ │ │ ├── TROUBLESHOOT.md │ │ │ ├── add-model-like.yml │ │ │ ├── assign-reviewers.yml │ │ │ ├── benchmark.yml │ │ │ ├── build-ci-docker-images.yml │ │ │ ├── build-docker-images.yml │ │ │ ├── build-nightly-ci-docker-images.yml │ │ │ ├── build-past-ci-docker-images.yml │ │ │ ├── build_documentation.yml │ │ │ ├── build_pr_documentation.yml │ │ │ ├── change_pr_to_draft.yml │ │ │ ├── check_failed_model_tests.yml │ │ │ ├── check_tiny_models.yml │ │ │ ├── doctest_job.yml │ │ │ ├── doctests.yml │ │ │ ├── model_jobs.yml │ │ │ ├── model_jobs_amd.yml │ │ │ ├── new_model_pr_merged_notification.yml │ │ │ ├── push-important-models.yml │ │ │ ├── release-conda.yml │ │ │ ├── self-comment-ci.yml │ │ │ ├── self-nightly-caller.yml │ │ │ ├── self-nightly-past-ci-caller.yml │ │ │ ├── self-past-caller.yml │ │ │ ├── self-push-amd-mi210-caller.yml │ │ │ ├── self-push-amd-mi250-caller.yml │ │ │ ├── self-push-amd-mi300-caller.yml │ │ │ ├── self-push-amd.yml │ │ │ ├── self-push-caller.yml │ │ │ ├── self-push.yml │ │ │ ├── self-scheduled-amd-caller.yml │ │ │ ├── self-scheduled-amd-mi210-caller.yml │ │ │ ├── self-scheduled-amd-mi250-caller.yml │ │ │ ├── self-scheduled-caller.yml │ │ │ ├── self-scheduled.yml │ │ │ ├── slack-report.yml │ │ │ ├── ssh-runner.yml │ │ │ ├── stale.yml │ │ │ ├── trufflehog.yml │ │ │ ├── update_metdata.yml │ │ │ └── upload_pr_documentation.yml │ │ ├── .gitignore │ │ ├── CITATION.cff │ │ ├── CODE_OF_CONDUCT.md │ │ ├── CONTRIBUTING.md │ │ ├── ISSUES.md │ │ ├── LICENSE │ │ ├── Makefile │ │ ├── README.md │ │ ├── SECURITY.md │ │ ├── awesome-transformers.md │ │ ├── benchmark │ │ ├── README.md │ │ ├── __init__.py │ │ ├── benchmark.py │ │ ├── benchmarks_entrypoint.py │ │ ├── config │ │ │ └── generation.yaml │ │ ├── default.yml │ │ ├── grafana_dashboard.json │ │ ├── grafana_datasource.yaml │ │ ├── init_db.sql │ │ ├── llama.py │ │ ├── optimum_benchmark_wrapper.py │ │ └── requirements.txt │ │ ├── conftest.py │ │ ├── docker │ │ ├── README.md │ │ ├── consistency.dockerfile │ │ ├── custom-tokenizers.dockerfile │ │ ├── examples-tf.dockerfile │ │ ├── examples-torch.dockerfile │ │ ├── exotic-models.dockerfile │ │ ├── jax-light.dockerfile │ │ ├── pipeline-tf.dockerfile │ │ ├── pipeline-torch.dockerfile │ │ ├── quality.dockerfile │ │ ├── tf-light.dockerfile │ │ ├── torch-jax-light.dockerfile │ │ ├── torch-light.dockerfile │ │ ├── torch-tf-light.dockerfile │ │ ├── transformers-all-latest-gpu │ │ │ └── Dockerfile │ │ ├── transformers-doc-builder │ │ │ └── Dockerfile │ │ ├── transformers-gpu │ │ │ └── Dockerfile │ │ ├── transformers-past-gpu │ │ │ └── Dockerfile │ │ ├── transformers-pytorch-amd-gpu │ │ │ └── Dockerfile │ │ ├── transformers-pytorch-deepspeed-amd-gpu │ │ │ └── Dockerfile │ │ ├── transformers-pytorch-deepspeed-latest-gpu │ │ │ └── Dockerfile │ │ ├── transformers-pytorch-deepspeed-nightly-gpu │ │ │ └── Dockerfile │ │ ├── transformers-pytorch-gpu │ │ │ └── Dockerfile │ │ ├── transformers-pytorch-tpu │ │ │ ├── Dockerfile │ │ │ ├── bert-base-cased.jsonnet │ │ │ ├── dataset.yaml │ │ │ └── docker-entrypoint.sh │ │ ├── transformers-quantization-latest-gpu │ │ │ └── Dockerfile │ │ └── transformers-tensorflow-gpu │ │ │ └── Dockerfile │ │ ├── docs │ │ ├── README.md │ │ ├── TRANSLATING.md │ │ └── source │ │ │ ├── _config.py │ │ │ ├── ar │ │ │ ├── _config.py │ │ │ ├── _toctree.yml │ │ │ ├── accelerate.md │ │ │ ├── agents.md │ │ │ ├── attention.md │ │ │ ├── autoclass_tutorial.md │ │ │ ├── bertology.md │ │ │ ├── chat_templating.md │ │ │ ├── community.md │ │ │ ├── conversations.md │ │ │ ├── create_a_model.md │ │ │ ├── custom_models.md │ │ │ ├── fast_tokenizers.md │ │ │ ├── gguf.md │ │ │ ├── glossary.md │ │ │ ├── how_to_hack_models.md │ │ │ ├── index.md │ │ │ ├── installation.md │ │ │ ├── llm_tutorial.md │ │ │ ├── llm_tutorial_optimization.md │ │ │ ├── model_memory_anatomy.md │ │ │ ├── model_sharing.md │ │ │ ├── model_summary.md │ │ │ ├── modular_transformers.md │ │ │ ├── multilingual.md │ │ │ ├── notebooks.md │ │ │ ├── pad_truncation.md │ │ │ ├── peft.md │ │ │ ├── perplexity.md │ │ │ ├── philosophy.md │ │ │ ├── pipeline_tutorial.md │ │ │ ├── pipeline_webserver.md │ │ │ ├── preprocessing.md │ │ │ ├── quicktour.md │ │ │ ├── run_scripts.md │ │ │ ├── sagemaker.md │ │ │ ├── serialization.md │ │ │ ├── task_summary.md │ │ │ ├── tasks │ │ │ │ ├── language_modeling.md │ │ │ │ ├── masked_language_modeling.md │ │ │ │ ├── multiple_choice.md │ │ │ │ ├── question_answering.md │ │ │ │ ├── sequence_classification.md │ │ │ │ ├── summarization.md │ │ │ │ ├── token_classification.md │ │ │ │ └── translation.md │ │ │ ├── tasks_explained.md │ │ │ ├── tflite.md │ │ │ ├── tiktoken.md │ │ │ ├── tokenizer_summary.md │ │ │ ├── torchscript.md │ │ │ ├── trainer.md │ │ │ ├── training.md │ │ │ └── troubleshooting.md │ │ │ ├── de │ │ │ ├── _config.py │ │ │ ├── _toctree.yml │ │ │ ├── accelerate.md │ │ │ ├── add_new_model.md │ │ │ ├── add_new_pipeline.md │ │ │ ├── autoclass_tutorial.md │ │ │ ├── contributing.md │ │ │ ├── index.md │ │ │ ├── installation.md │ │ │ ├── llm_tutorial.md │ │ │ ├── model_sharing.md │ │ │ ├── peft.md │ │ │ ├── pipeline_tutorial.md │ │ │ ├── pr_checks.md │ │ │ ├── preprocessing.md │ │ │ ├── quicktour.md │ │ │ ├── run_scripts.md │ │ │ ├── testing.md │ │ │ ├── training.md │ │ │ └── transformers_agents.md │ │ │ ├── en │ │ │ ├── _config.py │ │ │ ├── _redirects.yml │ │ │ ├── _toctree.yml │ │ │ ├── accelerate.md │ │ │ ├── add_new_model.md │ │ │ ├── add_new_pipeline.md │ │ │ ├── agents.md │ │ │ ├── attention.md │ │ │ ├── backbones.md │ │ │ ├── cache_explanation.md │ │ │ ├── chat_extras.md │ │ │ ├── chat_templating.md │ │ │ ├── chat_templating_multimodal.md │ │ │ ├── chat_templating_writing.md │ │ │ ├── community.md │ │ │ ├── contributing.md │ │ │ ├── conversations.md │ │ │ ├── custom_models.md │ │ │ ├── debugging.md │ │ │ ├── deepspeed.md │ │ │ ├── executorch.md │ │ │ ├── fast_tokenizers.md │ │ │ ├── feature_extractors.md │ │ │ ├── fsdp.md │ │ │ ├── generation_features.md │ │ │ ├── generation_strategies.md │ │ │ ├── gguf.md │ │ │ ├── glossary.md │ │ │ ├── gpu_selection.md │ │ │ ├── how_to_hack_models.md │ │ │ ├── hpo_train.md │ │ │ ├── image_processors.md │ │ │ ├── index.md │ │ │ ├── installation.md │ │ │ ├── internal │ │ │ │ ├── audio_utils.md │ │ │ │ ├── file_utils.md │ │ │ │ ├── generation_utils.md │ │ │ │ ├── image_processing_utils.md │ │ │ │ ├── modeling_utils.md │ │ │ │ ├── pipelines_utils.md │ │ │ │ ├── time_series_utils.md │ │ │ │ ├── tokenization_utils.md │ │ │ │ └── trainer_utils.md │ │ │ ├── kv_cache.md │ │ │ ├── llm_optims.md │ │ │ ├── llm_tutorial.md │ │ │ ├── llm_tutorial_optimization.md │ │ │ ├── main_classes │ │ │ │ ├── agent.md │ │ │ │ ├── backbones.md │ │ │ │ ├── callback.md │ │ │ │ ├── configuration.md │ │ │ │ ├── data_collator.md │ │ │ │ ├── deepspeed.md │ │ │ │ ├── executorch.md │ │ │ │ ├── feature_extractor.md │ │ │ │ ├── image_processor.md │ │ │ │ ├── keras_callbacks.md │ │ │ │ ├── logging.md │ │ │ │ ├── model.md │ │ │ │ ├── onnx.md │ │ │ │ ├── optimizer_schedules.md │ │ │ │ ├── output.md │ │ │ │ ├── peft.md │ │ │ │ ├── pipelines.md │ │ │ │ ├── processors.md │ │ │ │ ├── quantization.md │ │ │ │ ├── text_generation.md │ │ │ │ ├── tokenizer.md │ │ │ │ └── trainer.md │ │ │ ├── model_doc │ │ │ │ ├── albert.md │ │ │ │ ├── align.md │ │ │ │ ├── altclip.md │ │ │ │ ├── aria.md │ │ │ │ ├── audio-spectrogram-transformer.md │ │ │ │ ├── auto.md │ │ │ │ ├── autoformer.md │ │ │ │ ├── aya_vision.md │ │ │ │ ├── bamba.md │ │ │ │ ├── bark.md │ │ │ │ ├── bart.md │ │ │ │ ├── barthez.md │ │ │ │ ├── bartpho.md │ │ │ │ ├── beit.md │ │ │ │ ├── bert-generation.md │ │ │ │ ├── bert-japanese.md │ │ │ │ ├── bert.md │ │ │ │ ├── bertweet.md │ │ │ │ ├── big_bird.md │ │ │ │ ├── bigbird_pegasus.md │ │ │ │ ├── biogpt.md │ │ │ │ ├── bit.md │ │ │ │ ├── blenderbot-small.md │ │ │ │ ├── blenderbot.md │ │ │ │ ├── blip-2.md │ │ │ │ ├── blip.md │ │ │ │ ├── bloom.md │ │ │ │ ├── bort.md │ │ │ │ ├── bridgetower.md │ │ │ │ ├── bros.md │ │ │ │ ├── byt5.md │ │ │ │ ├── camembert.md │ │ │ │ ├── canine.md │ │ │ │ ├── chameleon.md │ │ │ │ ├── chinese_clip.md │ │ │ │ ├── clap.md │ │ │ │ ├── clip.md │ │ │ │ ├── clipseg.md │ │ │ │ ├── clvp.md │ │ │ │ ├── code_llama.md │ │ │ │ ├── codegen.md │ │ │ │ ├── cohere.md │ │ │ │ ├── cohere2.md │ │ │ │ ├── colpali.md │ │ │ │ ├── conditional_detr.md │ │ │ │ ├── convbert.md │ │ │ │ ├── convnext.md │ │ │ │ ├── convnextv2.md │ │ │ │ ├── cpm.md │ │ │ │ ├── cpmant.md │ │ │ │ ├── ctrl.md │ │ │ │ ├── cvt.md │ │ │ │ ├── dab-detr.md │ │ │ │ ├── dac.md │ │ │ │ ├── data2vec.md │ │ │ │ ├── dbrx.md │ │ │ │ ├── deberta-v2.md │ │ │ │ ├── deberta.md │ │ │ │ ├── decision_transformer.md │ │ │ │ ├── deformable_detr.md │ │ │ │ ├── deit.md │ │ │ │ ├── deplot.md │ │ │ │ ├── depth_anything.md │ │ │ │ ├── depth_anything_v2.md │ │ │ │ ├── depth_pro.md │ │ │ │ ├── deta.md │ │ │ │ ├── detr.md │ │ │ │ ├── dialogpt.md │ │ │ │ ├── diffllama.md │ │ │ │ ├── dinat.md │ │ │ │ ├── dinov2.md │ │ │ │ ├── dinov2_with_registers.md │ │ │ │ ├── distilbert.md │ │ │ │ ├── dit.md │ │ │ │ ├── donut.md │ │ │ │ ├── dpr.md │ │ │ │ ├── dpt.md │ │ │ │ ├── efficientformer.md │ │ │ │ ├── efficientnet.md │ │ │ │ ├── electra.md │ │ │ │ ├── emu3.md │ │ │ │ ├── encodec.md │ │ │ │ ├── encoder-decoder.md │ │ │ │ ├── ernie.md │ │ │ │ ├── ernie_m.md │ │ │ │ ├── esm.md │ │ │ │ ├── falcon.md │ │ │ │ ├── falcon3.md │ │ │ │ ├── falcon_mamba.md │ │ │ │ ├── fastspeech2_conformer.md │ │ │ │ ├── flan-t5.md │ │ │ │ ├── flan-ul2.md │ │ │ │ ├── flaubert.md │ │ │ │ ├── flava.md │ │ │ │ ├── fnet.md │ │ │ │ ├── focalnet.md │ │ │ │ ├── fsmt.md │ │ │ │ ├── funnel.md │ │ │ │ ├── fuyu.md │ │ │ │ ├── gemma.md │ │ │ │ ├── gemma2.md │ │ │ │ ├── gemma3.md │ │ │ │ ├── git.md │ │ │ │ ├── glm.md │ │ │ │ ├── glpn.md │ │ │ │ ├── got_ocr2.md │ │ │ │ ├── gpt-sw3.md │ │ │ │ ├── gpt2.md │ │ │ │ ├── gpt_bigcode.md │ │ │ │ ├── gpt_neo.md │ │ │ │ ├── gpt_neox.md │ │ │ │ ├── gpt_neox_japanese.md │ │ │ │ ├── gptj.md │ │ │ │ ├── gptsan-japanese.md │ │ │ │ ├── granite.md │ │ │ │ ├── granitemoe.md │ │ │ │ ├── granitemoeshared.md │ │ │ │ ├── granitevision.md │ │ │ │ ├── graphormer.md │ │ │ │ ├── grounding-dino.md │ │ │ │ ├── groupvit.md │ │ │ │ ├── helium.md │ │ │ │ ├── herbert.md │ │ │ │ ├── hiera.md │ │ │ │ ├── hubert.md │ │ │ │ ├── ibert.md │ │ │ │ ├── idefics.md │ │ │ │ ├── idefics2.md │ │ │ │ ├── idefics3.md │ │ │ │ ├── ijepa.md │ │ │ │ ├── imagegpt.md │ │ │ │ ├── informer.md │ │ │ │ ├── instructblip.md │ │ │ │ ├── instructblipvideo.md │ │ │ │ ├── jamba.md │ │ │ │ ├── jetmoe.md │ │ │ │ ├── jukebox.md │ │ │ │ ├── kosmos-2.md │ │ │ │ ├── layoutlm.md │ │ │ │ ├── layoutlmv2.md │ │ │ │ ├── layoutlmv3.md │ │ │ │ ├── layoutxlm.md │ │ │ │ ├── led.md │ │ │ │ ├── levit.md │ │ │ │ ├── lilt.md │ │ │ │ ├── llama.md │ │ │ │ ├── llama2.md │ │ │ │ ├── llama3.md │ │ │ │ ├── llava.md │ │ │ │ ├── llava_next.md │ │ │ │ ├── llava_next_video.md │ │ │ │ ├── llava_onevision.md │ │ │ │ ├── longformer.md │ │ │ │ ├── longt5.md │ │ │ │ ├── luke.md │ │ │ │ ├── lxmert.md │ │ │ │ ├── m2m_100.md │ │ │ │ ├── madlad-400.md │ │ │ │ ├── mamba.md │ │ │ │ ├── mamba2.md │ │ │ │ ├── marian.md │ │ │ │ ├── markuplm.md │ │ │ │ ├── mask2former.md │ │ │ │ ├── maskformer.md │ │ │ │ ├── matcha.md │ │ │ │ ├── mbart.md │ │ │ │ ├── mctct.md │ │ │ │ ├── mega.md │ │ │ │ ├── megatron-bert.md │ │ │ │ ├── megatron_gpt2.md │ │ │ │ ├── mgp-str.md │ │ │ │ ├── mimi.md │ │ │ │ ├── mistral.md │ │ │ │ ├── mistral3.md │ │ │ │ ├── mixtral.md │ │ │ │ ├── mllama.md │ │ │ │ ├── mluke.md │ │ │ │ ├── mms.md │ │ │ │ ├── mobilebert.md │ │ │ │ ├── mobilenet_v1.md │ │ │ │ ├── mobilenet_v2.md │ │ │ │ ├── mobilevit.md │ │ │ │ ├── mobilevitv2.md │ │ │ │ ├── modernbert.md │ │ │ │ ├── moonshine.md │ │ │ │ ├── moshi.md │ │ │ │ ├── mpnet.md │ │ │ │ ├── mpt.md │ │ │ │ ├── mra.md │ │ │ │ ├── mt5.md │ │ │ │ ├── musicgen.md │ │ │ │ ├── musicgen_melody.md │ │ │ │ ├── mvp.md │ │ │ │ ├── myt5.md │ │ │ │ ├── nat.md │ │ │ │ ├── nemotron.md │ │ │ │ ├── nezha.md │ │ │ │ ├── nllb-moe.md │ │ │ │ ├── nllb.md │ │ │ │ ├── nougat.md │ │ │ │ ├── nystromformer.md │ │ │ │ ├── olmo.md │ │ │ │ ├── olmo2.md │ │ │ │ ├── olmoe.md │ │ │ │ ├── omdet-turbo.md │ │ │ │ ├── oneformer.md │ │ │ │ ├── open-llama.md │ │ │ │ ├── openai-gpt.md │ │ │ │ ├── opt.md │ │ │ │ ├── owlv2.md │ │ │ │ ├── owlvit.md │ │ │ │ ├── paligemma.md │ │ │ │ ├── patchtsmixer.md │ │ │ │ ├── patchtst.md │ │ │ │ ├── pegasus.md │ │ │ │ ├── pegasus_x.md │ │ │ │ ├── perceiver.md │ │ │ │ ├── persimmon.md │ │ │ │ ├── phi.md │ │ │ │ ├── phi3.md │ │ │ │ ├── phimoe.md │ │ │ │ ├── phobert.md │ │ │ │ ├── pix2struct.md │ │ │ │ ├── pixtral.md │ │ │ │ ├── plbart.md │ │ │ │ ├── poolformer.md │ │ │ │ ├── pop2piano.md │ │ │ │ ├── prophetnet.md │ │ │ │ ├── pvt.md │ │ │ │ ├── pvt_v2.md │ │ │ │ ├── qdqbert.md │ │ │ │ ├── qwen2.md │ │ │ │ ├── qwen2_5_vl.md │ │ │ │ ├── qwen2_audio.md │ │ │ │ ├── qwen2_moe.md │ │ │ │ ├── qwen2_vl.md │ │ │ │ ├── rag.md │ │ │ │ ├── realm.md │ │ │ │ ├── recurrent_gemma.md │ │ │ │ ├── reformer.md │ │ │ │ ├── regnet.md │ │ │ │ ├── rembert.md │ │ │ │ ├── resnet.md │ │ │ │ ├── retribert.md │ │ │ │ ├── roberta-prelayernorm.md │ │ │ │ ├── roberta.md │ │ │ │ ├── roc_bert.md │ │ │ │ ├── roformer.md │ │ │ │ ├── rt_detr.md │ │ │ │ ├── rt_detr_v2.md │ │ │ │ ├── rwkv.md │ │ │ │ ├── sam.md │ │ │ │ ├── seamless_m4t.md │ │ │ │ ├── seamless_m4t_v2.md │ │ │ │ ├── segformer.md │ │ │ │ ├── seggpt.md │ │ │ │ ├── sew-d.md │ │ │ │ ├── sew.md │ │ │ │ ├── siglip.md │ │ │ │ ├── siglip2.md │ │ │ │ ├── smolvlm.md │ │ │ │ ├── speech-encoder-decoder.md │ │ │ │ ├── speech_to_text.md │ │ │ │ ├── speech_to_text_2.md │ │ │ │ ├── speecht5.md │ │ │ │ ├── splinter.md │ │ │ │ ├── squeezebert.md │ │ │ │ ├── stablelm.md │ │ │ │ ├── starcoder2.md │ │ │ │ ├── superglue.md │ │ │ │ ├── superpoint.md │ │ │ │ ├── swiftformer.md │ │ │ │ ├── swin.md │ │ │ │ ├── swin2sr.md │ │ │ │ ├── swinv2.md │ │ │ │ ├── switch_transformers.md │ │ │ │ ├── t5.md │ │ │ │ ├── t5v1.1.md │ │ │ │ ├── table-transformer.md │ │ │ │ ├── tapas.md │ │ │ │ ├── tapex.md │ │ │ │ ├── textnet.md │ │ │ │ ├── time_series_transformer.md │ │ │ │ ├── timesformer.md │ │ │ │ ├── timm_wrapper.md │ │ │ │ ├── trajectory_transformer.md │ │ │ │ ├── transfo-xl.md │ │ │ │ ├── trocr.md │ │ │ │ ├── tvlt.md │ │ │ │ ├── tvp.md │ │ │ │ ├── udop.md │ │ │ │ ├── ul2.md │ │ │ │ ├── umt5.md │ │ │ │ ├── unispeech-sat.md │ │ │ │ ├── unispeech.md │ │ │ │ ├── univnet.md │ │ │ │ ├── upernet.md │ │ │ │ ├── van.md │ │ │ │ ├── video_llava.md │ │ │ │ ├── videomae.md │ │ │ │ ├── vilt.md │ │ │ │ ├── vipllava.md │ │ │ │ ├── vision-encoder-decoder.md │ │ │ │ ├── vision-text-dual-encoder.md │ │ │ │ ├── visual_bert.md │ │ │ │ ├── vit.md │ │ │ │ ├── vit_hybrid.md │ │ │ │ ├── vit_mae.md │ │ │ │ ├── vit_msn.md │ │ │ │ ├── vitdet.md │ │ │ │ ├── vitmatte.md │ │ │ │ ├── vitpose.md │ │ │ │ ├── vits.md │ │ │ │ ├── vivit.md │ │ │ │ ├── wav2vec2-bert.md │ │ │ │ ├── wav2vec2-conformer.md │ │ │ │ ├── wav2vec2.md │ │ │ │ ├── wav2vec2_phoneme.md │ │ │ │ ├── wavlm.md │ │ │ │ ├── whisper.md │ │ │ │ ├── xclip.md │ │ │ │ ├── xglm.md │ │ │ │ ├── xlm-prophetnet.md │ │ │ │ ├── xlm-roberta-xl.md │ │ │ │ ├── xlm-roberta.md │ │ │ │ ├── xlm-v.md │ │ │ │ ├── xlm.md │ │ │ │ ├── xlnet.md │ │ │ │ ├── xls_r.md │ │ │ │ ├── xlsr_wav2vec2.md │ │ │ │ ├── xmod.md │ │ │ │ ├── yolos.md │ │ │ │ ├── yoso.md │ │ │ │ ├── zamba.md │ │ │ │ ├── zamba2.md │ │ │ │ └── zoedepth.md │ │ │ ├── model_memory_anatomy.md │ │ │ ├── model_sharing.md │ │ │ ├── model_summary.md │ │ │ ├── models.md │ │ │ ├── modular_transformers.md │ │ │ ├── notebooks.md │ │ │ ├── optimizers.md │ │ │ ├── pad_truncation.md │ │ │ ├── peft.md │ │ │ ├── perf_hardware.md │ │ │ ├── perf_infer_cpu.md │ │ │ ├── perf_infer_gpu_multi.md │ │ │ ├── perf_infer_gpu_one.md │ │ │ ├── perf_torch_compile.md │ │ │ ├── perf_train_cpu.md │ │ │ ├── perf_train_cpu_many.md │ │ │ ├── perf_train_gpu_many.md │ │ │ ├── perf_train_gpu_one.md │ │ │ ├── perf_train_special.md │ │ │ ├── perf_train_tpu_tf.md │ │ │ ├── perplexity.md │ │ │ ├── philosophy.md │ │ │ ├── pipeline_gradio.md │ │ │ ├── pipeline_tutorial.md │ │ │ ├── pipeline_webserver.md │ │ │ ├── pr_checks.md │ │ │ ├── processors.md │ │ │ ├── quantization │ │ │ │ ├── aqlm.md │ │ │ │ ├── awq.md │ │ │ │ ├── bitnet.md │ │ │ │ ├── bitsandbytes.md │ │ │ │ ├── compressed_tensors.md │ │ │ │ ├── contribute.md │ │ │ │ ├── eetq.md │ │ │ │ ├── fbgemm_fp8.md │ │ │ │ ├── finegrained_fp8.md │ │ │ │ ├── gptq.md │ │ │ │ ├── higgs.md │ │ │ │ ├── hqq.md │ │ │ │ ├── optimum.md │ │ │ │ ├── overview.md │ │ │ │ ├── quanto.md │ │ │ │ ├── spqr.md │ │ │ │ ├── torchao.md │ │ │ │ └── vptq.md │ │ │ ├── quicktour.md │ │ │ ├── run_scripts.md │ │ │ ├── serialization.md │ │ │ ├── serving.md │ │ │ ├── task_summary.md │ │ │ ├── tasks │ │ │ │ ├── asr.md │ │ │ │ ├── audio_classification.md │ │ │ │ ├── document_question_answering.md │ │ │ │ ├── idefics.md │ │ │ │ ├── image_captioning.md │ │ │ │ ├── image_classification.md │ │ │ │ ├── image_feature_extraction.md │ │ │ │ ├── image_text_to_text.md │ │ │ │ ├── image_to_image.md │ │ │ │ ├── keypoint_detection.md │ │ │ │ ├── knowledge_distillation_for_image_classification.md │ │ │ │ ├── language_modeling.md │ │ │ │ ├── mask_generation.md │ │ │ │ ├── masked_language_modeling.md │ │ │ │ ├── monocular_depth_estimation.md │ │ │ │ ├── multiple_choice.md │ │ │ │ ├── object_detection.md │ │ │ │ ├── prompting.md │ │ │ │ ├── question_answering.md │ │ │ │ ├── semantic_segmentation.md │ │ │ │ ├── sequence_classification.md │ │ │ │ ├── summarization.md │ │ │ │ ├── text-to-speech.md │ │ │ │ ├── token_classification.md │ │ │ │ ├── translation.md │ │ │ │ ├── video_classification.md │ │ │ │ ├── video_text_to_text.md │ │ │ │ ├── visual_question_answering.md │ │ │ │ ├── zero_shot_image_classification.md │ │ │ │ └── zero_shot_object_detection.md │ │ │ ├── tasks_explained.md │ │ │ ├── testing.md │ │ │ ├── tf_xla.md │ │ │ ├── tflite.md │ │ │ ├── tokenizer_summary.md │ │ │ ├── tools.md │ │ │ ├── torchscript.md │ │ │ ├── trainer.md │ │ │ ├── training.md │ │ │ └── troubleshooting.md │ │ │ ├── es │ │ │ ├── _config.py │ │ │ ├── _toctree.yml │ │ │ ├── accelerate.md │ │ │ ├── add_new_pipeline.md │ │ │ ├── attention.md │ │ │ ├── autoclass_tutorial.md │ │ │ ├── bertology.md │ │ │ ├── chat_templating.md │ │ │ ├── community.md │ │ │ ├── converting_tensorflow_models.md │ │ │ ├── create_a_model.md │ │ │ ├── custom_models.md │ │ │ ├── debugging.md │ │ │ ├── fast_tokenizers.md │ │ │ ├── glossary.md │ │ │ ├── index.md │ │ │ ├── installation.md │ │ │ ├── model_memory_anatomy.md │ │ │ ├── model_sharing.md │ │ │ ├── multilingual.md │ │ │ ├── pad_truncation.md │ │ │ ├── performance.md │ │ │ ├── perplexity.md │ │ │ ├── philosophy.md │ │ │ ├── pipeline_tutorial.md │ │ │ ├── pipeline_webserver.md │ │ │ ├── pr_checks.md │ │ │ ├── preprocessing.md │ │ │ ├── quicktour.md │ │ │ ├── run_scripts.md │ │ │ ├── sagemaker.md │ │ │ ├── serialization.md │ │ │ ├── task_summary.md │ │ │ ├── tasks │ │ │ │ ├── asr.md │ │ │ │ ├── image_captioning.md │ │ │ │ ├── image_classification.md │ │ │ │ ├── language_modeling.md │ │ │ │ ├── multiple_choice.md │ │ │ │ ├── question_answering.md │ │ │ │ └── summarization.md │ │ │ ├── tasks_explained.md │ │ │ ├── tokenizer_summary.md │ │ │ ├── torchscript.md │ │ │ ├── trainer.md │ │ │ └── training.md │ │ │ ├── fr │ │ │ ├── _config.py │ │ │ ├── _toctree.yml │ │ │ ├── autoclass_tutorial.md │ │ │ ├── in_translation.md │ │ │ ├── index.md │ │ │ ├── installation.md │ │ │ ├── quicktour.md │ │ │ ├── run_scripts_fr.md │ │ │ ├── task_summary.md │ │ │ ├── tasks_explained.md │ │ │ └── tutoriel_pipeline.md │ │ │ ├── hi │ │ │ ├── _toctree.yml │ │ │ ├── accelerate.md │ │ │ ├── pipeline_tutorial.md │ │ │ └── tflite.md │ │ │ ├── it │ │ │ ├── _config.py │ │ │ ├── _toctree.yml │ │ │ ├── accelerate.md │ │ │ ├── add_new_model.md │ │ │ ├── add_new_pipeline.md │ │ │ ├── autoclass_tutorial.md │ │ │ ├── big_models.md │ │ │ ├── community.md │ │ │ ├── converting_tensorflow_models.md │ │ │ ├── create_a_model.md │ │ │ ├── custom_models.md │ │ │ ├── debugging.md │ │ │ ├── index.md │ │ │ ├── installation.md │ │ │ ├── migration.md │ │ │ ├── model_sharing.md │ │ │ ├── multilingual.md │ │ │ ├── perf_hardware.md │ │ │ ├── perf_infer_cpu.md │ │ │ ├── perf_infer_gpu_many.md │ │ │ ├── perf_infer_gpu_one.md │ │ │ ├── perf_infer_special.md │ │ │ ├── perf_train_cpu.md │ │ │ ├── perf_train_cpu_many.md │ │ │ ├── perf_train_special.md │ │ │ ├── perf_train_tpu.md │ │ │ ├── pipeline_tutorial.md │ │ │ ├── pr_checks.md │ │ │ ├── preprocessing.md │ │ │ ├── quicktour.md │ │ │ ├── run_scripts.md │ │ │ ├── serialization.md │ │ │ └── training.md │ │ │ ├── ja │ │ │ ├── _toctree.yml │ │ │ ├── accelerate.md │ │ │ ├── add_new_model.md │ │ │ ├── attention.md │ │ │ ├── autoclass_tutorial.md │ │ │ ├── bertology.md │ │ │ ├── big_models.md │ │ │ ├── chat_templating.md │ │ │ ├── community.md │ │ │ ├── create_a_model.md │ │ │ ├── custom_models.md │ │ │ ├── custom_tools.md │ │ │ ├── fast_tokenizers.md │ │ │ ├── generation_strategies.md │ │ │ ├── glossary.md │ │ │ ├── hpo_train.md │ │ │ ├── index.md │ │ │ ├── installation.md │ │ │ ├── internal │ │ │ │ ├── audio_utils.md │ │ │ │ ├── file_utils.md │ │ │ │ ├── generation_utils.md │ │ │ │ ├── image_processing_utils.md │ │ │ │ ├── modeling_utils.md │ │ │ │ ├── pipelines_utils.md │ │ │ │ ├── time_series_utils.md │ │ │ │ ├── tokenization_utils.md │ │ │ │ └── trainer_utils.md │ │ │ ├── llm_tutorial.md │ │ │ ├── main_classes │ │ │ │ ├── agent.md │ │ │ │ ├── callback.md │ │ │ │ ├── configuration.md │ │ │ │ ├── data_collator.md │ │ │ │ ├── deepspeed.md │ │ │ │ ├── feature_extractor.md │ │ │ │ ├── image_processor.md │ │ │ │ ├── keras_callbacks.md │ │ │ │ ├── logging.md │ │ │ │ ├── model.md │ │ │ │ ├── onnx.md │ │ │ │ ├── optimizer_schedules.md │ │ │ │ ├── output.md │ │ │ │ ├── pipelines.md │ │ │ │ ├── processors.md │ │ │ │ ├── quantization.md │ │ │ │ ├── text_generation.md │ │ │ │ ├── tokenizer.md │ │ │ │ └── trainer.md │ │ │ ├── model_doc │ │ │ │ ├── albert.md │ │ │ │ ├── align.md │ │ │ │ ├── altclip.md │ │ │ │ ├── audio-spectrogram-transformer.md │ │ │ │ ├── auto.md │ │ │ │ ├── autoformer.md │ │ │ │ ├── bark.md │ │ │ │ ├── bart.md │ │ │ │ ├── barthez.md │ │ │ │ ├── bartpho.md │ │ │ │ ├── beit.md │ │ │ │ ├── bert-generation.md │ │ │ │ ├── bert-japanese.md │ │ │ │ ├── bert.md │ │ │ │ ├── bertweet.md │ │ │ │ ├── big_bird.md │ │ │ │ ├── bigbird_pegasus.md │ │ │ │ ├── biogpt.md │ │ │ │ ├── bit.md │ │ │ │ ├── blenderbot-small.md │ │ │ │ ├── blenderbot.md │ │ │ │ ├── blip-2.md │ │ │ │ ├── blip.md │ │ │ │ ├── bloom.md │ │ │ │ ├── bort.md │ │ │ │ ├── bridgetower.md │ │ │ │ ├── bros.md │ │ │ │ ├── byt5.md │ │ │ │ ├── camembert.md │ │ │ │ ├── canine.md │ │ │ │ ├── chinese_clip.md │ │ │ │ ├── clap.md │ │ │ │ ├── clip.md │ │ │ │ ├── clipseg.md │ │ │ │ ├── clvp.md │ │ │ │ ├── code_llama.md │ │ │ │ ├── codegen.md │ │ │ │ ├── conditional_detr.md │ │ │ │ ├── convbert.md │ │ │ │ ├── convnext.md │ │ │ │ ├── convnextv2.md │ │ │ │ ├── cpm.md │ │ │ │ ├── cpmant.md │ │ │ │ ├── ctrl.md │ │ │ │ ├── cvt.md │ │ │ │ ├── data2vec.md │ │ │ │ ├── deberta-v2.md │ │ │ │ ├── deberta.md │ │ │ │ ├── decision_transformer.md │ │ │ │ ├── deformable_detr.md │ │ │ │ ├── deit.md │ │ │ │ ├── deplot.md │ │ │ │ ├── deta.md │ │ │ │ ├── detr.md │ │ │ │ ├── dialogpt.md │ │ │ │ └── dinat.md │ │ │ ├── model_memory_anatomy.md │ │ │ ├── model_sharing.md │ │ │ ├── model_summary.md │ │ │ ├── multilingual.md │ │ │ ├── pad_truncation.md │ │ │ ├── peft.md │ │ │ ├── perf_hardware.md │ │ │ ├── perf_infer_cpu.md │ │ │ ├── perf_infer_gpu_many.md │ │ │ ├── perf_infer_gpu_one.md │ │ │ ├── perf_infer_special.md │ │ │ ├── perf_torch_compile.md │ │ │ ├── perf_train_cpu.md │ │ │ ├── perf_train_cpu_many.md │ │ │ ├── perf_train_gpu_many.md │ │ │ ├── perf_train_gpu_one.md │ │ │ ├── perf_train_special.md │ │ │ ├── perf_train_tpu.md │ │ │ ├── perf_train_tpu_tf.md │ │ │ ├── performance.md │ │ │ ├── perplexity.md │ │ │ ├── philosophy.md │ │ │ ├── pipeline_tutorial.md │ │ │ ├── pipeline_webserver.md │ │ │ ├── pr_checks.md │ │ │ ├── preprocessing.md │ │ │ ├── quicktour.md │ │ │ ├── run_scripts.md │ │ │ ├── serialization.md │ │ │ ├── task_summary.md │ │ │ ├── tasks │ │ │ │ ├── asr.md │ │ │ │ ├── audio_classification.md │ │ │ │ ├── document_question_answering.md │ │ │ │ ├── idefics.md │ │ │ │ ├── image_captioning.md │ │ │ │ ├── image_classification.md │ │ │ │ ├── image_to_image.md │ │ │ │ ├── knowledge_distillation_for_image_classification.md │ │ │ │ ├── language_modeling.md │ │ │ │ ├── masked_language_modeling.md │ │ │ │ ├── monocular_depth_estimation.md │ │ │ │ ├── multiple_choice.md │ │ │ │ ├── object_detection.md │ │ │ │ ├── prompting.md │ │ │ │ ├── question_answering.md │ │ │ │ ├── semantic_segmentation.md │ │ │ │ ├── sequence_classification.md │ │ │ │ ├── summarization.md │ │ │ │ ├── text-to-speech.md │ │ │ │ ├── token_classification.md │ │ │ │ ├── translation.md │ │ │ │ ├── video_classification.md │ │ │ │ ├── visual_question_answering.md │ │ │ │ ├── zero_shot_image_classification.md │ │ │ │ └── zero_shot_object_detection.md │ │ │ ├── tasks_explained.md │ │ │ ├── testing.md │ │ │ ├── tf_xla.md │ │ │ ├── tflite.md │ │ │ ├── tokenizer_summary.md │ │ │ ├── torchscript.md │ │ │ ├── training.md │ │ │ ├── transformers_agents.md │ │ │ └── troubleshooting.md │ │ │ ├── ko │ │ │ ├── _config.py │ │ │ ├── _toctree.yml │ │ │ ├── accelerate.md │ │ │ ├── add_new_model.md │ │ │ ├── add_new_pipeline.md │ │ │ ├── attention.md │ │ │ ├── autoclass_tutorial.md │ │ │ ├── bertology.md │ │ │ ├── big_models.md │ │ │ ├── chat_templating.md │ │ │ ├── community.md │ │ │ ├── contributing.md │ │ │ ├── conversations.md │ │ │ ├── create_a_model.md │ │ │ ├── custom_models.md │ │ │ ├── debugging.md │ │ │ ├── deepspeed.md │ │ │ ├── fast_tokenizers.md │ │ │ ├── fsdp.md │ │ │ ├── generation_strategies.md │ │ │ ├── gguf.md │ │ │ ├── hpo_train.md │ │ │ ├── in_translation.md │ │ │ ├── index.md │ │ │ ├── installation.md │ │ │ ├── internal │ │ │ │ ├── audio_utils.md │ │ │ │ ├── file_utils.md │ │ │ │ ├── generation_utils.md │ │ │ │ ├── image_processing_utils.md │ │ │ │ ├── modeling_utils.md │ │ │ │ ├── pipelines_utils.md │ │ │ │ ├── time_series_utils.md │ │ │ │ ├── tokenization_utils.md │ │ │ │ └── trainer_utils.md │ │ │ ├── llm_optims.md │ │ │ ├── llm_tutorial.md │ │ │ ├── llm_tutorial_optimization.md │ │ │ ├── main_classes │ │ │ │ ├── agent.md │ │ │ │ ├── callback.md │ │ │ │ ├── configuration.md │ │ │ │ ├── data_collator.md │ │ │ │ ├── executorch.md │ │ │ │ ├── feature_extractor.md │ │ │ │ ├── keras_callbacks.md │ │ │ │ ├── logging.md │ │ │ │ ├── model.md │ │ │ │ ├── onnx.md │ │ │ │ ├── output.md │ │ │ │ ├── quantization.md │ │ │ │ ├── text_generation.md │ │ │ │ └── trainer.md │ │ │ ├── model_doc │ │ │ │ ├── altclip.md │ │ │ │ ├── auto.md │ │ │ │ ├── autoformer.md │ │ │ │ ├── bart.md │ │ │ │ ├── barthez.md │ │ │ │ ├── bartpho.md │ │ │ │ ├── bert-japanese.md │ │ │ │ ├── bert.md │ │ │ │ ├── bertweet.md │ │ │ │ ├── biogpt.md │ │ │ │ ├── blip-2.md │ │ │ │ ├── blip.md │ │ │ │ ├── chameleon.md │ │ │ │ ├── clip.md │ │ │ │ ├── codegen.md │ │ │ │ ├── cohere.md │ │ │ │ ├── convbert.md │ │ │ │ ├── dbrx.md │ │ │ │ ├── deberta-v2.md │ │ │ │ ├── deberta.md │ │ │ │ ├── encoder-decoder.md │ │ │ │ ├── esm.md │ │ │ │ ├── gemma.md │ │ │ │ ├── gemma2.md │ │ │ │ ├── gpt_neox_japanese.md │ │ │ │ ├── graphormer.md │ │ │ │ ├── informer.md │ │ │ │ ├── llama.md │ │ │ │ ├── llama2.md │ │ │ │ ├── llama3.md │ │ │ │ ├── mamba.md │ │ │ │ ├── mamba2.md │ │ │ │ ├── marian.md │ │ │ │ ├── mistral.md │ │ │ │ ├── openai-gpt.md │ │ │ │ ├── paligemma.md │ │ │ │ ├── patchtsmixer.md │ │ │ │ ├── patchtst.md │ │ │ │ ├── rag.md │ │ │ │ ├── swin.md │ │ │ │ ├── swin2sr.md │ │ │ │ ├── swinv2.md │ │ │ │ ├── time_series_transformer.md │ │ │ │ ├── timesformer.md │ │ │ │ ├── trajectory_transformer.md │ │ │ │ ├── vit.md │ │ │ │ ├── vivit.md │ │ │ │ └── whisper.md │ │ │ ├── model_memory_anatomy.md │ │ │ ├── model_sharing.md │ │ │ ├── model_summary.md │ │ │ ├── modular_transformers.md │ │ │ ├── multilingual.md │ │ │ ├── pad_truncation.md │ │ │ ├── peft.md │ │ │ ├── perf_hardware.md │ │ │ ├── perf_infer_cpu.md │ │ │ ├── perf_infer_gpu_one.md │ │ │ ├── perf_train_cpu.md │ │ │ ├── perf_train_cpu_many.md │ │ │ ├── perf_train_gpu_many.md │ │ │ ├── perf_train_special.md │ │ │ ├── perf_train_tpu_tf.md │ │ │ ├── performance.md │ │ │ ├── perplexity.md │ │ │ ├── philosophy.md │ │ │ ├── pipeline_tutorial.md │ │ │ ├── pipeline_webserver.md │ │ │ ├── pr_checks.md │ │ │ ├── preprocessing.md │ │ │ ├── quantization │ │ │ │ ├── awq.md │ │ │ │ ├── bitsandbytes.md │ │ │ │ ├── eetq.md │ │ │ │ ├── gptq.md │ │ │ │ └── quanto.md │ │ │ ├── quicktour.md │ │ │ ├── run_scripts.md │ │ │ ├── sagemaker.md │ │ │ ├── serialization.md │ │ │ ├── task_summary.md │ │ │ ├── tasks │ │ │ │ ├── asr.md │ │ │ │ ├── audio_classification.md │ │ │ │ ├── document_question_answering.md │ │ │ │ ├── idefics.md │ │ │ │ ├── image_captioning.md │ │ │ │ ├── image_classification.md │ │ │ │ ├── image_feature_extraction.md │ │ │ │ ├── image_to_image.md │ │ │ │ ├── knowledge_distillation_for_image_classification.md │ │ │ │ ├── language_modeling.md │ │ │ │ ├── mask_generation.md │ │ │ │ ├── masked_language_modeling.md │ │ │ │ ├── monocular_depth_estimation.md │ │ │ │ ├── multiple_choice.md │ │ │ │ ├── object_detection.md │ │ │ │ ├── prompting.md │ │ │ │ ├── question_answering.md │ │ │ │ ├── semantic_segmentation.md │ │ │ │ ├── sequence_classification.md │ │ │ │ ├── summarization.md │ │ │ │ ├── token_classification.md │ │ │ │ ├── translation.md │ │ │ │ ├── video_classification.md │ │ │ │ ├── visual_question_answering.md │ │ │ │ ├── zero_shot_image_classification.md │ │ │ │ └── zero_shot_object_detection.md │ │ │ ├── tasks_explained.md │ │ │ ├── testing.md │ │ │ ├── tf_xla.md │ │ │ ├── tflite.md │ │ │ ├── tokenizer_summary.md │ │ │ ├── torchscript.md │ │ │ ├── trainer.md │ │ │ ├── training.md │ │ │ ├── transformers_agents.md │ │ │ └── troubleshooting.md │ │ │ ├── ms │ │ │ ├── _toctree.yml │ │ │ └── index.md │ │ │ ├── pt │ │ │ ├── _config.py │ │ │ ├── _toctree.yml │ │ │ ├── accelerate.md │ │ │ ├── converting_tensorflow_models.md │ │ │ ├── create_a_model.md │ │ │ ├── custom_models.md │ │ │ ├── fast_tokenizers.md │ │ │ ├── index.md │ │ │ ├── installation.md │ │ │ ├── multilingual.md │ │ │ ├── pipeline_tutorial.md │ │ │ ├── quicktour.md │ │ │ ├── run_scripts.md │ │ │ ├── serialization.md │ │ │ ├── tasks │ │ │ │ ├── sequence_classification.md │ │ │ │ └── token_classification.md │ │ │ └── training.md │ │ │ ├── te │ │ │ ├── _toctree.yml │ │ │ ├── index.md │ │ │ └── quicktour.md │ │ │ ├── tr │ │ │ ├── _toctree.yml │ │ │ └── index.md │ │ │ └── zh │ │ │ ├── _toctree.yml │ │ │ ├── accelerate.md │ │ │ ├── add_new_pipeline.md │ │ │ ├── agents.md │ │ │ ├── agents_advanced.md │ │ │ ├── attention.md │ │ │ ├── autoclass_tutorial.md │ │ │ ├── bertology.md │ │ │ ├── big_models.md │ │ │ ├── chat_templating.md │ │ │ ├── community.md │ │ │ ├── contributing.md │ │ │ ├── create_a_model.md │ │ │ ├── custom_models.md │ │ │ ├── debugging.md │ │ │ ├── fast_tokenizers.md │ │ │ ├── fsdp.md │ │ │ ├── gguf.md │ │ │ ├── hpo_train.md │ │ │ ├── index.md │ │ │ ├── installation.md │ │ │ ├── internal │ │ │ ├── audio_utils.md │ │ │ ├── file_utils.md │ │ │ ├── generation_utils.md │ │ │ ├── image_processing_utils.md │ │ │ ├── modeling_utils.md │ │ │ ├── pipelines_utils.md │ │ │ ├── time_series_utils.md │ │ │ ├── tokenization_utils.md │ │ │ └── trainer_utils.md │ │ │ ├── llm_tutorial.md │ │ │ ├── main_classes │ │ │ ├── agent.md │ │ │ ├── callback.md │ │ │ ├── configuration.md │ │ │ ├── data_collator.md │ │ │ ├── deepspeed.md │ │ │ ├── feature_extractor.md │ │ │ ├── image_processor.md │ │ │ ├── keras_callbacks.md │ │ │ ├── logging.md │ │ │ ├── model.md │ │ │ ├── onnx.md │ │ │ ├── optimizer_schedules.md │ │ │ ├── output.md │ │ │ ├── pipelines.md │ │ │ ├── processors.md │ │ │ ├── quantization.md │ │ │ ├── text_generation.md │ │ │ ├── tokenizer.md │ │ │ └── trainer.md │ │ │ ├── model_sharing.md │ │ │ ├── multilingual.md │ │ │ ├── peft.md │ │ │ ├── perf_hardware.md │ │ │ ├── perf_infer_gpu_multi.md │ │ │ ├── perf_torch_compile.md │ │ │ ├── perf_train_cpu.md │ │ │ ├── perf_train_special.md │ │ │ ├── performance.md │ │ │ ├── philosophy.md │ │ │ ├── pipeline_tutorial.md │ │ │ ├── preprocessing.md │ │ │ ├── quicktour.md │ │ │ ├── run_scripts.md │ │ │ ├── serialization.md │ │ │ ├── task_summary.md │ │ │ ├── tasks │ │ │ └── asr.md │ │ │ ├── tf_xla.md │ │ │ ├── tflite.md │ │ │ ├── tiktoken.md │ │ │ ├── tokenizer_summary.md │ │ │ ├── torchscript.md │ │ │ └── training.md │ │ ├── examples │ │ ├── README.md │ │ ├── flax │ │ │ ├── README.md │ │ │ ├── _tests_requirements.txt │ │ │ ├── conftest.py │ │ │ ├── image-captioning │ │ │ │ ├── README.md │ │ │ │ ├── create_model_from_encoder_decoder_models.py │ │ │ │ └── run_image_captioning_flax.py │ │ │ ├── language-modeling │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_bart_dlm_flax.py │ │ │ │ ├── run_bert_flax.py │ │ │ │ ├── run_clm_flax.py │ │ │ │ ├── run_mlm_flax.py │ │ │ │ ├── run_t5_mlm_flax.py │ │ │ │ └── t5_tokenizer_model.py │ │ │ ├── question-answering │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_qa.py │ │ │ │ └── utils_qa.py │ │ │ ├── speech-recognition │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_flax_speech_recognition_seq2seq.py │ │ │ ├── summarization │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_summarization_flax.py │ │ │ ├── test_flax_examples.py │ │ │ ├── text-classification │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_flax_glue.py │ │ │ ├── token-classification │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_flax_ner.py │ │ │ └── vision │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_image_classification.py │ │ ├── legacy │ │ │ ├── README.md │ │ │ ├── benchmarking │ │ │ │ ├── README.md │ │ │ │ ├── plot_csv_file.py │ │ │ │ ├── requirements.txt │ │ │ │ └── run_benchmark.py │ │ │ ├── multiple_choice │ │ │ │ ├── run_multiple_choice.py │ │ │ │ └── utils_multiple_choice.py │ │ │ ├── pytorch-lightning │ │ │ │ ├── lightning_base.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_glue.py │ │ │ │ ├── run_glue.sh │ │ │ │ ├── run_ner.py │ │ │ │ ├── run_ner.sh │ │ │ │ └── run_pos.sh │ │ │ ├── question-answering │ │ │ │ ├── README.md │ │ │ │ ├── run_squad.py │ │ │ │ └── run_squad_trainer.py │ │ │ ├── run_camembert.py │ │ │ ├── run_chinese_ref.py │ │ │ ├── run_language_modeling.py │ │ │ ├── run_openai_gpt.py │ │ │ ├── run_swag.py │ │ │ ├── run_transfo_xl.py │ │ │ ├── seq2seq │ │ │ │ ├── README.md │ │ │ │ ├── __init__.py │ │ │ │ ├── convert_model_to_fp16.py │ │ │ │ ├── download_wmt.py │ │ │ │ ├── finetune.sh │ │ │ │ ├── finetune_tpu.sh │ │ │ │ ├── finetune_trainer.py │ │ │ │ ├── minify_dataset.py │ │ │ │ ├── old_test_calculate_rouge.py │ │ │ │ ├── old_test_datasets.py │ │ │ │ ├── old_test_fsmt_bleu_score.py │ │ │ │ ├── old_test_seq2seq_examples.py │ │ │ │ ├── old_test_seq2seq_examples_multi_gpu.py │ │ │ │ ├── old_test_tatoeba_conversion.py │ │ │ │ ├── pack_dataset.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── romanian_postprocessing.md │ │ │ │ ├── rouge_cli.py │ │ │ │ ├── run_distributed_eval.py │ │ │ │ ├── run_eval.py │ │ │ │ ├── run_eval_search.py │ │ │ │ ├── save_len_file.py │ │ │ │ ├── save_randomly_initialized_model.py │ │ │ │ ├── sentence_splitter.py │ │ │ │ ├── seq2seq_trainer.py │ │ │ │ ├── seq2seq_training_args.py │ │ │ │ ├── test_data │ │ │ │ │ ├── fsmt │ │ │ │ │ │ ├── build-eval-data.py │ │ │ │ │ │ └── fsmt_val_data.json │ │ │ │ │ └── wmt_en_ro │ │ │ │ │ │ ├── test.source │ │ │ │ │ │ ├── test.target │ │ │ │ │ │ ├── train.len │ │ │ │ │ │ ├── train.source │ │ │ │ │ │ ├── train.target │ │ │ │ │ │ ├── val.len │ │ │ │ │ │ ├── val.source │ │ │ │ │ │ └── val.target │ │ │ │ ├── train_distil_marian_enro.sh │ │ │ │ ├── train_distil_marian_enro_tpu.sh │ │ │ │ ├── train_distilbart_cnn.sh │ │ │ │ ├── train_mbart_cc25_enro.sh │ │ │ │ ├── utils.py │ │ │ │ └── xla_spawn.py │ │ │ └── token-classification │ │ │ │ ├── README.md │ │ │ │ ├── run.sh │ │ │ │ ├── run_chunk.sh │ │ │ │ ├── run_ner.py │ │ │ │ ├── run_pos.sh │ │ │ │ ├── scripts │ │ │ │ └── preprocess.py │ │ │ │ ├── tasks.py │ │ │ │ └── utils_ner.py │ │ ├── modular-transformers │ │ │ ├── README.md │ │ │ ├── configuration_dummy.py │ │ │ ├── configuration_my_new_model.py │ │ │ ├── configuration_my_new_model2.py │ │ │ ├── configuration_new_model.py │ │ │ ├── configuration_super.py │ │ │ ├── convert_examples.sh │ │ │ ├── image_processing_new_imgproc_model.py │ │ │ ├── modeling_add_function.py │ │ │ ├── modeling_dummy.py │ │ │ ├── modeling_dummy_bert.py │ │ │ ├── modeling_from_uppercase_model.py │ │ │ ├── modeling_multimodal1.py │ │ │ ├── modeling_multimodal2.py │ │ │ ├── modeling_my_new_model2.py │ │ │ ├── modeling_new_task_model.py │ │ │ ├── modeling_roberta.py │ │ │ ├── modeling_super.py │ │ │ ├── modeling_switch_function.py │ │ │ ├── modular_add_function.py │ │ │ ├── modular_dummy.py │ │ │ ├── modular_dummy_bert.py │ │ │ ├── modular_from_uppercase_model.py │ │ │ ├── modular_multimodal1.py │ │ │ ├── modular_multimodal2.py │ │ │ ├── modular_my_new_model.py │ │ │ ├── modular_my_new_model2.py │ │ │ ├── modular_new_imgproc_model.py │ │ │ ├── modular_new_model.py │ │ │ ├── modular_new_task_model.py │ │ │ ├── modular_roberta.py │ │ │ ├── modular_super.py │ │ │ └── modular_switch_function.py │ │ ├── pytorch │ │ │ ├── README.md │ │ │ ├── _tests_requirements.txt │ │ │ ├── audio-classification │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_audio_classification.py │ │ │ ├── conftest.py │ │ │ ├── contrastive-image-text │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_clip.py │ │ │ ├── image-classification │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_image_classification.py │ │ │ │ └── run_image_classification_no_trainer.py │ │ │ ├── image-pretraining │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_mae.py │ │ │ │ ├── run_mim.py │ │ │ │ └── run_mim_no_trainer.py │ │ │ ├── instance-segmentation │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_instance_segmentation.py │ │ │ │ └── run_instance_segmentation_no_trainer.py │ │ │ ├── language-modeling │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_clm.py │ │ │ │ ├── run_clm_no_trainer.py │ │ │ │ ├── run_fim.py │ │ │ │ ├── run_fim_no_trainer.py │ │ │ │ ├── run_mlm.py │ │ │ │ ├── run_mlm_no_trainer.py │ │ │ │ └── run_plm.py │ │ │ ├── multiple-choice │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_no_trainer.sh │ │ │ │ ├── run_swag.py │ │ │ │ └── run_swag_no_trainer.py │ │ │ ├── object-detection │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_object_detection.py │ │ │ │ └── run_object_detection_no_trainer.py │ │ │ ├── old_test_xla_examples.py │ │ │ ├── question-answering │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_qa.py │ │ │ │ ├── run_qa_beam_search.py │ │ │ │ ├── run_qa_beam_search_no_trainer.py │ │ │ │ ├── run_qa_no_trainer.py │ │ │ │ ├── run_seq2seq_qa.py │ │ │ │ ├── trainer_qa.py │ │ │ │ ├── trainer_seq2seq_qa.py │ │ │ │ └── utils_qa.py │ │ │ ├── semantic-segmentation │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_semantic_segmentation.py │ │ │ │ └── run_semantic_segmentation_no_trainer.py │ │ │ ├── speech-pretraining │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_wav2vec2_pretraining_no_trainer.py │ │ │ ├── speech-recognition │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_speech_recognition_ctc.py │ │ │ │ ├── run_speech_recognition_ctc_adapter.py │ │ │ │ └── run_speech_recognition_seq2seq.py │ │ │ ├── summarization │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_summarization.py │ │ │ │ └── run_summarization_no_trainer.py │ │ │ ├── test_accelerate_examples.py │ │ │ ├── test_pytorch_examples.py │ │ │ ├── text-classification │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_classification.py │ │ │ │ ├── run_glue.py │ │ │ │ ├── run_glue_no_trainer.py │ │ │ │ └── run_xnli.py │ │ │ ├── text-generation │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_generation.py │ │ │ │ └── run_generation_contrastive_search.py │ │ │ ├── token-classification │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run.sh │ │ │ │ ├── run_ner.py │ │ │ │ ├── run_ner_no_trainer.py │ │ │ │ └── run_no_trainer.sh │ │ │ ├── translation │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_translation.py │ │ │ │ └── run_translation_no_trainer.py │ │ │ └── xla_spawn.py │ │ ├── quantization │ │ │ ├── custom_quantization.py │ │ │ └── custom_quantization_int8_example.py │ │ ├── research_projects │ │ │ └── README.md │ │ ├── run_on_remote.py │ │ ├── tensorflow │ │ │ ├── README.md │ │ │ ├── _tests_requirements.txt │ │ │ ├── contrastive-image-text │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_clip.py │ │ │ ├── image-classification │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_image_classification.py │ │ │ ├── language-modeling-tpu │ │ │ │ ├── README.md │ │ │ │ ├── prepare_tfrecord_shards.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_mlm.py │ │ │ │ └── train_unigram.py │ │ │ ├── language-modeling │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_clm.py │ │ │ │ └── run_mlm.py │ │ │ ├── multiple-choice │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_swag.py │ │ │ ├── question-answering │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_qa.py │ │ │ │ └── utils_qa.py │ │ │ ├── summarization │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_summarization.py │ │ │ ├── test_tensorflow_examples.py │ │ │ ├── text-classification │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_glue.py │ │ │ │ └── run_text_classification.py │ │ │ ├── token-classification │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_ner.py │ │ │ └── translation │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_translation.py │ │ └── training │ │ │ └── distributed_training.py │ │ ├── hubconf.py │ │ ├── i18n │ │ ├── README_ar.md │ │ ├── README_de.md │ │ ├── README_es.md │ │ ├── README_fr.md │ │ ├── README_hd.md │ │ ├── README_ja.md │ │ ├── README_ko.md │ │ ├── README_pt-br.md │ │ ├── README_ru.md │ │ ├── README_te.md │ │ ├── README_ur.md │ │ ├── README_vi.md │ │ ├── README_zh-hans.md │ │ └── README_zh-hant.md │ │ ├── model_cards │ │ └── README.md │ │ ├── notebooks │ │ └── README.md │ │ ├── pyproject.toml │ │ ├── scripts │ │ ├── benchmark │ │ │ └── trainer-benchmark.py │ │ ├── check_tokenizers.py │ │ ├── deberta_scrtipt.py │ │ ├── distributed │ │ │ └── torch-distributed-gpu-test.py │ │ ├── fsmt │ │ │ ├── convert-allenai-wmt16.sh │ │ │ ├── convert-allenai-wmt19.sh │ │ │ ├── convert-facebook-wmt19.sh │ │ │ ├── eval-allenai-wmt16.sh │ │ │ ├── eval-allenai-wmt19.sh │ │ │ ├── eval-facebook-wmt19.sh │ │ │ ├── fsmt-make-super-tiny-model.py │ │ │ ├── fsmt-make-tiny-model.py │ │ │ ├── gen-card-allenai-wmt16.py │ │ │ ├── gen-card-allenai-wmt19.py │ │ │ ├── gen-card-facebook-wmt19.py │ │ │ ├── s3-move.sh │ │ │ └── tests-to-run.sh │ │ ├── pegasus │ │ │ └── build_test_sample_spm_no_bos.py │ │ ├── stale.py │ │ └── tatoeba │ │ │ ├── README.md │ │ │ └── upload_models.sh │ │ ├── setup.py │ │ ├── src │ │ └── transformers │ │ │ ├── __init__.py │ │ │ ├── activations.py │ │ │ ├── activations_tf.py │ │ │ ├── agents │ │ │ ├── __init__.py │ │ │ ├── agent_types.py │ │ │ ├── agents.py │ │ │ ├── default_tools.py │ │ │ ├── document_question_answering.py │ │ │ ├── evaluate_agent.py │ │ │ ├── image_question_answering.py │ │ │ ├── llm_engine.py │ │ │ ├── monitoring.py │ │ │ ├── prompts.py │ │ │ ├── python_interpreter.py │ │ │ ├── search.py │ │ │ ├── speech_to_text.py │ │ │ ├── text_to_speech.py │ │ │ ├── tools.py │ │ │ └── translation.py │ │ │ ├── audio_utils.py │ │ │ ├── cache_utils.py │ │ │ ├── commands │ │ │ ├── __init__.py │ │ │ ├── add_fast_image_processor.py │ │ │ ├── add_new_model_like.py │ │ │ ├── chat.py │ │ │ ├── convert.py │ │ │ ├── download.py │ │ │ ├── env.py │ │ │ ├── run.py │ │ │ ├── serving.py │ │ │ ├── train.py │ │ │ └── transformers_cli.py │ │ │ ├── configuration_utils.py │ │ │ ├── convert_graph_to_onnx.py │ │ │ ├── convert_pytorch_checkpoint_to_tf2.py │ │ │ ├── convert_slow_tokenizer.py │ │ │ ├── convert_slow_tokenizers_checkpoints_to_fast.py │ │ │ ├── convert_tf_hub_seq_to_seq_bert_to_pytorch.py │ │ │ ├── data │ │ │ ├── __init__.py │ │ │ ├── data_collator.py │ │ │ ├── datasets │ │ │ │ ├── __init__.py │ │ │ │ ├── glue.py │ │ │ │ ├── language_modeling.py │ │ │ │ └── squad.py │ │ │ ├── metrics │ │ │ │ ├── __init__.py │ │ │ │ └── squad_metrics.py │ │ │ └── processors │ │ │ │ ├── __init__.py │ │ │ │ ├── glue.py │ │ │ │ ├── squad.py │ │ │ │ ├── utils.py │ │ │ │ └── xnli.py │ │ │ ├── debug_utils.py │ │ │ ├── dependency_versions_check.py │ │ │ ├── dependency_versions_table.py │ │ │ ├── dynamic_module_utils.py │ │ │ ├── feature_extraction_sequence_utils.py │ │ │ ├── feature_extraction_utils.py │ │ │ ├── file_utils.py │ │ │ ├── generation │ │ │ ├── __init__.py │ │ │ ├── beam_constraints.py │ │ │ ├── beam_search.py │ │ │ ├── candidate_generator.py │ │ │ ├── configuration_utils.py │ │ │ ├── flax_logits_process.py │ │ │ ├── flax_utils.py │ │ │ ├── logits_process.py │ │ │ ├── stopping_criteria.py │ │ │ ├── streamers.py │ │ │ ├── tf_logits_process.py │ │ │ ├── tf_utils.py │ │ │ ├── utils.py │ │ │ └── watermarking.py │ │ │ ├── hf_argparser.py │ │ │ ├── hyperparameter_search.py │ │ │ ├── image_processing_base.py │ │ │ ├── image_processing_utils.py │ │ │ ├── image_processing_utils_fast.py │ │ │ ├── image_transforms.py │ │ │ ├── image_utils.py │ │ │ ├── integrations │ │ │ ├── __init__.py │ │ │ ├── aqlm.py │ │ │ ├── awq.py │ │ │ ├── bitnet.py │ │ │ ├── bitsandbytes.py │ │ │ ├── deepspeed.py │ │ │ ├── eetq.py │ │ │ ├── executorch.py │ │ │ ├── fbgemm_fp8.py │ │ │ ├── finegrained_fp8.py │ │ │ ├── flash_attention.py │ │ │ ├── flex_attention.py │ │ │ ├── fsdp.py │ │ │ ├── ggml.py │ │ │ ├── higgs.py │ │ │ ├── hqq.py │ │ │ ├── integration_utils.py │ │ │ ├── mistral.py │ │ │ ├── peft.py │ │ │ ├── quanto.py │ │ │ ├── sdpa_attention.py │ │ │ ├── spqr.py │ │ │ ├── tensor_parallel.py │ │ │ ├── tiktoken.py │ │ │ ├── tpu.py │ │ │ └── vptq.py │ │ │ ├── keras_callbacks.py │ │ │ ├── kernels │ │ │ ├── __init__.py │ │ │ ├── deformable_detr │ │ │ │ ├── cpu │ │ │ │ │ ├── ms_deform_attn_cpu.cpp │ │ │ │ │ └── ms_deform_attn_cpu.h │ │ │ │ ├── cuda │ │ │ │ │ ├── ms_deform_attn_cuda.cu │ │ │ │ │ ├── ms_deform_attn_cuda.cuh │ │ │ │ │ ├── ms_deform_attn_cuda.h │ │ │ │ │ └── ms_deform_im2col_cuda.cuh │ │ │ │ ├── ms_deform_attn.h │ │ │ │ └── vision.cpp │ │ │ ├── deta │ │ │ │ ├── cpu │ │ │ │ │ ├── ms_deform_attn_cpu.cpp │ │ │ │ │ └── ms_deform_attn_cpu.h │ │ │ │ ├── cuda │ │ │ │ │ ├── ms_deform_attn_cuda.cu │ │ │ │ │ ├── ms_deform_attn_cuda.cuh │ │ │ │ │ ├── ms_deform_attn_cuda.h │ │ │ │ │ └── ms_deform_im2col_cuda.cuh │ │ │ │ ├── ms_deform_attn.h │ │ │ │ └── vision.cpp │ │ │ ├── falcon_mamba │ │ │ │ ├── __init__.py │ │ │ │ └── selective_scan_with_ln_interface.py │ │ │ ├── mra │ │ │ │ ├── cuda_kernel.cu │ │ │ │ ├── cuda_kernel.h │ │ │ │ ├── cuda_launch.cu │ │ │ │ ├── cuda_launch.h │ │ │ │ └── torch_extension.cpp │ │ │ ├── rwkv │ │ │ │ ├── wkv_cuda.cu │ │ │ │ ├── wkv_cuda_bf16.cu │ │ │ │ └── wkv_op.cpp │ │ │ └── yoso │ │ │ │ ├── common.h │ │ │ │ ├── common_cuda.h │ │ │ │ ├── common_cuda_device.h │ │ │ │ ├── fast_lsh_cumulation.cu │ │ │ │ ├── fast_lsh_cumulation.h │ │ │ │ ├── fast_lsh_cumulation_cuda.cu │ │ │ │ ├── fast_lsh_cumulation_cuda.h │ │ │ │ └── fast_lsh_cumulation_torch.cpp │ │ │ ├── loss │ │ │ ├── __init__.py │ │ │ ├── loss_deformable_detr.py │ │ │ ├── loss_for_object_detection.py │ │ │ ├── loss_grounding_dino.py │ │ │ ├── loss_rt_detr.py │ │ │ └── loss_utils.py │ │ │ ├── modelcard.py │ │ │ ├── modeling_attn_mask_utils.py │ │ │ ├── modeling_flash_attention_utils.py │ │ │ ├── modeling_flax_outputs.py │ │ │ ├── modeling_flax_pytorch_utils.py │ │ │ ├── modeling_flax_utils.py │ │ │ ├── modeling_gguf_pytorch_utils.py │ │ │ ├── modeling_outputs.py │ │ │ ├── modeling_rope_utils.py │ │ │ ├── modeling_tf_outputs.py │ │ │ ├── modeling_tf_pytorch_utils.py │ │ │ ├── modeling_tf_utils.py │ │ │ ├── modeling_utils.py │ │ │ ├── models │ │ │ ├── __init__.py │ │ │ ├── albert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_albert.py │ │ │ │ ├── convert_albert_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_albert.py │ │ │ │ ├── modeling_flax_albert.py │ │ │ │ ├── modeling_tf_albert.py │ │ │ │ ├── tokenization_albert.py │ │ │ │ └── tokenization_albert_fast.py │ │ │ ├── align │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_align.py │ │ │ │ ├── convert_align_tf_to_hf.py │ │ │ │ ├── modeling_align.py │ │ │ │ └── processing_align.py │ │ │ ├── altclip │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_altclip.py │ │ │ │ ├── modeling_altclip.py │ │ │ │ └── processing_altclip.py │ │ │ ├── aria │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_aria.py │ │ │ │ ├── convert_aria_weights_to_hf.py │ │ │ │ ├── image_processing_aria.py │ │ │ │ ├── modeling_aria.py │ │ │ │ ├── modular_aria.py │ │ │ │ └── processing_aria.py │ │ │ ├── audio_spectrogram_transformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_audio_spectrogram_transformer.py │ │ │ │ ├── convert_audio_spectrogram_transformer_original_to_pytorch.py │ │ │ │ ├── feature_extraction_audio_spectrogram_transformer.py │ │ │ │ └── modeling_audio_spectrogram_transformer.py │ │ │ ├── auto │ │ │ │ ├── __init__.py │ │ │ │ ├── auto_factory.py │ │ │ │ ├── configuration_auto.py │ │ │ │ ├── feature_extraction_auto.py │ │ │ │ ├── image_processing_auto.py │ │ │ │ ├── modeling_auto.py │ │ │ │ ├── modeling_flax_auto.py │ │ │ │ ├── modeling_tf_auto.py │ │ │ │ ├── processing_auto.py │ │ │ │ └── tokenization_auto.py │ │ │ ├── autoformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_autoformer.py │ │ │ │ └── modeling_autoformer.py │ │ │ ├── aya_vision │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_aya_vision.py │ │ │ │ ├── modeling_aya_vision.py │ │ │ │ └── processing_aya_vision.py │ │ │ ├── bamba │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_bamba.py │ │ │ │ ├── convert_mamba_ssm_checkpoint.py │ │ │ │ ├── modeling_bamba.py │ │ │ │ └── modular_bamba.py │ │ │ ├── bark │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_bark.py │ │ │ │ ├── convert_suno_to_hf.py │ │ │ │ ├── generation_configuration_bark.py │ │ │ │ ├── modeling_bark.py │ │ │ │ └── processing_bark.py │ │ │ ├── bart │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_bart.py │ │ │ │ ├── convert_bart_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_bart.py │ │ │ │ ├── modeling_flax_bart.py │ │ │ │ ├── modeling_tf_bart.py │ │ │ │ ├── tokenization_bart.py │ │ │ │ └── tokenization_bart_fast.py │ │ │ ├── barthez │ │ │ │ ├── __init__.py │ │ │ │ ├── tokenization_barthez.py │ │ │ │ └── tokenization_barthez_fast.py │ │ │ ├── bartpho │ │ │ │ ├── __init__.py │ │ │ │ └── tokenization_bartpho.py │ │ │ ├── beit │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_beit.py │ │ │ │ ├── convert_beit_unilm_to_pytorch.py │ │ │ │ ├── feature_extraction_beit.py │ │ │ │ ├── image_processing_beit.py │ │ │ │ ├── modeling_beit.py │ │ │ │ └── modeling_flax_beit.py │ │ │ ├── bert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_bert.py │ │ │ │ ├── convert_bert_original_tf2_checkpoint_to_pytorch.py │ │ │ │ ├── convert_bert_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── convert_bert_pytorch_checkpoint_to_original_tf.py │ │ │ │ ├── convert_bert_token_dropping_original_tf2_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_bert.py │ │ │ │ ├── modeling_flax_bert.py │ │ │ │ ├── modeling_tf_bert.py │ │ │ │ ├── tokenization_bert.py │ │ │ │ ├── tokenization_bert_fast.py │ │ │ │ └── tokenization_bert_tf.py │ │ │ ├── bert_generation │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_bert_generation.py │ │ │ │ ├── modeling_bert_generation.py │ │ │ │ └── tokenization_bert_generation.py │ │ │ ├── bert_japanese │ │ │ │ ├── __init__.py │ │ │ │ └── tokenization_bert_japanese.py │ │ │ ├── bertweet │ │ │ │ ├── __init__.py │ │ │ │ └── tokenization_bertweet.py │ │ │ ├── big_bird │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_big_bird.py │ │ │ │ ├── convert_bigbird_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_big_bird.py │ │ │ │ ├── modeling_flax_big_bird.py │ │ │ │ ├── tokenization_big_bird.py │ │ │ │ └── tokenization_big_bird_fast.py │ │ │ ├── bigbird_pegasus │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_bigbird_pegasus.py │ │ │ │ ├── convert_bigbird_pegasus_tf_to_pytorch.py │ │ │ │ └── modeling_bigbird_pegasus.py │ │ │ ├── biogpt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_biogpt.py │ │ │ │ ├── convert_biogpt_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_biogpt.py │ │ │ │ └── tokenization_biogpt.py │ │ │ ├── bit │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_bit.py │ │ │ │ ├── convert_bit_to_pytorch.py │ │ │ │ ├── image_processing_bit.py │ │ │ │ └── modeling_bit.py │ │ │ ├── blenderbot │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_blenderbot.py │ │ │ │ ├── convert_blenderbot_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_blenderbot.py │ │ │ │ ├── modeling_flax_blenderbot.py │ │ │ │ ├── modeling_tf_blenderbot.py │ │ │ │ ├── tokenization_blenderbot.py │ │ │ │ └── tokenization_blenderbot_fast.py │ │ │ ├── blenderbot_small │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_blenderbot_small.py │ │ │ │ ├── modeling_blenderbot_small.py │ │ │ │ ├── modeling_flax_blenderbot_small.py │ │ │ │ ├── modeling_tf_blenderbot_small.py │ │ │ │ ├── tokenization_blenderbot_small.py │ │ │ │ └── tokenization_blenderbot_small_fast.py │ │ │ ├── blip │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_blip.py │ │ │ │ ├── convert_blip_original_pytorch_to_hf.py │ │ │ │ ├── image_processing_blip.py │ │ │ │ ├── image_processing_blip_fast.py │ │ │ │ ├── modeling_blip.py │ │ │ │ ├── modeling_blip_text.py │ │ │ │ ├── modeling_tf_blip.py │ │ │ │ ├── modeling_tf_blip_text.py │ │ │ │ └── processing_blip.py │ │ │ ├── blip_2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_blip_2.py │ │ │ │ ├── convert_blip_2_original_to_pytorch.py │ │ │ │ ├── modeling_blip_2.py │ │ │ │ └── processing_blip_2.py │ │ │ ├── bloom │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_bloom.py │ │ │ │ ├── convert_bloom_original_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_bloom.py │ │ │ │ ├── modeling_flax_bloom.py │ │ │ │ └── tokenization_bloom_fast.py │ │ │ ├── bridgetower │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_bridgetower.py │ │ │ │ ├── image_processing_bridgetower.py │ │ │ │ ├── modeling_bridgetower.py │ │ │ │ └── processing_bridgetower.py │ │ │ ├── bros │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_bros.py │ │ │ │ ├── convert_bros_to_pytorch.py │ │ │ │ ├── modeling_bros.py │ │ │ │ └── processing_bros.py │ │ │ ├── byt5 │ │ │ │ ├── __init__.py │ │ │ │ ├── convert_byt5_original_tf_checkpoint_to_pytorch.py │ │ │ │ └── tokenization_byt5.py │ │ │ ├── camembert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_camembert.py │ │ │ │ ├── modeling_camembert.py │ │ │ │ ├── modeling_tf_camembert.py │ │ │ │ ├── tokenization_camembert.py │ │ │ │ └── tokenization_camembert_fast.py │ │ │ ├── canine │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_canine.py │ │ │ │ ├── convert_canine_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_canine.py │ │ │ │ └── tokenization_canine.py │ │ │ ├── chameleon │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_chameleon.py │ │ │ │ ├── convert_chameleon_weights_to_hf.py │ │ │ │ ├── image_processing_chameleon.py │ │ │ │ ├── modeling_chameleon.py │ │ │ │ └── processing_chameleon.py │ │ │ ├── chinese_clip │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_chinese_clip.py │ │ │ │ ├── convert_chinese_clip_original_pytorch_to_hf.py │ │ │ │ ├── feature_extraction_chinese_clip.py │ │ │ │ ├── image_processing_chinese_clip.py │ │ │ │ ├── modeling_chinese_clip.py │ │ │ │ └── processing_chinese_clip.py │ │ │ ├── clap │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_clap.py │ │ │ │ ├── convert_clap_original_pytorch_to_hf.py │ │ │ │ ├── feature_extraction_clap.py │ │ │ │ ├── modeling_clap.py │ │ │ │ └── processing_clap.py │ │ │ ├── clip │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_clip.py │ │ │ │ ├── convert_clip_original_pytorch_to_hf.py │ │ │ │ ├── feature_extraction_clip.py │ │ │ │ ├── image_processing_clip.py │ │ │ │ ├── image_processing_clip_fast.py │ │ │ │ ├── modeling_clip.py │ │ │ │ ├── modeling_flax_clip.py │ │ │ │ ├── modeling_tf_clip.py │ │ │ │ ├── processing_clip.py │ │ │ │ ├── tokenization_clip.py │ │ │ │ └── tokenization_clip_fast.py │ │ │ ├── clipseg │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_clipseg.py │ │ │ │ ├── convert_clipseg_original_pytorch_to_hf.py │ │ │ │ ├── modeling_clipseg.py │ │ │ │ └── processing_clipseg.py │ │ │ ├── clvp │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_clvp.py │ │ │ │ ├── convert_clvp_to_hf.py │ │ │ │ ├── feature_extraction_clvp.py │ │ │ │ ├── modeling_clvp.py │ │ │ │ ├── number_normalizer.py │ │ │ │ ├── processing_clvp.py │ │ │ │ └── tokenization_clvp.py │ │ │ ├── code_llama │ │ │ │ ├── __init__.py │ │ │ │ ├── tokenization_code_llama.py │ │ │ │ └── tokenization_code_llama_fast.py │ │ │ ├── codegen │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_codegen.py │ │ │ │ ├── modeling_codegen.py │ │ │ │ ├── tokenization_codegen.py │ │ │ │ └── tokenization_codegen_fast.py │ │ │ ├── cohere │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_cohere.py │ │ │ │ ├── modeling_cohere.py │ │ │ │ ├── modular_cohere.py │ │ │ │ └── tokenization_cohere_fast.py │ │ │ ├── cohere2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_cohere2.py │ │ │ │ ├── modeling_cohere2.py │ │ │ │ └── modular_cohere2.py │ │ │ ├── colpali │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_colpali.py │ │ │ │ ├── convert_colpali_weights_to_hf.py │ │ │ │ ├── modeling_colpali.py │ │ │ │ ├── modular_colpali.py │ │ │ │ └── processing_colpali.py │ │ │ ├── conditional_detr │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_conditional_detr.py │ │ │ │ ├── convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── feature_extraction_conditional_detr.py │ │ │ │ ├── image_processing_conditional_detr.py │ │ │ │ └── modeling_conditional_detr.py │ │ │ ├── convbert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_convbert.py │ │ │ │ ├── convert_convbert_original_tf1_checkpoint_to_pytorch_and_tf2.py │ │ │ │ ├── modeling_convbert.py │ │ │ │ ├── modeling_tf_convbert.py │ │ │ │ ├── tokenization_convbert.py │ │ │ │ └── tokenization_convbert_fast.py │ │ │ ├── convnext │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_convnext.py │ │ │ │ ├── convert_convnext_to_pytorch.py │ │ │ │ ├── feature_extraction_convnext.py │ │ │ │ ├── image_processing_convnext.py │ │ │ │ ├── image_processing_convnext_fast.py │ │ │ │ ├── modeling_convnext.py │ │ │ │ └── modeling_tf_convnext.py │ │ │ ├── convnextv2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_convnextv2.py │ │ │ │ ├── convert_convnextv2_to_pytorch.py │ │ │ │ ├── modeling_convnextv2.py │ │ │ │ └── modeling_tf_convnextv2.py │ │ │ ├── cpm │ │ │ │ ├── __init__.py │ │ │ │ ├── tokenization_cpm.py │ │ │ │ └── tokenization_cpm_fast.py │ │ │ ├── cpmant │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_cpmant.py │ │ │ │ ├── modeling_cpmant.py │ │ │ │ └── tokenization_cpmant.py │ │ │ ├── ctrl │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_ctrl.py │ │ │ │ ├── modeling_ctrl.py │ │ │ │ ├── modeling_tf_ctrl.py │ │ │ │ └── tokenization_ctrl.py │ │ │ ├── cvt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_cvt.py │ │ │ │ ├── convert_cvt_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_cvt.py │ │ │ │ └── modeling_tf_cvt.py │ │ │ ├── dab_detr │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_dab_detr.py │ │ │ │ ├── convert_dab_detr_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── modeling_dab_detr.py │ │ │ ├── dac │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_dac.py │ │ │ │ ├── convert_dac_checkpoint.py │ │ │ │ ├── feature_extraction_dac.py │ │ │ │ └── modeling_dac.py │ │ │ ├── data2vec │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_data2vec_audio.py │ │ │ │ ├── configuration_data2vec_text.py │ │ │ │ ├── configuration_data2vec_vision.py │ │ │ │ ├── convert_data2vec_audio_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── convert_data2vec_text_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_data2vec_audio.py │ │ │ │ ├── modeling_data2vec_text.py │ │ │ │ ├── modeling_data2vec_vision.py │ │ │ │ └── modeling_tf_data2vec_vision.py │ │ │ ├── dbrx │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_dbrx.py │ │ │ │ └── modeling_dbrx.py │ │ │ ├── deberta │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_deberta.py │ │ │ │ ├── modeling_deberta.py │ │ │ │ ├── modeling_tf_deberta.py │ │ │ │ ├── tokenization_deberta.py │ │ │ │ └── tokenization_deberta_fast.py │ │ │ ├── deberta_v2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_deberta_v2.py │ │ │ │ ├── modeling_deberta_v2.py │ │ │ │ ├── modeling_tf_deberta_v2.py │ │ │ │ ├── tokenization_deberta_v2.py │ │ │ │ └── tokenization_deberta_v2_fast.py │ │ │ ├── decision_transformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_decision_transformer.py │ │ │ │ └── modeling_decision_transformer.py │ │ │ ├── deformable_detr │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_deformable_detr.py │ │ │ │ ├── convert_deformable_detr_to_pytorch.py │ │ │ │ ├── feature_extraction_deformable_detr.py │ │ │ │ ├── image_processing_deformable_detr.py │ │ │ │ ├── image_processing_deformable_detr_fast.py │ │ │ │ ├── load_custom.py │ │ │ │ ├── modeling_deformable_detr.py │ │ │ │ └── modular_deformable_detr.py │ │ │ ├── deit │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_deit.py │ │ │ │ ├── convert_deit_timm_to_pytorch.py │ │ │ │ ├── feature_extraction_deit.py │ │ │ │ ├── image_processing_deit.py │ │ │ │ ├── image_processing_deit_fast.py │ │ │ │ ├── modeling_deit.py │ │ │ │ └── modeling_tf_deit.py │ │ │ ├── deprecated │ │ │ │ ├── __init__.py │ │ │ │ ├── bort │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── convert_bort_original_gluonnlp_checkpoint_to_pytorch.py │ │ │ │ ├── deta │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_deta.py │ │ │ │ │ ├── convert_deta_resnet_to_pytorch.py │ │ │ │ │ ├── convert_deta_swin_to_pytorch.py │ │ │ │ │ ├── image_processing_deta.py │ │ │ │ │ └── modeling_deta.py │ │ │ │ ├── efficientformer │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_efficientformer.py │ │ │ │ │ ├── convert_efficientformer_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ │ ├── image_processing_efficientformer.py │ │ │ │ │ ├── modeling_efficientformer.py │ │ │ │ │ └── modeling_tf_efficientformer.py │ │ │ │ ├── ernie_m │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_ernie_m.py │ │ │ │ │ ├── modeling_ernie_m.py │ │ │ │ │ └── tokenization_ernie_m.py │ │ │ │ ├── gptsan_japanese │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_gptsan_japanese.py │ │ │ │ │ ├── convert_gptsan_tf_checkpoint_to_pytorch.py │ │ │ │ │ ├── modeling_gptsan_japanese.py │ │ │ │ │ └── tokenization_gptsan_japanese.py │ │ │ │ ├── graphormer │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── algos_graphormer.pyx │ │ │ │ │ ├── collating_graphormer.py │ │ │ │ │ ├── configuration_graphormer.py │ │ │ │ │ └── modeling_graphormer.py │ │ │ │ ├── jukebox │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_jukebox.py │ │ │ │ │ ├── convert_jukebox.py │ │ │ │ │ ├── modeling_jukebox.py │ │ │ │ │ └── tokenization_jukebox.py │ │ │ │ ├── mctct │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_mctct.py │ │ │ │ │ ├── feature_extraction_mctct.py │ │ │ │ │ ├── modeling_mctct.py │ │ │ │ │ └── processing_mctct.py │ │ │ │ ├── mega │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_mega.py │ │ │ │ │ ├── convert_mega_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ │ └── modeling_mega.py │ │ │ │ ├── mmbt │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_mmbt.py │ │ │ │ │ └── modeling_mmbt.py │ │ │ │ ├── nat │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_nat.py │ │ │ │ │ └── modeling_nat.py │ │ │ │ ├── nezha │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_nezha.py │ │ │ │ │ └── modeling_nezha.py │ │ │ │ ├── open_llama │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_open_llama.py │ │ │ │ │ └── modeling_open_llama.py │ │ │ │ ├── qdqbert │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_qdqbert.py │ │ │ │ │ └── modeling_qdqbert.py │ │ │ │ ├── realm │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_realm.py │ │ │ │ │ ├── modeling_realm.py │ │ │ │ │ ├── retrieval_realm.py │ │ │ │ │ ├── tokenization_realm.py │ │ │ │ │ └── tokenization_realm_fast.py │ │ │ │ ├── retribert │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_retribert.py │ │ │ │ │ ├── modeling_retribert.py │ │ │ │ │ ├── tokenization_retribert.py │ │ │ │ │ └── tokenization_retribert_fast.py │ │ │ │ ├── speech_to_text_2 │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_speech_to_text_2.py │ │ │ │ │ ├── modeling_speech_to_text_2.py │ │ │ │ │ ├── processing_speech_to_text_2.py │ │ │ │ │ └── tokenization_speech_to_text_2.py │ │ │ │ ├── tapex │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── tokenization_tapex.py │ │ │ │ ├── trajectory_transformer │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_trajectory_transformer.py │ │ │ │ │ ├── convert_trajectory_transformer_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ │ └── modeling_trajectory_transformer.py │ │ │ │ ├── transfo_xl │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_transfo_xl.py │ │ │ │ │ ├── convert_transfo_xl_original_tf_checkpoint_to_pytorch.py │ │ │ │ │ ├── modeling_tf_transfo_xl.py │ │ │ │ │ ├── modeling_tf_transfo_xl_utilities.py │ │ │ │ │ ├── modeling_transfo_xl.py │ │ │ │ │ ├── modeling_transfo_xl_utilities.py │ │ │ │ │ └── tokenization_transfo_xl.py │ │ │ │ ├── tvlt │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_tvlt.py │ │ │ │ │ ├── feature_extraction_tvlt.py │ │ │ │ │ ├── image_processing_tvlt.py │ │ │ │ │ ├── modeling_tvlt.py │ │ │ │ │ └── processing_tvlt.py │ │ │ │ ├── van │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_van.py │ │ │ │ │ ├── convert_van_to_pytorch.py │ │ │ │ │ └── modeling_van.py │ │ │ │ ├── vit_hybrid │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_vit_hybrid.py │ │ │ │ │ ├── convert_vit_hybrid_timm_to_pytorch.py │ │ │ │ │ ├── image_processing_vit_hybrid.py │ │ │ │ │ └── modeling_vit_hybrid.py │ │ │ │ └── xlm_prophetnet │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── configuration_xlm_prophetnet.py │ │ │ │ │ ├── modeling_xlm_prophetnet.py │ │ │ │ │ └── tokenization_xlm_prophetnet.py │ │ │ ├── depth_anything │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_depth_anything.py │ │ │ │ ├── convert_depth_anything_to_hf.py │ │ │ │ └── modeling_depth_anything.py │ │ │ ├── depth_pro │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_depth_pro.py │ │ │ │ ├── convert_depth_pro_weights_to_hf.py │ │ │ │ ├── image_processing_depth_pro.py │ │ │ │ ├── image_processing_depth_pro_fast.py │ │ │ │ └── modeling_depth_pro.py │ │ │ ├── detr │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_detr.py │ │ │ │ ├── convert_detr_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── convert_detr_to_pytorch.py │ │ │ │ ├── feature_extraction_detr.py │ │ │ │ ├── image_processing_detr.py │ │ │ │ ├── image_processing_detr_fast.py │ │ │ │ └── modeling_detr.py │ │ │ ├── dialogpt │ │ │ │ ├── __init__.py │ │ │ │ └── convert_dialogpt_original_pytorch_checkpoint_to_pytorch.py │ │ │ ├── diffllama │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_diffllama.py │ │ │ │ ├── modeling_diffllama.py │ │ │ │ └── modular_diffllama.py │ │ │ ├── dinat │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_dinat.py │ │ │ │ └── modeling_dinat.py │ │ │ ├── dinov2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_dinov2.py │ │ │ │ ├── convert_dinov2_to_hf.py │ │ │ │ ├── modeling_dinov2.py │ │ │ │ └── modeling_flax_dinov2.py │ │ │ ├── dinov2_with_registers │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_dinov2_with_registers.py │ │ │ │ ├── convert_dinov2_with_registers_to_hf.py │ │ │ │ ├── modeling_dinov2_with_registers.py │ │ │ │ └── modular_dinov2_with_registers.py │ │ │ ├── distilbert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_distilbert.py │ │ │ │ ├── modeling_distilbert.py │ │ │ │ ├── modeling_flax_distilbert.py │ │ │ │ ├── modeling_tf_distilbert.py │ │ │ │ ├── tokenization_distilbert.py │ │ │ │ └── tokenization_distilbert_fast.py │ │ │ ├── dit │ │ │ │ ├── __init__.py │ │ │ │ └── convert_dit_unilm_to_pytorch.py │ │ │ ├── donut │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_donut_swin.py │ │ │ │ ├── convert_donut_to_pytorch.py │ │ │ │ ├── feature_extraction_donut.py │ │ │ │ ├── image_processing_donut.py │ │ │ │ ├── modeling_donut_swin.py │ │ │ │ └── processing_donut.py │ │ │ ├── dpr │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_dpr.py │ │ │ │ ├── convert_dpr_original_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_dpr.py │ │ │ │ ├── modeling_tf_dpr.py │ │ │ │ ├── tokenization_dpr.py │ │ │ │ └── tokenization_dpr_fast.py │ │ │ ├── dpt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_dpt.py │ │ │ │ ├── convert_dinov2_depth_to_hf.py │ │ │ │ ├── convert_dpt_beit_to_hf.py │ │ │ │ ├── convert_dpt_hybrid_to_pytorch.py │ │ │ │ ├── convert_dpt_swinv2_to_hf.py │ │ │ │ ├── convert_dpt_to_pytorch.py │ │ │ │ ├── feature_extraction_dpt.py │ │ │ │ ├── image_processing_dpt.py │ │ │ │ └── modeling_dpt.py │ │ │ ├── efficientnet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_efficientnet.py │ │ │ │ ├── convert_efficientnet_to_pytorch.py │ │ │ │ ├── image_processing_efficientnet.py │ │ │ │ └── modeling_efficientnet.py │ │ │ ├── electra │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_electra.py │ │ │ │ ├── convert_electra_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_electra.py │ │ │ │ ├── modeling_flax_electra.py │ │ │ │ ├── modeling_tf_electra.py │ │ │ │ ├── tokenization_electra.py │ │ │ │ └── tokenization_electra_fast.py │ │ │ ├── emu3 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_emu3.py │ │ │ │ ├── convert_emu3_weights_to_hf.py │ │ │ │ ├── image_processing_emu3.py │ │ │ │ ├── modeling_emu3.py │ │ │ │ ├── modular_emu3.py │ │ │ │ └── processing_emu3.py │ │ │ ├── encodec │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_encodec.py │ │ │ │ ├── convert_encodec_checkpoint_to_pytorch.py │ │ │ │ ├── feature_extraction_encodec.py │ │ │ │ └── modeling_encodec.py │ │ │ ├── encoder_decoder │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_encoder_decoder.py │ │ │ │ ├── modeling_encoder_decoder.py │ │ │ │ ├── modeling_flax_encoder_decoder.py │ │ │ │ └── modeling_tf_encoder_decoder.py │ │ │ ├── ernie │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_ernie.py │ │ │ │ └── modeling_ernie.py │ │ │ ├── esm │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_esm.py │ │ │ │ ├── convert_esm.py │ │ │ │ ├── modeling_esm.py │ │ │ │ ├── modeling_esmfold.py │ │ │ │ ├── modeling_tf_esm.py │ │ │ │ ├── openfold_utils │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── chunk_utils.py │ │ │ │ │ ├── data_transforms.py │ │ │ │ │ ├── feats.py │ │ │ │ │ ├── loss.py │ │ │ │ │ ├── protein.py │ │ │ │ │ ├── residue_constants.py │ │ │ │ │ ├── rigid_utils.py │ │ │ │ │ └── tensor_utils.py │ │ │ │ └── tokenization_esm.py │ │ │ ├── falcon │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_falcon.py │ │ │ │ ├── convert_custom_code_checkpoint.py │ │ │ │ └── modeling_falcon.py │ │ │ ├── falcon_mamba │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_falcon_mamba.py │ │ │ │ └── modeling_falcon_mamba.py │ │ │ ├── fastspeech2_conformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_fastspeech2_conformer.py │ │ │ │ ├── convert_fastspeech2_conformer_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── convert_hifigan.py │ │ │ │ ├── convert_model_with_hifigan.py │ │ │ │ ├── modeling_fastspeech2_conformer.py │ │ │ │ └── tokenization_fastspeech2_conformer.py │ │ │ ├── flaubert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_flaubert.py │ │ │ │ ├── modeling_flaubert.py │ │ │ │ ├── modeling_tf_flaubert.py │ │ │ │ └── tokenization_flaubert.py │ │ │ ├── flava │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_flava.py │ │ │ │ ├── convert_dalle_to_flava_codebook.py │ │ │ │ ├── convert_flava_original_pytorch_to_hf.py │ │ │ │ ├── feature_extraction_flava.py │ │ │ │ ├── image_processing_flava.py │ │ │ │ ├── modeling_flava.py │ │ │ │ └── processing_flava.py │ │ │ ├── fnet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_fnet.py │ │ │ │ ├── convert_fnet_original_flax_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_fnet.py │ │ │ │ ├── tokenization_fnet.py │ │ │ │ └── tokenization_fnet_fast.py │ │ │ ├── focalnet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_focalnet.py │ │ │ │ ├── convert_focalnet_to_hf_format.py │ │ │ │ └── modeling_focalnet.py │ │ │ ├── fsmt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_fsmt.py │ │ │ │ ├── convert_fsmt_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_fsmt.py │ │ │ │ └── tokenization_fsmt.py │ │ │ ├── funnel │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_funnel.py │ │ │ │ ├── convert_funnel_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_funnel.py │ │ │ │ ├── modeling_tf_funnel.py │ │ │ │ ├── tokenization_funnel.py │ │ │ │ └── tokenization_funnel_fast.py │ │ │ ├── fuyu │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_fuyu.py │ │ │ │ ├── convert_fuyu_model_weights_to_hf.py │ │ │ │ ├── image_processing_fuyu.py │ │ │ │ ├── modeling_fuyu.py │ │ │ │ └── processing_fuyu.py │ │ │ ├── gemma │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_gemma.py │ │ │ │ ├── convert_gemma_weights_to_hf.py │ │ │ │ ├── modeling_flax_gemma.py │ │ │ │ ├── modeling_gemma.py │ │ │ │ ├── modular_gemma.py │ │ │ │ ├── tokenization_gemma.py │ │ │ │ └── tokenization_gemma_fast.py │ │ │ ├── gemma2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_gemma2.py │ │ │ │ ├── convert_gemma2_weights_to_hf.py │ │ │ │ ├── modeling_gemma2.py │ │ │ │ └── modular_gemma2.py │ │ │ ├── gemma3 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_gemma3.py │ │ │ │ ├── convert_gemma3_weights_orbax_to_hf.py │ │ │ │ ├── image_processing_gemma3.py │ │ │ │ ├── image_processing_gemma3_fast.py │ │ │ │ ├── modeling_gemma3.py │ │ │ │ ├── modular_gemma3.py │ │ │ │ └── processing_gemma3.py │ │ │ ├── git │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_git.py │ │ │ │ ├── convert_git_to_pytorch.py │ │ │ │ ├── modeling_git.py │ │ │ │ └── processing_git.py │ │ │ ├── glm │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_glm.py │ │ │ │ ├── convert_glm_weights_to_hf.py │ │ │ │ ├── modeling_glm.py │ │ │ │ └── modular_glm.py │ │ │ ├── glpn │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_glpn.py │ │ │ │ ├── convert_glpn_to_pytorch.py │ │ │ │ ├── feature_extraction_glpn.py │ │ │ │ ├── image_processing_glpn.py │ │ │ │ └── modeling_glpn.py │ │ │ ├── got_ocr2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_got_ocr2.py │ │ │ │ ├── convert_got_ocr2_weights_to_hf.py │ │ │ │ ├── image_processing_got_ocr2.py │ │ │ │ ├── image_processing_got_ocr2_fast.py │ │ │ │ ├── modeling_got_ocr2.py │ │ │ │ ├── modular_got_ocr2.py │ │ │ │ └── processing_got_ocr2.py │ │ │ ├── gpt2 │ │ │ │ ├── CONVERSION.md │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_gpt2.py │ │ │ │ ├── convert_gpt2_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_flax_gpt2.py │ │ │ │ ├── modeling_gpt2.py │ │ │ │ ├── modeling_tf_gpt2.py │ │ │ │ ├── tokenization_gpt2.py │ │ │ │ ├── tokenization_gpt2_fast.py │ │ │ │ └── tokenization_gpt2_tf.py │ │ │ ├── gpt_bigcode │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_gpt_bigcode.py │ │ │ │ └── modeling_gpt_bigcode.py │ │ │ ├── gpt_neo │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_gpt_neo.py │ │ │ │ ├── convert_gpt_neo_mesh_tf_to_pytorch.py │ │ │ │ ├── modeling_flax_gpt_neo.py │ │ │ │ └── modeling_gpt_neo.py │ │ │ ├── gpt_neox │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_gpt_neox.py │ │ │ │ ├── modeling_gpt_neox.py │ │ │ │ ├── modular_gpt_neox.py │ │ │ │ └── tokenization_gpt_neox_fast.py │ │ │ ├── gpt_neox_japanese │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_gpt_neox_japanese.py │ │ │ │ ├── modeling_gpt_neox_japanese.py │ │ │ │ └── tokenization_gpt_neox_japanese.py │ │ │ ├── gpt_sw3 │ │ │ │ ├── __init__.py │ │ │ │ ├── convert_megatron_to_pytorch.py │ │ │ │ └── tokenization_gpt_sw3.py │ │ │ ├── gptj │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_gptj.py │ │ │ │ ├── modeling_flax_gptj.py │ │ │ │ ├── modeling_gptj.py │ │ │ │ └── modeling_tf_gptj.py │ │ │ ├── granite │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_granite.py │ │ │ │ ├── modeling_granite.py │ │ │ │ └── modular_granite.py │ │ │ ├── granitemoe │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_granitemoe.py │ │ │ │ └── modeling_granitemoe.py │ │ │ ├── granitemoeshared │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_granitemoeshared.py │ │ │ │ ├── modeling_granitemoeshared.py │ │ │ │ └── modular_granitemoeshared.py │ │ │ ├── grounding_dino │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_grounding_dino.py │ │ │ │ ├── convert_grounding_dino_to_hf.py │ │ │ │ ├── image_processing_grounding_dino.py │ │ │ │ ├── modeling_grounding_dino.py │ │ │ │ └── processing_grounding_dino.py │ │ │ ├── groupvit │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_groupvit.py │ │ │ │ ├── convert_groupvit_nvlab_to_hf.py │ │ │ │ ├── modeling_groupvit.py │ │ │ │ └── modeling_tf_groupvit.py │ │ │ ├── helium │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_helium.py │ │ │ │ ├── modeling_helium.py │ │ │ │ └── modular_helium.py │ │ │ ├── herbert │ │ │ │ ├── __init__.py │ │ │ │ ├── tokenization_herbert.py │ │ │ │ └── tokenization_herbert_fast.py │ │ │ ├── hiera │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_hiera.py │ │ │ │ ├── convert_hiera_to_hf.py │ │ │ │ └── modeling_hiera.py │ │ │ ├── hubert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_hubert.py │ │ │ │ ├── convert_distilhubert_original_s3prl_checkpoint_to_pytorch.py │ │ │ │ ├── convert_hubert_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── convert_hubert_original_s3prl_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_hubert.py │ │ │ │ └── modeling_tf_hubert.py │ │ │ ├── ibert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_ibert.py │ │ │ │ ├── modeling_ibert.py │ │ │ │ └── quant_modules.py │ │ │ ├── idefics │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_idefics.py │ │ │ │ ├── image_processing_idefics.py │ │ │ │ ├── modeling_idefics.py │ │ │ │ ├── modeling_tf_idefics.py │ │ │ │ ├── perceiver.py │ │ │ │ ├── perceiver_tf.py │ │ │ │ ├── processing_idefics.py │ │ │ │ ├── vision.py │ │ │ │ └── vision_tf.py │ │ │ ├── idefics2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_idefics2.py │ │ │ │ ├── convert_idefics2_weights_to_hf.py │ │ │ │ ├── image_processing_idefics2.py │ │ │ │ ├── modeling_idefics2.py │ │ │ │ └── processing_idefics2.py │ │ │ ├── idefics3 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_idefics3.py │ │ │ │ ├── convert_idefics3_weights_to_hf.py │ │ │ │ ├── image_processing_idefics3.py │ │ │ │ ├── modeling_idefics3.py │ │ │ │ └── processing_idefics3.py │ │ │ ├── ijepa │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_ijepa.py │ │ │ │ ├── convert_ijepa_to_hf.py │ │ │ │ ├── modeling_ijepa.py │ │ │ │ └── modular_ijepa.py │ │ │ ├── imagegpt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_imagegpt.py │ │ │ │ ├── convert_imagegpt_original_tf2_to_pytorch.py │ │ │ │ ├── feature_extraction_imagegpt.py │ │ │ │ ├── image_processing_imagegpt.py │ │ │ │ └── modeling_imagegpt.py │ │ │ ├── informer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_informer.py │ │ │ │ └── modeling_informer.py │ │ │ ├── instructblip │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_instructblip.py │ │ │ │ ├── convert_instructblip_original_to_pytorch.py │ │ │ │ ├── modeling_instructblip.py │ │ │ │ └── processing_instructblip.py │ │ │ ├── instructblipvideo │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_instructblipvideo.py │ │ │ │ ├── convert_instructblipvideo_original_to_pytorch.py │ │ │ │ ├── image_processing_instructblipvideo.py │ │ │ │ ├── modeling_instructblipvideo.py │ │ │ │ ├── modular_instructblipvideo.py │ │ │ │ └── processing_instructblipvideo.py │ │ │ ├── jamba │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_jamba.py │ │ │ │ └── modeling_jamba.py │ │ │ ├── jetmoe │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_jetmoe.py │ │ │ │ └── modeling_jetmoe.py │ │ │ ├── kosmos2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_kosmos2.py │ │ │ │ ├── convert_kosmos2_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_kosmos2.py │ │ │ │ └── processing_kosmos2.py │ │ │ ├── layoutlm │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_layoutlm.py │ │ │ │ ├── modeling_layoutlm.py │ │ │ │ ├── modeling_tf_layoutlm.py │ │ │ │ ├── tokenization_layoutlm.py │ │ │ │ └── tokenization_layoutlm_fast.py │ │ │ ├── layoutlmv2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_layoutlmv2.py │ │ │ │ ├── feature_extraction_layoutlmv2.py │ │ │ │ ├── image_processing_layoutlmv2.py │ │ │ │ ├── modeling_layoutlmv2.py │ │ │ │ ├── processing_layoutlmv2.py │ │ │ │ ├── tokenization_layoutlmv2.py │ │ │ │ └── tokenization_layoutlmv2_fast.py │ │ │ ├── layoutlmv3 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_layoutlmv3.py │ │ │ │ ├── feature_extraction_layoutlmv3.py │ │ │ │ ├── image_processing_layoutlmv3.py │ │ │ │ ├── modeling_layoutlmv3.py │ │ │ │ ├── modeling_tf_layoutlmv3.py │ │ │ │ ├── processing_layoutlmv3.py │ │ │ │ ├── tokenization_layoutlmv3.py │ │ │ │ └── tokenization_layoutlmv3_fast.py │ │ │ ├── layoutxlm │ │ │ │ ├── __init__.py │ │ │ │ ├── processing_layoutxlm.py │ │ │ │ ├── tokenization_layoutxlm.py │ │ │ │ └── tokenization_layoutxlm_fast.py │ │ │ ├── led │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_led.py │ │ │ │ ├── modeling_led.py │ │ │ │ ├── modeling_tf_led.py │ │ │ │ ├── tokenization_led.py │ │ │ │ └── tokenization_led_fast.py │ │ │ ├── levit │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_levit.py │ │ │ │ ├── convert_levit_timm_to_pytorch.py │ │ │ │ ├── feature_extraction_levit.py │ │ │ │ ├── image_processing_levit.py │ │ │ │ └── modeling_levit.py │ │ │ ├── lilt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_lilt.py │ │ │ │ └── modeling_lilt.py │ │ │ ├── llama │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_llama.py │ │ │ │ ├── convert_llama_weights_to_hf.py │ │ │ │ ├── modeling_flax_llama.py │ │ │ │ ├── modeling_llama.py │ │ │ │ ├── tokenization_llama.py │ │ │ │ └── tokenization_llama_fast.py │ │ │ ├── llava │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_llava.py │ │ │ │ ├── convert_llava_weights_to_hf.py │ │ │ │ ├── image_processing_llava.py │ │ │ │ ├── image_processing_llava_fast.py │ │ │ │ ├── modeling_llava.py │ │ │ │ └── processing_llava.py │ │ │ ├── llava_next │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_llava_next.py │ │ │ │ ├── convert_llava_next_weights_to_hf.py │ │ │ │ ├── image_processing_llava_next.py │ │ │ │ ├── image_processing_llava_next_fast.py │ │ │ │ ├── modeling_llava_next.py │ │ │ │ └── processing_llava_next.py │ │ │ ├── llava_next_video │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_llava_next_video.py │ │ │ │ ├── convert_llava_next_video_weights_to_hf.py │ │ │ │ ├── image_processing_llava_next_video.py │ │ │ │ ├── modeling_llava_next_video.py │ │ │ │ ├── modular_llava_next_video.py │ │ │ │ └── processing_llava_next_video.py │ │ │ ├── llava_onevision │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_llava_onevision.py │ │ │ │ ├── convert_llava_onevision_weights_to_hf.py │ │ │ │ ├── image_processing_llava_onevision.py │ │ │ │ ├── image_processing_llava_onevision_fast.py │ │ │ │ ├── modeling_llava_onevision.py │ │ │ │ ├── modular_llava_onevision.py │ │ │ │ ├── processing_llava_onevision.py │ │ │ │ └── video_processing_llava_onevision.py │ │ │ ├── longformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_longformer.py │ │ │ │ ├── convert_longformer_original_pytorch_lightning_to_pytorch.py │ │ │ │ ├── modeling_longformer.py │ │ │ │ ├── modeling_tf_longformer.py │ │ │ │ ├── tokenization_longformer.py │ │ │ │ └── tokenization_longformer_fast.py │ │ │ ├── longt5 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_longt5.py │ │ │ │ ├── convert_longt5x_checkpoint_to_flax.py │ │ │ │ ├── modeling_flax_longt5.py │ │ │ │ └── modeling_longt5.py │ │ │ ├── luke │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_luke.py │ │ │ │ ├── convert_luke_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_luke.py │ │ │ │ └── tokenization_luke.py │ │ │ ├── lxmert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_lxmert.py │ │ │ │ ├── convert_lxmert_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_lxmert.py │ │ │ │ ├── modeling_tf_lxmert.py │ │ │ │ ├── tokenization_lxmert.py │ │ │ │ └── tokenization_lxmert_fast.py │ │ │ ├── m2m_100 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_m2m_100.py │ │ │ │ ├── convert_m2m100_original_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_m2m_100.py │ │ │ │ └── tokenization_m2m_100.py │ │ │ ├── mamba │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mamba.py │ │ │ │ ├── convert_mamba_ssm_checkpoint_to_pytorch.py │ │ │ │ └── modeling_mamba.py │ │ │ ├── mamba2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mamba2.py │ │ │ │ ├── convert_mamba2_ssm_checkpoint_to_pytorch.py │ │ │ │ └── modeling_mamba2.py │ │ │ ├── marian │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_marian.py │ │ │ │ ├── convert_marian_tatoeba_to_pytorch.py │ │ │ │ ├── convert_marian_to_pytorch.py │ │ │ │ ├── modeling_flax_marian.py │ │ │ │ ├── modeling_marian.py │ │ │ │ ├── modeling_tf_marian.py │ │ │ │ └── tokenization_marian.py │ │ │ ├── markuplm │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_markuplm.py │ │ │ │ ├── feature_extraction_markuplm.py │ │ │ │ ├── modeling_markuplm.py │ │ │ │ ├── processing_markuplm.py │ │ │ │ ├── tokenization_markuplm.py │ │ │ │ └── tokenization_markuplm_fast.py │ │ │ ├── mask2former │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mask2former.py │ │ │ │ ├── convert_mask2former_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── image_processing_mask2former.py │ │ │ │ └── modeling_mask2former.py │ │ │ ├── maskformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_maskformer.py │ │ │ │ ├── configuration_maskformer_swin.py │ │ │ │ ├── convert_maskformer_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── convert_maskformer_resnet_to_pytorch.py │ │ │ │ ├── convert_maskformer_swin_to_pytorch.py │ │ │ │ ├── feature_extraction_maskformer.py │ │ │ │ ├── image_processing_maskformer.py │ │ │ │ ├── modeling_maskformer.py │ │ │ │ └── modeling_maskformer_swin.py │ │ │ ├── mbart │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mbart.py │ │ │ │ ├── convert_mbart_original_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_flax_mbart.py │ │ │ │ ├── modeling_mbart.py │ │ │ │ ├── modeling_tf_mbart.py │ │ │ │ ├── tokenization_mbart.py │ │ │ │ └── tokenization_mbart_fast.py │ │ │ ├── mbart50 │ │ │ │ ├── __init__.py │ │ │ │ ├── tokenization_mbart50.py │ │ │ │ └── tokenization_mbart50_fast.py │ │ │ ├── megatron_bert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_megatron_bert.py │ │ │ │ ├── convert_megatron_bert_checkpoint.py │ │ │ │ └── modeling_megatron_bert.py │ │ │ ├── megatron_gpt2 │ │ │ │ ├── __init__.py │ │ │ │ ├── checkpoint_reshaping_and_interoperability.py │ │ │ │ └── convert_megatron_gpt2_checkpoint.py │ │ │ ├── mgp_str │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mgp_str.py │ │ │ │ ├── modeling_mgp_str.py │ │ │ │ ├── processing_mgp_str.py │ │ │ │ └── tokenization_mgp_str.py │ │ │ ├── mimi │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mimi.py │ │ │ │ ├── convert_mimi_checkpoint_to_pytorch.py │ │ │ │ └── modeling_mimi.py │ │ │ ├── mistral │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mistral.py │ │ │ │ ├── convert_mistral_weights_to_hf.py │ │ │ │ ├── modeling_flax_mistral.py │ │ │ │ ├── modeling_mistral.py │ │ │ │ ├── modeling_tf_mistral.py │ │ │ │ └── modular_mistral.py │ │ │ ├── mistral3 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mistral3.py │ │ │ │ ├── convert_mistral3_weights_to_hf.py │ │ │ │ ├── modeling_mistral3.py │ │ │ │ └── modular_mistral3.py │ │ │ ├── mixtral │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mixtral.py │ │ │ │ ├── convert_mixtral_weights_to_hf.py │ │ │ │ ├── modeling_mixtral.py │ │ │ │ └── modular_mixtral.py │ │ │ ├── mllama │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mllama.py │ │ │ │ ├── convert_mllama_weights_to_hf.py │ │ │ │ ├── image_processing_mllama.py │ │ │ │ ├── modeling_mllama.py │ │ │ │ └── processing_mllama.py │ │ │ ├── mluke │ │ │ │ ├── __init__.py │ │ │ │ ├── convert_mluke_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── tokenization_mluke.py │ │ │ ├── mobilebert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mobilebert.py │ │ │ │ ├── convert_mobilebert_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_mobilebert.py │ │ │ │ ├── modeling_tf_mobilebert.py │ │ │ │ ├── tokenization_mobilebert.py │ │ │ │ └── tokenization_mobilebert_fast.py │ │ │ ├── mobilenet_v1 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mobilenet_v1.py │ │ │ │ ├── convert_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── feature_extraction_mobilenet_v1.py │ │ │ │ ├── image_processing_mobilenet_v1.py │ │ │ │ └── modeling_mobilenet_v1.py │ │ │ ├── mobilenet_v2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mobilenet_v2.py │ │ │ │ ├── convert_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── feature_extraction_mobilenet_v2.py │ │ │ │ ├── image_processing_mobilenet_v2.py │ │ │ │ └── modeling_mobilenet_v2.py │ │ │ ├── mobilevit │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mobilevit.py │ │ │ │ ├── convert_mlcvnets_to_pytorch.py │ │ │ │ ├── feature_extraction_mobilevit.py │ │ │ │ ├── image_processing_mobilevit.py │ │ │ │ ├── modeling_mobilevit.py │ │ │ │ └── modeling_tf_mobilevit.py │ │ │ ├── mobilevitv2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mobilevitv2.py │ │ │ │ ├── convert_mlcvnets_to_pytorch.py │ │ │ │ └── modeling_mobilevitv2.py │ │ │ ├── modernbert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_modernbert.py │ │ │ │ ├── modeling_modernbert.py │ │ │ │ └── modular_modernbert.py │ │ │ ├── moonshine │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_moonshine.py │ │ │ │ ├── convert_usefulsensors_to_hf.py │ │ │ │ ├── modeling_moonshine.py │ │ │ │ └── modular_moonshine.py │ │ │ ├── moshi │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_moshi.py │ │ │ │ ├── convert_moshi_transformers.py │ │ │ │ └── modeling_moshi.py │ │ │ ├── mpnet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mpnet.py │ │ │ │ ├── modeling_mpnet.py │ │ │ │ ├── modeling_tf_mpnet.py │ │ │ │ ├── tokenization_mpnet.py │ │ │ │ └── tokenization_mpnet_fast.py │ │ │ ├── mpt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mpt.py │ │ │ │ └── modeling_mpt.py │ │ │ ├── mra │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mra.py │ │ │ │ ├── convert_mra_pytorch_to_pytorch.py │ │ │ │ └── modeling_mra.py │ │ │ ├── mt5 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mt5.py │ │ │ │ ├── modeling_flax_mt5.py │ │ │ │ ├── modeling_mt5.py │ │ │ │ ├── modeling_tf_mt5.py │ │ │ │ ├── tokenization_mt5.py │ │ │ │ └── tokenization_mt5_fast.py │ │ │ ├── musicgen │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_musicgen.py │ │ │ │ ├── convert_musicgen_transformers.py │ │ │ │ ├── modeling_musicgen.py │ │ │ │ └── processing_musicgen.py │ │ │ ├── musicgen_melody │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_musicgen_melody.py │ │ │ │ ├── convert_musicgen_melody_transformers.py │ │ │ │ ├── feature_extraction_musicgen_melody.py │ │ │ │ ├── modeling_musicgen_melody.py │ │ │ │ └── processing_musicgen_melody.py │ │ │ ├── mvp │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_mvp.py │ │ │ │ ├── modeling_mvp.py │ │ │ │ ├── tokenization_mvp.py │ │ │ │ └── tokenization_mvp_fast.py │ │ │ ├── myt5 │ │ │ │ ├── __init__.py │ │ │ │ ├── convert_myt5_original_tf_checkpoint_to_pytorch.py │ │ │ │ └── tokenization_myt5.py │ │ │ ├── nemotron │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_nemotron.py │ │ │ │ ├── convert_nemotron_nemo_to_hf.py │ │ │ │ └── modeling_nemotron.py │ │ │ ├── nllb │ │ │ │ ├── __init__.py │ │ │ │ ├── tokenization_nllb.py │ │ │ │ └── tokenization_nllb_fast.py │ │ │ ├── nllb_moe │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_nllb_moe.py │ │ │ │ ├── convert_nllb_moe_sharded_original_checkpoint_to_pytorch.py │ │ │ │ └── modeling_nllb_moe.py │ │ │ ├── nougat │ │ │ │ ├── __init__.py │ │ │ │ ├── convert_nougat_to_hf.py │ │ │ │ ├── image_processing_nougat.py │ │ │ │ ├── processing_nougat.py │ │ │ │ └── tokenization_nougat_fast.py │ │ │ ├── nystromformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_nystromformer.py │ │ │ │ ├── convert_nystromformer_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── modeling_nystromformer.py │ │ │ ├── olmo │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_olmo.py │ │ │ │ ├── convert_olmo_weights_to_hf.py │ │ │ │ ├── modeling_olmo.py │ │ │ │ └── modular_olmo.py │ │ │ ├── olmo2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_olmo2.py │ │ │ │ ├── convert_olmo2_weights_to_hf.py │ │ │ │ ├── modeling_olmo2.py │ │ │ │ └── modular_olmo2.py │ │ │ ├── olmoe │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_olmoe.py │ │ │ │ ├── convert_olmoe_weights_to_hf.py │ │ │ │ └── modeling_olmoe.py │ │ │ ├── omdet_turbo │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_omdet_turbo.py │ │ │ │ ├── convert_omdet_turbo_to_hf.py │ │ │ │ ├── modeling_omdet_turbo.py │ │ │ │ └── processing_omdet_turbo.py │ │ │ ├── oneformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_oneformer.py │ │ │ │ ├── convert_to_hf_oneformer.py │ │ │ │ ├── image_processing_oneformer.py │ │ │ │ ├── modeling_oneformer.py │ │ │ │ └── processing_oneformer.py │ │ │ ├── openai │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_openai.py │ │ │ │ ├── convert_openai_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_openai.py │ │ │ │ ├── modeling_tf_openai.py │ │ │ │ ├── tokenization_openai.py │ │ │ │ └── tokenization_openai_fast.py │ │ │ ├── opt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_opt.py │ │ │ │ ├── convert_opt_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_flax_opt.py │ │ │ │ ├── modeling_opt.py │ │ │ │ └── modeling_tf_opt.py │ │ │ ├── owlv2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_owlv2.py │ │ │ │ ├── convert_owlv2_to_hf.py │ │ │ │ ├── image_processing_owlv2.py │ │ │ │ ├── modeling_owlv2.py │ │ │ │ └── processing_owlv2.py │ │ │ ├── owlvit │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_owlvit.py │ │ │ │ ├── convert_owlvit_original_flax_to_hf.py │ │ │ │ ├── feature_extraction_owlvit.py │ │ │ │ ├── image_processing_owlvit.py │ │ │ │ ├── modeling_owlvit.py │ │ │ │ └── processing_owlvit.py │ │ │ ├── paligemma │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_paligemma.py │ │ │ │ ├── convert_paligemma2_weights_to_hf.py │ │ │ │ ├── convert_paligemma_weights_to_hf.py │ │ │ │ ├── modeling_paligemma.py │ │ │ │ └── processing_paligemma.py │ │ │ ├── patchtsmixer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_patchtsmixer.py │ │ │ │ └── modeling_patchtsmixer.py │ │ │ ├── patchtst │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_patchtst.py │ │ │ │ └── modeling_patchtst.py │ │ │ ├── pegasus │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_pegasus.py │ │ │ │ ├── convert_pegasus_tf_to_pytorch.py │ │ │ │ ├── modeling_flax_pegasus.py │ │ │ │ ├── modeling_pegasus.py │ │ │ │ ├── modeling_tf_pegasus.py │ │ │ │ ├── tokenization_pegasus.py │ │ │ │ └── tokenization_pegasus_fast.py │ │ │ ├── pegasus_x │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_pegasus_x.py │ │ │ │ └── modeling_pegasus_x.py │ │ │ ├── perceiver │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_perceiver.py │ │ │ │ ├── convert_perceiver_haiku_to_pytorch.py │ │ │ │ ├── feature_extraction_perceiver.py │ │ │ │ ├── image_processing_perceiver.py │ │ │ │ ├── modeling_perceiver.py │ │ │ │ └── tokenization_perceiver.py │ │ │ ├── persimmon │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_persimmon.py │ │ │ │ ├── convert_persimmon_weights_to_hf.py │ │ │ │ └── modeling_persimmon.py │ │ │ ├── phi │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_phi.py │ │ │ │ ├── convert_phi_weights_to_hf.py │ │ │ │ ├── modeling_phi.py │ │ │ │ └── modular_phi.py │ │ │ ├── phi3 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_phi3.py │ │ │ │ ├── modeling_phi3.py │ │ │ │ └── modular_phi3.py │ │ │ ├── phimoe │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_phimoe.py │ │ │ │ └── modeling_phimoe.py │ │ │ ├── phobert │ │ │ │ ├── __init__.py │ │ │ │ └── tokenization_phobert.py │ │ │ ├── pix2struct │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_pix2struct.py │ │ │ │ ├── convert_pix2struct_original_pytorch_to_hf.py │ │ │ │ ├── image_processing_pix2struct.py │ │ │ │ ├── modeling_pix2struct.py │ │ │ │ └── processing_pix2struct.py │ │ │ ├── pixtral │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_pixtral.py │ │ │ │ ├── convert_pixtral_weights_to_hf.py │ │ │ │ ├── image_processing_pixtral.py │ │ │ │ ├── image_processing_pixtral_fast.py │ │ │ │ ├── modeling_pixtral.py │ │ │ │ └── processing_pixtral.py │ │ │ ├── plbart │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_plbart.py │ │ │ │ ├── convert_plbart_original_checkpoint_to_torch.py │ │ │ │ ├── modeling_plbart.py │ │ │ │ └── tokenization_plbart.py │ │ │ ├── poolformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_poolformer.py │ │ │ │ ├── convert_poolformer_original_to_pytorch.py │ │ │ │ ├── feature_extraction_poolformer.py │ │ │ │ ├── image_processing_poolformer.py │ │ │ │ └── modeling_poolformer.py │ │ │ ├── pop2piano │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_pop2piano.py │ │ │ │ ├── convert_pop2piano_weights_to_hf.py │ │ │ │ ├── feature_extraction_pop2piano.py │ │ │ │ ├── modeling_pop2piano.py │ │ │ │ ├── processing_pop2piano.py │ │ │ │ └── tokenization_pop2piano.py │ │ │ ├── prophetnet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_prophetnet.py │ │ │ │ ├── convert_prophetnet_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_prophetnet.py │ │ │ │ └── tokenization_prophetnet.py │ │ │ ├── pvt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_pvt.py │ │ │ │ ├── convert_pvt_to_pytorch.py │ │ │ │ ├── image_processing_pvt.py │ │ │ │ └── modeling_pvt.py │ │ │ ├── pvt_v2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_pvt_v2.py │ │ │ │ ├── convert_pvt_v2_to_pytorch.py │ │ │ │ └── modeling_pvt_v2.py │ │ │ ├── qwen2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_qwen2.py │ │ │ │ ├── modeling_qwen2.py │ │ │ │ ├── modular_qwen2.py │ │ │ │ ├── tokenization_qwen2.py │ │ │ │ └── tokenization_qwen2_fast.py │ │ │ ├── qwen2_5_vl │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_qwen2_5_vl.py │ │ │ │ ├── modeling_qwen2_5_vl.py │ │ │ │ ├── modular_qwen2_5_vl.py │ │ │ │ └── processing_qwen2_5_vl.py │ │ │ ├── qwen2_audio │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_qwen2_audio.py │ │ │ │ ├── modeling_qwen2_audio.py │ │ │ │ └── processing_qwen2_audio.py │ │ │ ├── qwen2_moe │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_qwen2_moe.py │ │ │ │ └── modeling_qwen2_moe.py │ │ │ ├── qwen2_vl │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_qwen2_vl.py │ │ │ │ ├── image_processing_qwen2_vl.py │ │ │ │ ├── image_processing_qwen2_vl_fast.py │ │ │ │ ├── modeling_qwen2_vl.py │ │ │ │ └── processing_qwen2_vl.py │ │ │ ├── rag │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_rag.py │ │ │ │ ├── modeling_rag.py │ │ │ │ ├── modeling_tf_rag.py │ │ │ │ ├── retrieval_rag.py │ │ │ │ └── tokenization_rag.py │ │ │ ├── recurrent_gemma │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_recurrent_gemma.py │ │ │ │ ├── convert_recurrent_gemma_to_hf.py │ │ │ │ └── modeling_recurrent_gemma.py │ │ │ ├── reformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_reformer.py │ │ │ │ ├── convert_reformer_trax_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_reformer.py │ │ │ │ ├── tokenization_reformer.py │ │ │ │ └── tokenization_reformer_fast.py │ │ │ ├── regnet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_regnet.py │ │ │ │ ├── convert_regnet_seer_10b_to_pytorch.py │ │ │ │ ├── convert_regnet_to_pytorch.py │ │ │ │ ├── modeling_flax_regnet.py │ │ │ │ ├── modeling_regnet.py │ │ │ │ └── modeling_tf_regnet.py │ │ │ ├── rembert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_rembert.py │ │ │ │ ├── convert_rembert_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_rembert.py │ │ │ │ ├── modeling_tf_rembert.py │ │ │ │ ├── tokenization_rembert.py │ │ │ │ └── tokenization_rembert_fast.py │ │ │ ├── resnet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_resnet.py │ │ │ │ ├── convert_resnet_to_pytorch.py │ │ │ │ ├── modeling_flax_resnet.py │ │ │ │ ├── modeling_resnet.py │ │ │ │ └── modeling_tf_resnet.py │ │ │ ├── roberta │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_roberta.py │ │ │ │ ├── convert_roberta_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_flax_roberta.py │ │ │ │ ├── modeling_roberta.py │ │ │ │ ├── modeling_tf_roberta.py │ │ │ │ ├── tokenization_roberta.py │ │ │ │ └── tokenization_roberta_fast.py │ │ │ ├── roberta_prelayernorm │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_roberta_prelayernorm.py │ │ │ │ ├── convert_roberta_prelayernorm_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_flax_roberta_prelayernorm.py │ │ │ │ ├── modeling_roberta_prelayernorm.py │ │ │ │ └── modeling_tf_roberta_prelayernorm.py │ │ │ ├── roc_bert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_roc_bert.py │ │ │ │ ├── modeling_roc_bert.py │ │ │ │ └── tokenization_roc_bert.py │ │ │ ├── roformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_roformer.py │ │ │ │ ├── convert_roformer_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_flax_roformer.py │ │ │ │ ├── modeling_roformer.py │ │ │ │ ├── modeling_tf_roformer.py │ │ │ │ ├── tokenization_roformer.py │ │ │ │ ├── tokenization_roformer_fast.py │ │ │ │ └── tokenization_utils.py │ │ │ ├── rt_detr │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_rt_detr.py │ │ │ │ ├── configuration_rt_detr_resnet.py │ │ │ │ ├── convert_rt_detr_original_pytorch_checkpoint_to_hf.py │ │ │ │ ├── image_processing_rt_detr.py │ │ │ │ ├── image_processing_rt_detr_fast.py │ │ │ │ ├── modeling_rt_detr.py │ │ │ │ ├── modeling_rt_detr_resnet.py │ │ │ │ └── modular_rt_detr.py │ │ │ ├── rt_detr_v2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_rt_detr_v2.py │ │ │ │ ├── convert_rt_detr_v2_weights_to_hf.py │ │ │ │ ├── modeling_rt_detr_v2.py │ │ │ │ └── modular_rt_detr_v2.py │ │ │ ├── rwkv │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_rwkv.py │ │ │ │ ├── convert_rwkv_checkpoint_to_hf.py │ │ │ │ └── modeling_rwkv.py │ │ │ ├── sam │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_sam.py │ │ │ │ ├── convert_sam_to_hf.py │ │ │ │ ├── image_processing_sam.py │ │ │ │ ├── modeling_sam.py │ │ │ │ ├── modeling_tf_sam.py │ │ │ │ └── processing_sam.py │ │ │ ├── seamless_m4t │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_seamless_m4t.py │ │ │ │ ├── convert_fairseq2_to_hf.py │ │ │ │ ├── feature_extraction_seamless_m4t.py │ │ │ │ ├── modeling_seamless_m4t.py │ │ │ │ ├── processing_seamless_m4t.py │ │ │ │ ├── tokenization_seamless_m4t.py │ │ │ │ └── tokenization_seamless_m4t_fast.py │ │ │ ├── seamless_m4t_v2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_seamless_m4t_v2.py │ │ │ │ ├── convert_fairseq2_to_hf.py │ │ │ │ └── modeling_seamless_m4t_v2.py │ │ │ ├── segformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_segformer.py │ │ │ │ ├── convert_segformer_original_to_pytorch.py │ │ │ │ ├── feature_extraction_segformer.py │ │ │ │ ├── image_processing_segformer.py │ │ │ │ ├── modeling_segformer.py │ │ │ │ └── modeling_tf_segformer.py │ │ │ ├── seggpt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_seggpt.py │ │ │ │ ├── convert_seggpt_to_hf.py │ │ │ │ ├── image_processing_seggpt.py │ │ │ │ └── modeling_seggpt.py │ │ │ ├── sew │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_sew.py │ │ │ │ ├── convert_sew_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── modeling_sew.py │ │ │ ├── sew_d │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_sew_d.py │ │ │ │ ├── convert_sew_d_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── modeling_sew_d.py │ │ │ ├── siglip │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_siglip.py │ │ │ │ ├── convert_siglip_to_hf.py │ │ │ │ ├── image_processing_siglip.py │ │ │ │ ├── image_processing_siglip_fast.py │ │ │ │ ├── modeling_siglip.py │ │ │ │ ├── processing_siglip.py │ │ │ │ └── tokenization_siglip.py │ │ │ ├── siglip2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_siglip2.py │ │ │ │ ├── convert_siglip2_to_hf.py │ │ │ │ ├── image_processing_siglip2.py │ │ │ │ ├── image_processing_siglip2_fast.py │ │ │ │ ├── modeling_siglip2.py │ │ │ │ ├── modular_siglip2.py │ │ │ │ └── processing_siglip2.py │ │ │ ├── smolvlm │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_smolvlm.py │ │ │ │ ├── image_processing_smolvlm.py │ │ │ │ ├── modeling_smolvlm.py │ │ │ │ ├── modular_smolvlm.py │ │ │ │ ├── processing_smolvlm.py │ │ │ │ └── video_processing_smolvlm.py │ │ │ ├── speech_encoder_decoder │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_speech_encoder_decoder.py │ │ │ │ ├── convert_mbart_wav2vec2_seq2seq_original_to_pytorch.py │ │ │ │ ├── convert_speech_to_text_wav2vec2_seq2seq_original_to_pytorch.py │ │ │ │ ├── modeling_flax_speech_encoder_decoder.py │ │ │ │ └── modeling_speech_encoder_decoder.py │ │ │ ├── speech_to_text │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_speech_to_text.py │ │ │ │ ├── convert_s2t_fairseq_to_tfms.py │ │ │ │ ├── feature_extraction_speech_to_text.py │ │ │ │ ├── modeling_speech_to_text.py │ │ │ │ ├── modeling_tf_speech_to_text.py │ │ │ │ ├── processing_speech_to_text.py │ │ │ │ └── tokenization_speech_to_text.py │ │ │ ├── speecht5 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_speecht5.py │ │ │ │ ├── convert_hifigan.py │ │ │ │ ├── convert_speecht5_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── feature_extraction_speecht5.py │ │ │ │ ├── modeling_speecht5.py │ │ │ │ ├── number_normalizer.py │ │ │ │ ├── processing_speecht5.py │ │ │ │ └── tokenization_speecht5.py │ │ │ ├── splinter │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_splinter.py │ │ │ │ ├── modeling_splinter.py │ │ │ │ ├── tokenization_splinter.py │ │ │ │ └── tokenization_splinter_fast.py │ │ │ ├── squeezebert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_squeezebert.py │ │ │ │ ├── modeling_squeezebert.py │ │ │ │ ├── tokenization_squeezebert.py │ │ │ │ └── tokenization_squeezebert_fast.py │ │ │ ├── stablelm │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_stablelm.py │ │ │ │ └── modeling_stablelm.py │ │ │ ├── starcoder2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_starcoder2.py │ │ │ │ ├── modeling_starcoder2.py │ │ │ │ └── modular_starcoder2.py │ │ │ ├── superglue │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_superglue.py │ │ │ │ ├── convert_superglue_to_hf.py │ │ │ │ ├── image_processing_superglue.py │ │ │ │ └── modeling_superglue.py │ │ │ ├── superpoint │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_superpoint.py │ │ │ │ ├── convert_superpoint_to_pytorch.py │ │ │ │ ├── image_processing_superpoint.py │ │ │ │ └── modeling_superpoint.py │ │ │ ├── swiftformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_swiftformer.py │ │ │ │ ├── convert_swiftformer_original_to_hf.py │ │ │ │ ├── modeling_swiftformer.py │ │ │ │ └── modeling_tf_swiftformer.py │ │ │ ├── swin │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_swin.py │ │ │ │ ├── convert_swin_simmim_to_pytorch.py │ │ │ │ ├── convert_swin_timm_to_pytorch.py │ │ │ │ ├── modeling_swin.py │ │ │ │ └── modeling_tf_swin.py │ │ │ ├── swin2sr │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_swin2sr.py │ │ │ │ ├── convert_swin2sr_original_to_pytorch.py │ │ │ │ ├── image_processing_swin2sr.py │ │ │ │ └── modeling_swin2sr.py │ │ │ ├── swinv2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_swinv2.py │ │ │ │ ├── convert_swinv2_timm_to_pytorch.py │ │ │ │ └── modeling_swinv2.py │ │ │ ├── switch_transformers │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_switch_transformers.py │ │ │ │ ├── convert_big_switch.py │ │ │ │ ├── convert_switch_transformers_original_flax_checkpoint_to_pytorch.py │ │ │ │ └── modeling_switch_transformers.py │ │ │ ├── t5 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_t5.py │ │ │ │ ├── convert_t5_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── convert_t5x_checkpoint_to_flax.py │ │ │ │ ├── convert_t5x_checkpoint_to_pytorch.py │ │ │ │ ├── download_from_gcp.sh │ │ │ │ ├── modeling_flax_t5.py │ │ │ │ ├── modeling_t5.py │ │ │ │ ├── modeling_tf_t5.py │ │ │ │ ├── tokenization_t5.py │ │ │ │ └── tokenization_t5_fast.py │ │ │ ├── table_transformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_table_transformer.py │ │ │ │ ├── convert_table_transformer_to_hf.py │ │ │ │ ├── convert_table_transformer_to_hf_no_timm.py │ │ │ │ └── modeling_table_transformer.py │ │ │ ├── tapas │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_tapas.py │ │ │ │ ├── convert_tapas_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_tapas.py │ │ │ │ ├── modeling_tf_tapas.py │ │ │ │ └── tokenization_tapas.py │ │ │ ├── textnet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_textnet.py │ │ │ │ ├── convert_textnet_to_hf.py │ │ │ │ ├── image_processing_textnet.py │ │ │ │ └── modeling_textnet.py │ │ │ ├── time_series_transformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_time_series_transformer.py │ │ │ │ └── modeling_time_series_transformer.py │ │ │ ├── timesformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_timesformer.py │ │ │ │ ├── convert_timesformer_to_pytorch.py │ │ │ │ └── modeling_timesformer.py │ │ │ ├── timm_backbone │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_timm_backbone.py │ │ │ │ └── modeling_timm_backbone.py │ │ │ ├── timm_wrapper │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_timm_wrapper.py │ │ │ │ ├── image_processing_timm_wrapper.py │ │ │ │ └── modeling_timm_wrapper.py │ │ │ ├── trocr │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_trocr.py │ │ │ │ ├── convert_trocr_unilm_to_pytorch.py │ │ │ │ ├── modeling_trocr.py │ │ │ │ └── processing_trocr.py │ │ │ ├── tvp │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_tvp.py │ │ │ │ ├── image_processing_tvp.py │ │ │ │ ├── modeling_tvp.py │ │ │ │ └── processing_tvp.py │ │ │ ├── udop │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_udop.py │ │ │ │ ├── convert_udop_to_hf.py │ │ │ │ ├── modeling_udop.py │ │ │ │ ├── processing_udop.py │ │ │ │ ├── tokenization_udop.py │ │ │ │ └── tokenization_udop_fast.py │ │ │ ├── umt5 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_umt5.py │ │ │ │ ├── convert_umt5_checkpoint_to_pytorch.py │ │ │ │ └── modeling_umt5.py │ │ │ ├── unispeech │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_unispeech.py │ │ │ │ ├── convert_unispeech_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── modeling_unispeech.py │ │ │ ├── unispeech_sat │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_unispeech_sat.py │ │ │ │ ├── convert_unispeech_original_s3prl_checkpoint_to_pytorch.py │ │ │ │ ├── convert_unispeech_sat_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── modeling_unispeech_sat.py │ │ │ ├── univnet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_univnet.py │ │ │ │ ├── convert_univnet.py │ │ │ │ ├── feature_extraction_univnet.py │ │ │ │ └── modeling_univnet.py │ │ │ ├── upernet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_upernet.py │ │ │ │ ├── convert_convnext_upernet_to_pytorch.py │ │ │ │ ├── convert_swin_upernet_to_pytorch.py │ │ │ │ └── modeling_upernet.py │ │ │ ├── video_llava │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_video_llava.py │ │ │ │ ├── convert_video_llava_weights_to_hf.py │ │ │ │ ├── image_processing_video_llava.py │ │ │ │ ├── modeling_video_llava.py │ │ │ │ └── processing_video_llava.py │ │ │ ├── videomae │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_videomae.py │ │ │ │ ├── convert_videomae_to_pytorch.py │ │ │ │ ├── feature_extraction_videomae.py │ │ │ │ ├── image_processing_videomae.py │ │ │ │ └── modeling_videomae.py │ │ │ ├── vilt │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vilt.py │ │ │ │ ├── convert_vilt_original_to_pytorch.py │ │ │ │ ├── feature_extraction_vilt.py │ │ │ │ ├── image_processing_vilt.py │ │ │ │ ├── modeling_vilt.py │ │ │ │ └── processing_vilt.py │ │ │ ├── vipllava │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vipllava.py │ │ │ │ ├── convert_vipllava_weights_to_hf.py │ │ │ │ └── modeling_vipllava.py │ │ │ ├── vision_encoder_decoder │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vision_encoder_decoder.py │ │ │ │ ├── modeling_flax_vision_encoder_decoder.py │ │ │ │ ├── modeling_tf_vision_encoder_decoder.py │ │ │ │ └── modeling_vision_encoder_decoder.py │ │ │ ├── vision_text_dual_encoder │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vision_text_dual_encoder.py │ │ │ │ ├── modeling_flax_vision_text_dual_encoder.py │ │ │ │ ├── modeling_tf_vision_text_dual_encoder.py │ │ │ │ ├── modeling_vision_text_dual_encoder.py │ │ │ │ └── processing_vision_text_dual_encoder.py │ │ │ ├── visual_bert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_visual_bert.py │ │ │ │ ├── convert_visual_bert_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── modeling_visual_bert.py │ │ │ ├── vit │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vit.py │ │ │ │ ├── convert_dino_to_pytorch.py │ │ │ │ ├── convert_vit_timm_to_pytorch.py │ │ │ │ ├── feature_extraction_vit.py │ │ │ │ ├── image_processing_vit.py │ │ │ │ ├── image_processing_vit_fast.py │ │ │ │ ├── modeling_flax_vit.py │ │ │ │ ├── modeling_tf_vit.py │ │ │ │ └── modeling_vit.py │ │ │ ├── vit_mae │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vit_mae.py │ │ │ │ ├── convert_vit_mae_to_pytorch.py │ │ │ │ ├── modeling_tf_vit_mae.py │ │ │ │ └── modeling_vit_mae.py │ │ │ ├── vit_msn │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vit_msn.py │ │ │ │ ├── convert_msn_to_pytorch.py │ │ │ │ └── modeling_vit_msn.py │ │ │ ├── vitdet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vitdet.py │ │ │ │ └── modeling_vitdet.py │ │ │ ├── vitmatte │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vitmatte.py │ │ │ │ ├── convert_vitmatte_to_hf.py │ │ │ │ ├── image_processing_vitmatte.py │ │ │ │ └── modeling_vitmatte.py │ │ │ ├── vitpose │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vitpose.py │ │ │ │ ├── convert_vitpose_to_hf.py │ │ │ │ ├── image_processing_vitpose.py │ │ │ │ └── modeling_vitpose.py │ │ │ ├── vitpose_backbone │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vitpose_backbone.py │ │ │ │ └── modeling_vitpose_backbone.py │ │ │ ├── vits │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vits.py │ │ │ │ ├── convert_original_checkpoint.py │ │ │ │ ├── modeling_vits.py │ │ │ │ └── tokenization_vits.py │ │ │ ├── vivit │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_vivit.py │ │ │ │ ├── convert_vivit_flax_to_pytorch.py │ │ │ │ ├── image_processing_vivit.py │ │ │ │ └── modeling_vivit.py │ │ │ ├── wav2vec2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_wav2vec2.py │ │ │ │ ├── convert_wav2vec2_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── convert_wav2vec2_original_s3prl_checkpoint_to_pytorch.py │ │ │ │ ├── feature_extraction_wav2vec2.py │ │ │ │ ├── modeling_flax_wav2vec2.py │ │ │ │ ├── modeling_tf_wav2vec2.py │ │ │ │ ├── modeling_wav2vec2.py │ │ │ │ ├── processing_wav2vec2.py │ │ │ │ └── tokenization_wav2vec2.py │ │ │ ├── wav2vec2_bert │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_wav2vec2_bert.py │ │ │ │ ├── convert_wav2vec2_seamless_checkpoint.py │ │ │ │ ├── modeling_wav2vec2_bert.py │ │ │ │ └── processing_wav2vec2_bert.py │ │ │ ├── wav2vec2_conformer │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_wav2vec2_conformer.py │ │ │ │ ├── convert_wav2vec2_conformer_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── modeling_wav2vec2_conformer.py │ │ │ ├── wav2vec2_phoneme │ │ │ │ ├── __init__.py │ │ │ │ └── tokenization_wav2vec2_phoneme.py │ │ │ ├── wav2vec2_with_lm │ │ │ │ ├── __init__.py │ │ │ │ └── processing_wav2vec2_with_lm.py │ │ │ ├── wavlm │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_wavlm.py │ │ │ │ ├── convert_wavlm_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── convert_wavlm_original_s3prl_checkpoint_to_pytorch.py │ │ │ │ └── modeling_wavlm.py │ │ │ ├── whisper │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_whisper.py │ │ │ │ ├── convert_openai_to_hf.py │ │ │ │ ├── english_normalizer.py │ │ │ │ ├── feature_extraction_whisper.py │ │ │ │ ├── generation_whisper.py │ │ │ │ ├── modeling_flax_whisper.py │ │ │ │ ├── modeling_tf_whisper.py │ │ │ │ ├── modeling_whisper.py │ │ │ │ ├── processing_whisper.py │ │ │ │ ├── tokenization_whisper.py │ │ │ │ └── tokenization_whisper_fast.py │ │ │ ├── x_clip │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_x_clip.py │ │ │ │ ├── convert_x_clip_original_pytorch_to_hf.py │ │ │ │ ├── modeling_x_clip.py │ │ │ │ └── processing_x_clip.py │ │ │ ├── xglm │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_xglm.py │ │ │ │ ├── convert_xglm_original_ckpt_to_trfms.py │ │ │ │ ├── modeling_flax_xglm.py │ │ │ │ ├── modeling_tf_xglm.py │ │ │ │ ├── modeling_xglm.py │ │ │ │ ├── tokenization_xglm.py │ │ │ │ └── tokenization_xglm_fast.py │ │ │ ├── xlm │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_xlm.py │ │ │ │ ├── convert_xlm_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_tf_xlm.py │ │ │ │ ├── modeling_xlm.py │ │ │ │ └── tokenization_xlm.py │ │ │ ├── xlm_roberta │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_xlm_roberta.py │ │ │ │ ├── modeling_flax_xlm_roberta.py │ │ │ │ ├── modeling_tf_xlm_roberta.py │ │ │ │ ├── modeling_xlm_roberta.py │ │ │ │ ├── tokenization_xlm_roberta.py │ │ │ │ └── tokenization_xlm_roberta_fast.py │ │ │ ├── xlm_roberta_xl │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_xlm_roberta_xl.py │ │ │ │ ├── convert_xlm_roberta_xl_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── modeling_xlm_roberta_xl.py │ │ │ ├── xlnet │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_xlnet.py │ │ │ │ ├── convert_xlnet_original_tf_checkpoint_to_pytorch.py │ │ │ │ ├── modeling_tf_xlnet.py │ │ │ │ ├── modeling_xlnet.py │ │ │ │ ├── tokenization_xlnet.py │ │ │ │ └── tokenization_xlnet_fast.py │ │ │ ├── xmod │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_xmod.py │ │ │ │ ├── convert_xmod_original_pytorch_checkpoint_to_pytorch.py │ │ │ │ └── modeling_xmod.py │ │ │ ├── yolos │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_yolos.py │ │ │ │ ├── convert_yolos_to_pytorch.py │ │ │ │ ├── feature_extraction_yolos.py │ │ │ │ ├── image_processing_yolos.py │ │ │ │ └── modeling_yolos.py │ │ │ ├── yoso │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_yoso.py │ │ │ │ ├── convert_yoso_pytorch_to_pytorch.py │ │ │ │ └── modeling_yoso.py │ │ │ ├── zamba │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_zamba.py │ │ │ │ └── modeling_zamba.py │ │ │ ├── zamba2 │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_zamba2.py │ │ │ │ ├── modeling_zamba2.py │ │ │ │ └── modular_zamba2.py │ │ │ └── zoedepth │ │ │ │ ├── __init__.py │ │ │ │ ├── configuration_zoedepth.py │ │ │ │ ├── convert_zoedepth_to_hf.py │ │ │ │ ├── image_processing_zoedepth.py │ │ │ │ └── modeling_zoedepth.py │ │ │ ├── onnx │ │ │ ├── __init__.py │ │ │ ├── __main__.py │ │ │ ├── config.py │ │ │ ├── convert.py │ │ │ ├── features.py │ │ │ └── utils.py │ │ │ ├── optimization.py │ │ │ ├── optimization_tf.py │ │ │ ├── pipelines │ │ │ ├── __init__.py │ │ │ ├── audio_classification.py │ │ │ ├── audio_utils.py │ │ │ ├── automatic_speech_recognition.py │ │ │ ├── base.py │ │ │ ├── depth_estimation.py │ │ │ ├── document_question_answering.py │ │ │ ├── feature_extraction.py │ │ │ ├── fill_mask.py │ │ │ ├── image_classification.py │ │ │ ├── image_feature_extraction.py │ │ │ ├── image_segmentation.py │ │ │ ├── image_text_to_text.py │ │ │ ├── image_to_image.py │ │ │ ├── image_to_text.py │ │ │ ├── mask_generation.py │ │ │ ├── object_detection.py │ │ │ ├── pt_utils.py │ │ │ ├── question_answering.py │ │ │ ├── table_question_answering.py │ │ │ ├── text2text_generation.py │ │ │ ├── text_classification.py │ │ │ ├── text_generation.py │ │ │ ├── text_to_audio.py │ │ │ ├── token_classification.py │ │ │ ├── video_classification.py │ │ │ ├── visual_question_answering.py │ │ │ ├── zero_shot_audio_classification.py │ │ │ ├── zero_shot_classification.py │ │ │ ├── zero_shot_image_classification.py │ │ │ └── zero_shot_object_detection.py │ │ │ ├── processing_utils.py │ │ │ ├── pytorch_utils.py │ │ │ ├── quantizers │ │ │ ├── __init__.py │ │ │ ├── auto.py │ │ │ ├── base.py │ │ │ ├── quantizer_aqlm.py │ │ │ ├── quantizer_awq.py │ │ │ ├── quantizer_bitnet.py │ │ │ ├── quantizer_bnb_4bit.py │ │ │ ├── quantizer_bnb_8bit.py │ │ │ ├── quantizer_compressed_tensors.py │ │ │ ├── quantizer_eetq.py │ │ │ ├── quantizer_fbgemm_fp8.py │ │ │ ├── quantizer_finegrained_fp8.py │ │ │ ├── quantizer_gptq.py │ │ │ ├── quantizer_higgs.py │ │ │ ├── quantizer_hqq.py │ │ │ ├── quantizer_quanto.py │ │ │ ├── quantizer_spqr.py │ │ │ ├── quantizer_torchao.py │ │ │ ├── quantizer_vptq.py │ │ │ └── quantizers_utils.py │ │ │ ├── safetensors_conversion.py │ │ │ ├── sagemaker │ │ │ ├── __init__.py │ │ │ ├── trainer_sm.py │ │ │ └── training_args_sm.py │ │ │ ├── testing_utils.py │ │ │ ├── tf_utils.py │ │ │ ├── time_series_utils.py │ │ │ ├── tokenization_utils.py │ │ │ ├── tokenization_utils_base.py │ │ │ ├── tokenization_utils_fast.py │ │ │ ├── trainer.py │ │ │ ├── trainer_callback.py │ │ │ ├── trainer_pt_utils.py │ │ │ ├── trainer_seq2seq.py │ │ │ ├── trainer_utils.py │ │ │ ├── training_args.py │ │ │ ├── training_args_seq2seq.py │ │ │ ├── training_args_tf.py │ │ │ └── utils │ │ │ ├── __init__.py │ │ │ ├── backbone_utils.py │ │ │ ├── bitsandbytes.py │ │ │ ├── chat_template_utils.py │ │ │ ├── constants.py │ │ │ ├── deprecation.py │ │ │ ├── doc.py │ │ │ ├── dummy_detectron2_objects.py │ │ │ ├── dummy_essentia_and_librosa_and_pretty_midi_and_scipy_and_torch_objects.py │ │ │ ├── dummy_flax_objects.py │ │ │ ├── dummy_keras_nlp_objects.py │ │ │ ├── dummy_music_objects.py │ │ │ ├── dummy_pt_objects.py │ │ │ ├── dummy_sentencepiece_and_tokenizers_objects.py │ │ │ ├── dummy_sentencepiece_objects.py │ │ │ ├── dummy_speech_objects.py │ │ │ ├── dummy_tensorflow_text_objects.py │ │ │ ├── dummy_tf_objects.py │ │ │ ├── dummy_timm_and_torchvision_objects.py │ │ │ ├── dummy_tokenizers_objects.py │ │ │ ├── dummy_torchaudio_objects.py │ │ │ ├── dummy_torchvision_objects.py │ │ │ ├── dummy_vision_objects.py │ │ │ ├── fx.py │ │ │ ├── generic.py │ │ │ ├── hp_naming.py │ │ │ ├── hub.py │ │ │ ├── import_utils.py │ │ │ ├── logging.py │ │ │ ├── model_parallel_utils.py │ │ │ ├── notebook.py │ │ │ ├── peft_utils.py │ │ │ ├── quantization_config.py │ │ │ ├── sentencepiece_model_pb2.py │ │ │ ├── sentencepiece_model_pb2_new.py │ │ │ └── versions.py │ │ ├── templates │ │ ├── adding_a_missing_tokenization_test │ │ │ ├── README.md │ │ │ ├── cookiecutter-template-{{cookiecutter.modelname}} │ │ │ │ └── test_tokenization_{{cookiecutter.lowercase_modelname}}.py │ │ │ └── cookiecutter.json │ │ ├── adding_a_new_example_script │ │ │ ├── README.md │ │ │ ├── cookiecutter.json │ │ │ └── {{cookiecutter.directory_name}} │ │ │ │ └── run_{{cookiecutter.example_shortcut}}.py │ │ └── adding_a_new_model │ │ │ ├── ADD_NEW_MODEL_PROPOSAL_TEMPLATE.md │ │ │ ├── README.md │ │ │ └── open_model_proposals │ │ │ ├── ADD_BIG_BIRD.md │ │ │ └── README.md │ │ ├── tests │ │ ├── __init__.py │ │ ├── agents │ │ │ ├── __init__.py │ │ │ ├── test_agent_types.py │ │ │ ├── test_agents.py │ │ │ ├── test_document_question_answering.py │ │ │ ├── test_final_answer.py │ │ │ ├── test_image_question_answering.py │ │ │ ├── test_monitoring.py │ │ │ ├── test_python_interpreter.py │ │ │ ├── test_search.py │ │ │ ├── test_speech_to_text.py │ │ │ ├── test_text_to_speech.py │ │ │ ├── test_tools_common.py │ │ │ └── test_translation.py │ │ ├── bettertransformer │ │ │ ├── __init__.py │ │ │ └── test_integration.py │ │ ├── deepspeed │ │ │ ├── ds_config_zero2.json │ │ │ ├── ds_config_zero3.json │ │ │ ├── test_deepspeed.py │ │ │ ├── test_model_zoo.py │ │ │ └── vit_feature_extractor.json │ │ ├── extended │ │ │ └── test_trainer_ext.py │ │ ├── fixtures │ │ │ ├── add_distilbert_like_config.json │ │ │ ├── dummy-config.json │ │ │ ├── dummy_feature_extractor_config.json │ │ │ ├── empty.txt │ │ │ ├── input.txt │ │ │ ├── merges.txt │ │ │ ├── preprocessor_config.json │ │ │ ├── sample_text.txt │ │ │ ├── sample_text_no_unicode.txt │ │ │ ├── spiece.model │ │ │ ├── test_entity_vocab.json │ │ │ ├── test_sentencepiece.model │ │ │ ├── test_sentencepiece_bpe.model │ │ │ ├── test_sentencepiece_bpe_char.model │ │ │ ├── test_sentencepiece_no_bos.model │ │ │ ├── test_sentencepiece_with_bytefallback.model │ │ │ ├── tests_samples │ │ │ │ ├── .gitignore │ │ │ │ ├── COCO │ │ │ │ │ ├── 000000004016.png │ │ │ │ │ ├── 000000039769.png │ │ │ │ │ ├── coco_annotations.txt │ │ │ │ │ ├── coco_panoptic │ │ │ │ │ │ └── 000000039769.png │ │ │ │ │ └── coco_panoptic_annotations.txt │ │ │ │ ├── GermEval │ │ │ │ │ ├── dev.txt │ │ │ │ │ ├── labels.txt │ │ │ │ │ └── train.txt │ │ │ │ ├── MRPC │ │ │ │ │ ├── dev.csv │ │ │ │ │ ├── dev.tsv │ │ │ │ │ ├── train.csv │ │ │ │ │ └── train.tsv │ │ │ │ ├── SQUAD │ │ │ │ │ └── sample.json │ │ │ │ ├── STS-B │ │ │ │ │ ├── dev.tsv │ │ │ │ │ └── train.tsv │ │ │ │ ├── conll │ │ │ │ │ └── sample.json │ │ │ │ ├── swag │ │ │ │ │ └── sample.json │ │ │ │ ├── wiki_text │ │ │ │ │ └── wiki_00 │ │ │ │ ├── wmt16 │ │ │ │ │ └── sample.json │ │ │ │ ├── wmt_en_ro │ │ │ │ │ ├── test.json │ │ │ │ │ ├── train.json │ │ │ │ │ └── val.json │ │ │ │ └── xsum │ │ │ │ │ └── sample.json │ │ │ ├── vocab.json │ │ │ └── vocab.txt │ │ ├── fsdp │ │ │ └── test_fsdp.py │ │ ├── generation │ │ │ ├── __init__.py │ │ │ ├── test_beam_constraints.py │ │ │ ├── test_beam_search.py │ │ │ ├── test_candidate_generator.py │ │ │ ├── test_configuration_utils.py │ │ │ ├── test_fsdp.py │ │ │ ├── test_logits_process.py │ │ │ ├── test_stopping_criteria.py │ │ │ ├── test_streamers.py │ │ │ └── test_utils.py │ │ ├── models │ │ │ ├── __init__.py │ │ │ ├── albert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_albert.py │ │ │ │ ├── test_modeling_flax_albert.py │ │ │ │ ├── test_modeling_tf_albert.py │ │ │ │ └── test_tokenization_albert.py │ │ │ ├── align │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_align.py │ │ │ │ └── test_processor_align.py │ │ │ ├── altclip │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_altclip.py │ │ │ │ └── test_processor_altclip.py │ │ │ ├── aria │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_aria.py │ │ │ │ ├── test_modeling_aria.py │ │ │ │ └── test_processor_aria.py │ │ │ ├── audio_spectrogram_transformer │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_audio_spectrogram_transformer.py │ │ │ │ └── test_modeling_audio_spectrogram_transformer.py │ │ │ ├── auto │ │ │ │ ├── __init__.py │ │ │ │ ├── test_configuration_auto.py │ │ │ │ ├── test_feature_extraction_auto.py │ │ │ │ ├── test_image_processing_auto.py │ │ │ │ ├── test_modeling_auto.py │ │ │ │ ├── test_modeling_flax_auto.py │ │ │ │ ├── test_modeling_tf_auto.py │ │ │ │ ├── test_processor_auto.py │ │ │ │ └── test_tokenization_auto.py │ │ │ ├── autoformer │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_autoformer.py │ │ │ ├── aya_vision │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_aya_vision.py │ │ │ │ └── test_processor_aya_vision.py │ │ │ ├── bamba │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_bamba.py │ │ │ ├── bark │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_bark.py │ │ │ │ └── test_processor_bark.py │ │ │ ├── bart │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_bart.py │ │ │ │ ├── test_modeling_flax_bart.py │ │ │ │ ├── test_modeling_tf_bart.py │ │ │ │ └── test_tokenization_bart.py │ │ │ ├── barthez │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_barthez.py │ │ │ ├── bartpho │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_bartpho.py │ │ │ ├── beit │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_beit.py │ │ │ │ ├── test_modeling_beit.py │ │ │ │ └── test_modeling_flax_beit.py │ │ │ ├── bert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_bert.py │ │ │ │ ├── test_modeling_flax_bert.py │ │ │ │ ├── test_modeling_tf_bert.py │ │ │ │ ├── test_tokenization_bert.py │ │ │ │ └── test_tokenization_bert_tf.py │ │ │ ├── bert_generation │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_bert_generation.py │ │ │ │ └── test_tokenization_bert_generation.py │ │ │ ├── bert_japanese │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_bert_japanese.py │ │ │ ├── bertweet │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_bertweet.py │ │ │ ├── big_bird │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_big_bird.py │ │ │ │ ├── test_modeling_flax_big_bird.py │ │ │ │ └── test_tokenization_big_bird.py │ │ │ ├── bigbird_pegasus │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_bigbird_pegasus.py │ │ │ ├── biogpt │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_biogpt.py │ │ │ │ └── test_tokenization_biogpt.py │ │ │ ├── bit │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_bit.py │ │ │ ├── blenderbot │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_blenderbot.py │ │ │ │ ├── test_modeling_flax_blenderbot.py │ │ │ │ ├── test_modeling_tf_blenderbot.py │ │ │ │ └── test_tokenization_blenderbot.py │ │ │ ├── blenderbot_small │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_blenderbot_small.py │ │ │ │ ├── test_modeling_flax_blenderbot_small.py │ │ │ │ ├── test_modeling_tf_blenderbot_small.py │ │ │ │ └── test_tokenization_blenderbot_small.py │ │ │ ├── blip │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_blip.py │ │ │ │ ├── test_modeling_blip.py │ │ │ │ ├── test_modeling_blip_text.py │ │ │ │ ├── test_modeling_tf_blip.py │ │ │ │ ├── test_modeling_tf_blip_text.py │ │ │ │ └── test_processor_blip.py │ │ │ ├── blip_2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_blip_2.py │ │ │ │ └── test_processor_blip_2.py │ │ │ ├── bloom │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_bloom.py │ │ │ │ ├── test_modeling_flax_bloom.py │ │ │ │ └── test_tokenization_bloom.py │ │ │ ├── bridgetower │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_bridgetower.py │ │ │ │ ├── test_modeling_bridgetower.py │ │ │ │ └── test_processor_bridgetower.py │ │ │ ├── bros │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_bros.py │ │ │ ├── byt5 │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_byt5.py │ │ │ ├── camembert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_camembert.py │ │ │ │ ├── test_modeling_tf_camembert.py │ │ │ │ └── test_tokenization_camembert.py │ │ │ ├── canine │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_canine.py │ │ │ │ └── test_tokenization_canine.py │ │ │ ├── chameleon │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_chameleon.py │ │ │ │ ├── test_modeling_chameleon.py │ │ │ │ └── test_processor_chameleon.py │ │ │ ├── chinese_clip │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_chinese_clip.py │ │ │ │ ├── test_modeling_chinese_clip.py │ │ │ │ └── test_processor_chinese_clip.py │ │ │ ├── clap │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_clap.py │ │ │ │ ├── test_modeling_clap.py │ │ │ │ └── test_processor_clap.py │ │ │ ├── clip │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_clip.py │ │ │ │ ├── test_modeling_clip.py │ │ │ │ ├── test_modeling_flax_clip.py │ │ │ │ ├── test_modeling_tf_clip.py │ │ │ │ ├── test_processor_clip.py │ │ │ │ └── test_tokenization_clip.py │ │ │ ├── clipseg │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_clipseg.py │ │ │ │ └── test_processor_clipseg.py │ │ │ ├── clvp │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_clvp.py │ │ │ │ ├── test_modeling_clvp.py │ │ │ │ ├── test_processor_clvp.py │ │ │ │ └── test_tokenization_clvp.py │ │ │ ├── code_llama │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_code_llama.py │ │ │ ├── codegen │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_codegen.py │ │ │ │ └── test_tokenization_codegen.py │ │ │ ├── cohere │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_cohere.py │ │ │ │ └── test_tokenization_cohere.py │ │ │ ├── cohere2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_cohere2.py │ │ │ ├── colpali │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_colpali.py │ │ │ │ └── test_processing_colpali.py │ │ │ ├── conditional_detr │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_conditional_detr.py │ │ │ │ └── test_modeling_conditional_detr.py │ │ │ ├── convbert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_convbert.py │ │ │ │ └── test_modeling_tf_convbert.py │ │ │ ├── convnext │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_convnext.py │ │ │ │ ├── test_modeling_convnext.py │ │ │ │ └── test_modeling_tf_convnext.py │ │ │ ├── convnextv2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_convnextv2.py │ │ │ │ └── test_modeling_tf_convnextv2.py │ │ │ ├── cpm │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_cpm.py │ │ │ ├── cpmant │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_cpmant.py │ │ │ │ └── test_tokenization_cpmant.py │ │ │ ├── ctrl │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_ctrl.py │ │ │ │ ├── test_modeling_tf_ctrl.py │ │ │ │ └── test_tokenization_ctrl.py │ │ │ ├── cvt │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_cvt.py │ │ │ │ └── test_modeling_tf_cvt.py │ │ │ ├── dab_detr │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_dab_detr.py │ │ │ ├── dac │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_dac.py │ │ │ │ └── test_modeling_dac.py │ │ │ ├── data2vec │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_data2vec_audio.py │ │ │ │ ├── test_modeling_data2vec_text.py │ │ │ │ ├── test_modeling_data2vec_vision.py │ │ │ │ └── test_modeling_tf_data2vec_vision.py │ │ │ ├── dbrx │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_dbrx.py │ │ │ ├── deberta │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_deberta.py │ │ │ │ ├── test_modeling_tf_deberta.py │ │ │ │ └── test_tokenization_deberta.py │ │ │ ├── deberta_v2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_deberta_v2.py │ │ │ │ ├── test_modeling_tf_deberta_v2.py │ │ │ │ └── test_tokenization_deberta_v2.py │ │ │ ├── decision_transformer │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_decision_transformer.py │ │ │ ├── deformable_detr │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_deformable_detr.py │ │ │ │ └── test_modeling_deformable_detr.py │ │ │ ├── deit │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_deit.py │ │ │ │ ├── test_modeling_deit.py │ │ │ │ └── test_modeling_tf_deit.py │ │ │ ├── depth_anything │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_depth_anything.py │ │ │ ├── depth_pro │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_depth_pro.py │ │ │ │ └── test_modeling_depth_pro.py │ │ │ ├── detr │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_detr.py │ │ │ │ └── test_modeling_detr.py │ │ │ ├── diffllama │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_diffllama.py │ │ │ ├── dinat │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_dinat.py │ │ │ ├── dinov2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_dinov2.py │ │ │ │ └── test_modeling_flax_dinov2.py │ │ │ ├── dinov2_with_registers │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_dinov2_with_registers.py │ │ │ ├── distilbert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_distilbert.py │ │ │ │ ├── test_modeling_flax_distilbert.py │ │ │ │ ├── test_modeling_tf_distilbert.py │ │ │ │ └── test_tokenization_distilbert.py │ │ │ ├── dit │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_dit.py │ │ │ ├── donut │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_donut.py │ │ │ │ ├── test_modeling_donut_swin.py │ │ │ │ └── test_processor_donut.py │ │ │ ├── dpr │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_dpr.py │ │ │ │ ├── test_modeling_tf_dpr.py │ │ │ │ └── test_tokenization_dpr.py │ │ │ ├── dpt │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_dpt.py │ │ │ │ ├── test_modeling_dpt.py │ │ │ │ ├── test_modeling_dpt_auto_backbone.py │ │ │ │ └── test_modeling_dpt_hybrid.py │ │ │ ├── efficientnet │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_efficientnet.py │ │ │ │ └── test_modeling_efficientnet.py │ │ │ ├── electra │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_electra.py │ │ │ │ ├── test_modeling_flax_electra.py │ │ │ │ ├── test_modeling_tf_electra.py │ │ │ │ └── test_tokenization_electra.py │ │ │ ├── emu3 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_emu3.py │ │ │ │ └── test_processor_emu3.py │ │ │ ├── encodec │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_encodec.py │ │ │ │ └── test_modeling_encodec.py │ │ │ ├── encoder_decoder │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_encoder_decoder.py │ │ │ │ ├── test_modeling_flax_encoder_decoder.py │ │ │ │ └── test_modeling_tf_encoder_decoder.py │ │ │ ├── ernie │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_ernie.py │ │ │ ├── esm │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_esm.py │ │ │ │ ├── test_modeling_esmfold.py │ │ │ │ ├── test_modeling_tf_esm.py │ │ │ │ └── test_tokenization_esm.py │ │ │ ├── falcon │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_falcon.py │ │ │ ├── falcon_mamba │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_falcon_mamba.py │ │ │ ├── fastspeech2_conformer │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_fastspeech2_conformer.py │ │ │ │ └── test_tokenization_fastspeech2_conformer.py │ │ │ ├── flaubert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flaubert.py │ │ │ │ ├── test_modeling_tf_flaubert.py │ │ │ │ └── test_tokenization_flaubert.py │ │ │ ├── flava │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_flava.py │ │ │ │ ├── test_modeling_flava.py │ │ │ │ └── test_processor_flava.py │ │ │ ├── fnet │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_fnet.py │ │ │ │ └── test_tokenization_fnet.py │ │ │ ├── focalnet │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_focalnet.py │ │ │ ├── fsmt │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_fsmt.py │ │ │ │ └── test_tokenization_fsmt.py │ │ │ ├── funnel │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_funnel.py │ │ │ │ ├── test_modeling_tf_funnel.py │ │ │ │ └── test_tokenization_funnel.py │ │ │ ├── fuyu │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_fuyu.py │ │ │ │ ├── test_modeling_fuyu.py │ │ │ │ └── test_processor_fuyu.py │ │ │ ├── gemma │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_gemma.py │ │ │ │ ├── test_modeling_gemma.py │ │ │ │ └── test_tokenization_gemma.py │ │ │ ├── gemma2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_gemma2.py │ │ │ ├── gemma3 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_gemma3.py │ │ │ │ ├── test_modeling_gemma3.py │ │ │ │ └── test_processing_gemma3.py │ │ │ ├── git │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_git.py │ │ │ │ └── test_processor_git.py │ │ │ ├── glm │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_glm.py │ │ │ ├── glpn │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_glpn.py │ │ │ │ └── test_modeling_glpn.py │ │ │ ├── got_ocr2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_got_ocr2.py │ │ │ │ ├── test_modeling_got_ocr2.py │ │ │ │ └── test_processor_got_ocr2.py │ │ │ ├── gpt2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_gpt2.py │ │ │ │ ├── test_modeling_gpt2.py │ │ │ │ ├── test_modeling_tf_gpt2.py │ │ │ │ ├── test_tokenization_gpt2.py │ │ │ │ └── test_tokenization_gpt2_tf.py │ │ │ ├── gpt_bigcode │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_gpt_bigcode.py │ │ │ ├── gpt_neo │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_gpt_neo.py │ │ │ │ └── test_modeling_gpt_neo.py │ │ │ ├── gpt_neox │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_gpt_neox.py │ │ │ ├── gpt_neox_japanese │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_gpt_neox_japanese.py │ │ │ │ └── test_tokenization_gpt_neox_japanese.py │ │ │ ├── gpt_sw3 │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_gpt_sw3.py │ │ │ ├── gptj │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_gptj.py │ │ │ │ ├── test_modeling_gptj.py │ │ │ │ └── test_modeling_tf_gptj.py │ │ │ ├── granite │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_granite.py │ │ │ ├── granitemoe │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_granitemoe.py │ │ │ ├── granitemoeshared │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_granitemoeshared.py │ │ │ ├── grounding_dino │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_grounding_dino.py │ │ │ │ ├── test_modeling_grounding_dino.py │ │ │ │ └── test_processor_grounding_dino.py │ │ │ ├── groupvit │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_groupvit.py │ │ │ │ └── test_modeling_tf_groupvit.py │ │ │ ├── helium │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_helium.py │ │ │ ├── herbert │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_herbert.py │ │ │ ├── hiera │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_hiera.py │ │ │ ├── hubert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_hubert.py │ │ │ │ └── test_modeling_tf_hubert.py │ │ │ ├── ibert │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_ibert.py │ │ │ ├── idefics │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_idefics.py │ │ │ │ ├── test_modeling_idefics.py │ │ │ │ ├── test_modeling_tf_idefics.py │ │ │ │ └── test_processor_idefics.py │ │ │ ├── idefics2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_idefics2.py │ │ │ │ ├── test_modeling_idefics2.py │ │ │ │ └── test_processor_idefics2.py │ │ │ ├── idefics3 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_idefics3.py │ │ │ │ ├── test_modeling_idefics3.py │ │ │ │ └── test_processor_idefics3.py │ │ │ ├── ijepa │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_ijepa.py │ │ │ ├── imagegpt │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_imagegpt.py │ │ │ │ └── test_modeling_imagegpt.py │ │ │ ├── informer │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_informer.py │ │ │ ├── instructblip │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_instructblip.py │ │ │ │ └── test_processor_instructblip.py │ │ │ ├── instructblipvideo │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_instrictblipvideo.py │ │ │ │ ├── test_modeling_instructblipvideo.py │ │ │ │ └── test_processor_instructblipvideo.py │ │ │ ├── jamba │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_jamba.py │ │ │ ├── jetmoe │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_jetmoe.py │ │ │ ├── kosmos2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_kosmos2.py │ │ │ │ └── test_processor_kosmos2.py │ │ │ ├── layoutlm │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_layoutlm.py │ │ │ │ ├── test_modeling_tf_layoutlm.py │ │ │ │ └── test_tokenization_layoutlm.py │ │ │ ├── layoutlmv2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_layoutlmv2.py │ │ │ │ ├── test_modeling_layoutlmv2.py │ │ │ │ ├── test_processor_layoutlmv2.py │ │ │ │ └── test_tokenization_layoutlmv2.py │ │ │ ├── layoutlmv3 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_layoutlmv3.py │ │ │ │ ├── test_modeling_layoutlmv3.py │ │ │ │ ├── test_modeling_tf_layoutlmv3.py │ │ │ │ ├── test_processor_layoutlmv3.py │ │ │ │ └── test_tokenization_layoutlmv3.py │ │ │ ├── layoutxlm │ │ │ │ ├── __init__.py │ │ │ │ ├── test_processor_layoutxlm.py │ │ │ │ └── test_tokenization_layoutxlm.py │ │ │ ├── led │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_led.py │ │ │ │ ├── test_modeling_tf_led.py │ │ │ │ └── test_tokenization_led.py │ │ │ ├── levit │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_levit.py │ │ │ │ └── test_modeling_levit.py │ │ │ ├── lilt │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_lilt.py │ │ │ ├── llama │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_llama.py │ │ │ │ ├── test_modeling_llama.py │ │ │ │ └── test_tokenization_llama.py │ │ │ ├── llava │ │ │ │ ├── __init__.py │ │ │ │ ├── test_configuration_llava.py │ │ │ │ ├── test_image_processing_llava.py │ │ │ │ ├── test_modeling_llava.py │ │ │ │ └── test_processor_llava.py │ │ │ ├── llava_next │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_llava_next.py │ │ │ │ ├── test_modeling_llava_next.py │ │ │ │ └── test_processor_llava_next.py │ │ │ ├── llava_next_video │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_llava_next_video.py │ │ │ │ ├── test_modeling_llava_next_video.py │ │ │ │ └── test_processor_llava_next_video.py │ │ │ ├── llava_onevision │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_llava_onevision.py │ │ │ │ ├── test_modeling_llava_onevision.py │ │ │ │ └── test_processor_llava_onevision.py │ │ │ ├── longformer │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_longformer.py │ │ │ │ ├── test_modeling_tf_longformer.py │ │ │ │ └── test_tokenization_longformer.py │ │ │ ├── longt5 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_longt5.py │ │ │ │ └── test_modeling_longt5.py │ │ │ ├── luke │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_luke.py │ │ │ │ └── test_tokenization_luke.py │ │ │ ├── lxmert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_lxmert.py │ │ │ │ ├── test_modeling_tf_lxmert.py │ │ │ │ └── test_tokenization_lxmert.py │ │ │ ├── m2m_100 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_m2m_100.py │ │ │ │ └── test_tokenization_m2m_100.py │ │ │ ├── mamba │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_mamba.py │ │ │ ├── mamba2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_mamba2.py │ │ │ ├── marian │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_marian.py │ │ │ │ ├── test_modeling_marian.py │ │ │ │ ├── test_modeling_tf_marian.py │ │ │ │ └── test_tokenization_marian.py │ │ │ ├── markuplm │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_markuplm.py │ │ │ │ ├── test_modeling_markuplm.py │ │ │ │ ├── test_processor_markuplm.py │ │ │ │ └── test_tokenization_markuplm.py │ │ │ ├── mask2former │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_mask2former.py │ │ │ │ └── test_modeling_mask2former.py │ │ │ ├── maskformer │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_maskformer.py │ │ │ │ ├── test_modeling_maskformer.py │ │ │ │ └── test_modeling_maskformer_swin.py │ │ │ ├── mbart │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_mbart.py │ │ │ │ ├── test_modeling_mbart.py │ │ │ │ ├── test_modeling_tf_mbart.py │ │ │ │ └── test_tokenization_mbart.py │ │ │ ├── mbart50 │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_mbart50.py │ │ │ ├── megatron_bert │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_megatron_bert.py │ │ │ ├── megatron_gpt2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_megatron_gpt2.py │ │ │ ├── mgp_str │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_mgp_str.py │ │ │ │ ├── test_processor_mgp_str.py │ │ │ │ └── test_tokenization_mgp_str.py │ │ │ ├── mimi │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_mimi.py │ │ │ ├── mistral │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_mistral.py │ │ │ │ ├── test_modeling_mistral.py │ │ │ │ └── test_modeling_tf_mistral.py │ │ │ ├── mistral3 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_mistral3.py │ │ │ │ └── test_processor_mistral3.py │ │ │ ├── mixtral │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_mixtral.py │ │ │ ├── mllama │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_mllama.py │ │ │ │ ├── test_modeling_mllama.py │ │ │ │ └── test_processor_mllama.py │ │ │ ├── mluke │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_mluke.py │ │ │ ├── mobilebert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_mobilebert.py │ │ │ │ ├── test_modeling_tf_mobilebert.py │ │ │ │ └── test_tokenization_mobilebert.py │ │ │ ├── mobilenet_v1 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_mobilenet_v1.py │ │ │ │ └── test_modeling_mobilenet_v1.py │ │ │ ├── mobilenet_v2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_mobilenet_v2.py │ │ │ │ └── test_modeling_mobilenet_v2.py │ │ │ ├── mobilevit │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_mobilevit.py │ │ │ │ ├── test_modeling_mobilevit.py │ │ │ │ └── test_modeling_tf_mobilevit.py │ │ │ ├── mobilevitv2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_mobilevitv2.py │ │ │ ├── modernbert │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_modernbert.py │ │ │ ├── moonshine │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_moonshine.py │ │ │ ├── moshi │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_moshi.py │ │ │ │ └── test_tokenization_moshi.py │ │ │ ├── mpnet │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_mpnet.py │ │ │ │ ├── test_modeling_tf_mpnet.py │ │ │ │ └── test_tokenization_mpnet.py │ │ │ ├── mpt │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_mpt.py │ │ │ ├── mra │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_mra.py │ │ │ ├── mt5 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_mt5.py │ │ │ │ ├── test_modeling_mt5.py │ │ │ │ └── test_modeling_tf_mt5.py │ │ │ ├── musicgen │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_musicgen.py │ │ │ │ └── test_processor_musicgen.py │ │ │ ├── musicgen_melody │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_musicgen_melody.py │ │ │ │ ├── test_modeling_musicgen_melody.py │ │ │ │ └── test_processor_musicgen_melody.py │ │ │ ├── mvp │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_mvp.py │ │ │ │ └── test_tokenization_mvp.py │ │ │ ├── myt5 │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_myt5.py │ │ │ ├── nemotron │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_nemotron.py │ │ │ ├── nllb │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_nllb.py │ │ │ ├── nllb_moe │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_nllb_moe.py │ │ │ ├── nougat │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_nougat.py │ │ │ │ └── test_tokenization_nougat.py │ │ │ ├── nystromformer │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_nystromformer.py │ │ │ ├── olmo │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_olmo.py │ │ │ ├── olmo2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_olmo2.py │ │ │ ├── olmoe │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_olmoe.py │ │ │ ├── omdet_turbo │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_omdet_turbo.py │ │ │ │ └── test_processor_omdet_turbo.py │ │ │ ├── oneformer │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_oneformer.py │ │ │ │ ├── test_modeling_oneformer.py │ │ │ │ └── test_processor_oneformer.py │ │ │ ├── openai │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_openai.py │ │ │ │ ├── test_modeling_tf_openai.py │ │ │ │ └── test_tokenization_openai.py │ │ │ ├── opt │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_opt.py │ │ │ │ ├── test_modeling_opt.py │ │ │ │ └── test_modeling_tf_opt.py │ │ │ ├── owlv2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_owlv2.py │ │ │ │ ├── test_modeling_owlv2.py │ │ │ │ └── test_processor_owlv2.py │ │ │ ├── owlvit │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_owlvit.py │ │ │ │ ├── test_modeling_owlvit.py │ │ │ │ └── test_processor_owlvit.py │ │ │ ├── paligemma │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_paligemma.py │ │ │ │ └── test_processor_paligemma.py │ │ │ ├── paligemma2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_paligemma2.py │ │ │ ├── patchtsmixer │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_patchtsmixer.py │ │ │ ├── patchtst │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_patchtst.py │ │ │ ├── pegasus │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_pegasus.py │ │ │ │ ├── test_modeling_pegasus.py │ │ │ │ ├── test_modeling_tf_pegasus.py │ │ │ │ └── test_tokenization_pegasus.py │ │ │ ├── pegasus_x │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_pegasus_x.py │ │ │ ├── perceiver │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_perceiver.py │ │ │ │ └── test_tokenization_perceiver.py │ │ │ ├── persimmon │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_persimmon.py │ │ │ ├── phi │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_phi.py │ │ │ ├── phi3 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_phi3.py │ │ │ ├── phimoe │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_phimoe.py │ │ │ ├── phobert │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_phobert.py │ │ │ ├── pix2struct │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_pix2struct.py │ │ │ │ ├── test_modeling_pix2struct.py │ │ │ │ └── test_processor_pix2struct.py │ │ │ ├── pixtral │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_pixtral.py │ │ │ │ ├── test_modeling_pixtral.py │ │ │ │ └── test_processor_pixtral.py │ │ │ ├── plbart │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_plbart.py │ │ │ │ └── test_tokenization_plbart.py │ │ │ ├── poolformer │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_poolformer.py │ │ │ │ └── test_modeling_poolformer.py │ │ │ ├── pop2piano │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_pop2piano.py │ │ │ │ ├── test_modeling_pop2piano.py │ │ │ │ ├── test_processor_pop2piano.py │ │ │ │ └── test_tokenization_pop2piano.py │ │ │ ├── prophetnet │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_prophetnet.py │ │ │ │ └── test_tokenization_prophetnet.py │ │ │ ├── pvt │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_pvt.py │ │ │ │ └── test_modeling_pvt.py │ │ │ ├── pvt_v2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_pvt_v2.py │ │ │ ├── qwen2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_qwen2.py │ │ │ │ └── test_tokenization_qwen2.py │ │ │ ├── qwen2_5_vl │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_qwen2_5_vl.py │ │ │ │ └── test_processor_qwen2_5_vl.py │ │ │ ├── qwen2_audio │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_qwen2_audio.py │ │ │ │ └── test_processor_qwen2_audio.py │ │ │ ├── qwen2_moe │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_qwen2_moe.py │ │ │ ├── qwen2_vl │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_qwen2_vl.py │ │ │ │ ├── test_modeling_qwen2_vl.py │ │ │ │ └── test_processor_qwen2_vl.py │ │ │ ├── rag │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_rag.py │ │ │ │ ├── test_modeling_tf_rag.py │ │ │ │ ├── test_retrieval_rag.py │ │ │ │ └── test_tokenization_rag.py │ │ │ ├── recurrent_gemma │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_recurrent_gemma.py │ │ │ ├── reformer │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_reformer.py │ │ │ │ └── test_tokenization_reformer.py │ │ │ ├── regnet │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_regnet.py │ │ │ │ ├── test_modeling_regnet.py │ │ │ │ └── test_modeling_tf_regnet.py │ │ │ ├── rembert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_rembert.py │ │ │ │ ├── test_modeling_tf_rembert.py │ │ │ │ └── test_tokenization_rembert.py │ │ │ ├── resnet │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_resnet.py │ │ │ │ ├── test_modeling_resnet.py │ │ │ │ └── test_modeling_tf_resnet.py │ │ │ ├── roberta │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_roberta.py │ │ │ │ ├── test_modeling_roberta.py │ │ │ │ ├── test_modeling_tf_roberta.py │ │ │ │ └── test_tokenization_roberta.py │ │ │ ├── roberta_prelayernorm │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_roberta_prelayernorm.py │ │ │ │ ├── test_modeling_roberta_prelayernorm.py │ │ │ │ └── test_modeling_tf_roberta_prelayernorm.py │ │ │ ├── roc_bert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_roc_bert.py │ │ │ │ └── test_tokenization_roc_bert.py │ │ │ ├── roformer │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_roformer.py │ │ │ │ ├── test_modeling_roformer.py │ │ │ │ ├── test_modeling_tf_roformer.py │ │ │ │ └── test_tokenization_roformer.py │ │ │ ├── rt_detr │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_rt_detr.py │ │ │ │ ├── test_modeling_rt_detr.py │ │ │ │ └── test_modeling_rt_detr_resnet.py │ │ │ ├── rt_detr_v2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_rt_detr_v2.py │ │ │ ├── rwkv │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_rwkv.py │ │ │ ├── sam │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_sam.py │ │ │ │ ├── test_modeling_tf_sam.py │ │ │ │ └── test_processor_sam.py │ │ │ ├── seamless_m4t │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_seamless_m4t.py │ │ │ │ ├── test_modeling_seamless_m4t.py │ │ │ │ ├── test_processor_seamless_m4t.py │ │ │ │ └── test_tokenization_seamless_m4t.py │ │ │ ├── seamless_m4t_v2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_seamless_m4t_v2.py │ │ │ ├── segformer │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_segformer.py │ │ │ │ ├── test_modeling_segformer.py │ │ │ │ └── test_modeling_tf_segformer.py │ │ │ ├── seggpt │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_seggpt.py │ │ │ │ └── test_modeling_seggpt.py │ │ │ ├── sew │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_sew.py │ │ │ ├── sew_d │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_sew_d.py │ │ │ ├── siglip │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_siglip.py │ │ │ │ ├── test_modeling_siglip.py │ │ │ │ └── test_tokenization_siglip.py │ │ │ ├── siglip2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_siglip2.py │ │ │ │ └── test_modeling_siglip2.py │ │ │ ├── smolvlm │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_smolvlm.py │ │ │ │ ├── test_modeling_smolvlm.py │ │ │ │ └── test_processor_smolvlm.py │ │ │ ├── speech_encoder_decoder │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_speech_encoder_decoder.py │ │ │ │ └── test_modeling_speech_encoder_decoder.py │ │ │ ├── speech_to_text │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_speech_to_text.py │ │ │ │ ├── test_modeling_speech_to_text.py │ │ │ │ ├── test_modeling_tf_speech_to_text.py │ │ │ │ ├── test_processor_speech_to_text.py │ │ │ │ └── test_tokenization_speech_to_text.py │ │ │ ├── speecht5 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_speecht5.py │ │ │ │ ├── test_modeling_speecht5.py │ │ │ │ ├── test_processor_speecht5.py │ │ │ │ └── test_tokenization_speecht5.py │ │ │ ├── splinter │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_splinter.py │ │ │ │ └── test_tokenization_splinter.py │ │ │ ├── squeezebert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_squeezebert.py │ │ │ │ └── test_tokenization_squeezebert.py │ │ │ ├── stablelm │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_stablelm.py │ │ │ ├── starcoder2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_starcoder2.py │ │ │ ├── superglue │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_superglue.py │ │ │ │ └── test_modeling_superglue.py │ │ │ ├── superpoint │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_superpoint.py │ │ │ │ └── test_modeling_superpoint.py │ │ │ ├── swiftformer │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_swiftformer.py │ │ │ │ └── test_modeling_tf_swiftformer.py │ │ │ ├── swin │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_swin.py │ │ │ │ └── test_modeling_tf_swin.py │ │ │ ├── swin2sr │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_swin2sr.py │ │ │ │ └── test_modeling_swin2sr.py │ │ │ ├── swinv2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_swinv2.py │ │ │ ├── switch_transformers │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_switch_transformers.py │ │ │ ├── t5 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_t5.py │ │ │ │ ├── test_modeling_t5.py │ │ │ │ ├── test_modeling_tf_t5.py │ │ │ │ └── test_tokenization_t5.py │ │ │ ├── table_transformer │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_table_transformer.py │ │ │ ├── tapas │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_tapas.py │ │ │ │ ├── test_modeling_tf_tapas.py │ │ │ │ └── test_tokenization_tapas.py │ │ │ ├── textnet │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_textnet.py │ │ │ │ └── test_modeling_textnet.py │ │ │ ├── time_series_transformer │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_time_series_transformer.py │ │ │ ├── timesformer │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_timesformer.py │ │ │ ├── timm_backbone │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_timm_backbone.py │ │ │ ├── timm_wrapper │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_timm_wrapper.py │ │ │ │ └── test_modeling_timm_wrapper.py │ │ │ ├── trocr │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_trocr.py │ │ │ │ └── test_processor_trocr.py │ │ │ ├── tvp │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_tvp.py │ │ │ │ └── test_modeling_tvp.py │ │ │ ├── udop │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_udop.py │ │ │ │ ├── test_processor_udop.py │ │ │ │ └── test_tokenization_udop.py │ │ │ ├── umt5 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_umt5.py │ │ │ ├── unispeech │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_unispeech.py │ │ │ ├── unispeech_sat │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_unispeech_sat.py │ │ │ ├── univnet │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_univnet.py │ │ │ │ └── test_modeling_univnet.py │ │ │ ├── upernet │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_upernet.py │ │ │ ├── video_llava │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_video_llava.py │ │ │ │ └── test_modeling_video_llava.py │ │ │ ├── videomae │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_videomae.py │ │ │ │ └── test_modeling_videomae.py │ │ │ ├── vilt │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_vilt.py │ │ │ │ └── test_modeling_vilt.py │ │ │ ├── vipllava │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_vipllava.py │ │ │ │ └── test_processor_vipllava.py │ │ │ ├── vision_encoder_decoder │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_vision_encoder_decoder.py │ │ │ │ ├── test_modeling_tf_vision_encoder_decoder.py │ │ │ │ └── test_modeling_vision_encoder_decoder.py │ │ │ ├── vision_text_dual_encoder │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_vision_text_dual_encoder.py │ │ │ │ ├── test_modeling_tf_vision_text_dual_encoder.py │ │ │ │ ├── test_modeling_vision_text_dual_encoder.py │ │ │ │ └── test_processor_vision_text_dual_encoder.py │ │ │ ├── visual_bert │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_visual_bert.py │ │ │ ├── vit │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_vit.py │ │ │ │ ├── test_modeling_flax_vit.py │ │ │ │ ├── test_modeling_tf_vit.py │ │ │ │ └── test_modeling_vit.py │ │ │ ├── vit_mae │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_tf_vit_mae.py │ │ │ │ └── test_modeling_vit_mae.py │ │ │ ├── vit_msn │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_vit_msn.py │ │ │ ├── vitdet │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_vitdet.py │ │ │ ├── vitmatte │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_vitmatte.py │ │ │ │ └── test_modeling_vitmatte.py │ │ │ ├── vitpose │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_vitpose.py │ │ │ │ └── test_modeling_vitpose.py │ │ │ ├── vitpose_backbone │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_vitpose_backbone.py │ │ │ ├── vits │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_vits.py │ │ │ │ └── test_tokenization_vits.py │ │ │ ├── vivit │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_vivit.py │ │ │ │ └── test_modeling_vivit.py │ │ │ ├── wav2vec2 │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_wav2vec2.py │ │ │ │ ├── test_modeling_flax_wav2vec2.py │ │ │ │ ├── test_modeling_tf_wav2vec2.py │ │ │ │ ├── test_modeling_wav2vec2.py │ │ │ │ ├── test_processor_wav2vec2.py │ │ │ │ └── test_tokenization_wav2vec2.py │ │ │ ├── wav2vec2_bert │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_wav2vec2_bert.py │ │ │ │ └── test_processor_wav2vec2_bert.py │ │ │ ├── wav2vec2_conformer │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_wav2vec2_conformer.py │ │ │ ├── wav2vec2_phoneme │ │ │ │ ├── __init__.py │ │ │ │ └── test_tokenization_wav2vec2_phoneme.py │ │ │ ├── wav2vec2_with_lm │ │ │ │ ├── __init__.py │ │ │ │ └── test_processor_wav2vec2_with_lm.py │ │ │ ├── wavlm │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_wavlm.py │ │ │ ├── whisper │ │ │ │ ├── __init__.py │ │ │ │ ├── test_feature_extraction_whisper.py │ │ │ │ ├── test_modeling_flax_whisper.py │ │ │ │ ├── test_modeling_tf_whisper.py │ │ │ │ ├── test_modeling_whisper.py │ │ │ │ ├── test_processor_whisper.py │ │ │ │ └── test_tokenization_whisper.py │ │ │ ├── x_clip │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_x_clip.py │ │ │ ├── xglm │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_xglm.py │ │ │ │ ├── test_modeling_tf_xglm.py │ │ │ │ ├── test_modeling_xglm.py │ │ │ │ └── test_tokenization_xglm.py │ │ │ ├── xlm │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_tf_xlm.py │ │ │ │ ├── test_modeling_xlm.py │ │ │ │ └── test_tokenization_xlm.py │ │ │ ├── xlm_roberta │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_flax_xlm_roberta.py │ │ │ │ ├── test_modeling_tf_xlm_roberta.py │ │ │ │ ├── test_modeling_xlm_roberta.py │ │ │ │ └── test_tokenization_xlm_roberta.py │ │ │ ├── xlm_roberta_xl │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_xlm_roberta_xl.py │ │ │ ├── xlnet │ │ │ │ ├── __init__.py │ │ │ │ ├── test_modeling_tf_xlnet.py │ │ │ │ ├── test_modeling_xlnet.py │ │ │ │ └── test_tokenization_xlnet.py │ │ │ ├── xmod │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_xmod.py │ │ │ ├── yolos │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_yolos.py │ │ │ │ └── test_modeling_yolos.py │ │ │ ├── yoso │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_yoso.py │ │ │ ├── zamba │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_zamba.py │ │ │ ├── zamba2 │ │ │ │ ├── __init__.py │ │ │ │ └── test_modeling_zamba2.py │ │ │ └── zoedepth │ │ │ │ ├── __init__.py │ │ │ │ ├── test_image_processing_zoedepth.py │ │ │ │ └── test_modeling_zoedepth.py │ │ ├── optimization │ │ │ ├── __init__.py │ │ │ ├── test_optimization.py │ │ │ └── test_optimization_tf.py │ │ ├── peft_integration │ │ │ └── test_peft_integration.py │ │ ├── pipelines │ │ │ ├── __init__.py │ │ │ ├── test_pipelines_audio_classification.py │ │ │ ├── test_pipelines_automatic_speech_recognition.py │ │ │ ├── test_pipelines_common.py │ │ │ ├── test_pipelines_depth_estimation.py │ │ │ ├── test_pipelines_document_question_answering.py │ │ │ ├── test_pipelines_feature_extraction.py │ │ │ ├── test_pipelines_fill_mask.py │ │ │ ├── test_pipelines_image_classification.py │ │ │ ├── test_pipelines_image_feature_extraction.py │ │ │ ├── test_pipelines_image_segmentation.py │ │ │ ├── test_pipelines_image_text_to_text.py │ │ │ ├── test_pipelines_image_to_image.py │ │ │ ├── test_pipelines_image_to_text.py │ │ │ ├── test_pipelines_mask_generation.py │ │ │ ├── test_pipelines_object_detection.py │ │ │ ├── test_pipelines_question_answering.py │ │ │ ├── test_pipelines_summarization.py │ │ │ ├── test_pipelines_table_question_answering.py │ │ │ ├── test_pipelines_text2text_generation.py │ │ │ ├── test_pipelines_text_classification.py │ │ │ ├── test_pipelines_text_generation.py │ │ │ ├── test_pipelines_text_to_audio.py │ │ │ ├── test_pipelines_token_classification.py │ │ │ ├── test_pipelines_translation.py │ │ │ ├── test_pipelines_video_classification.py │ │ │ ├── test_pipelines_visual_question_answering.py │ │ │ ├── test_pipelines_zero_shot.py │ │ │ ├── test_pipelines_zero_shot_audio_classification.py │ │ │ ├── test_pipelines_zero_shot_image_classification.py │ │ │ └── test_pipelines_zero_shot_object_detection.py │ │ ├── quantization │ │ │ ├── aqlm_integration │ │ │ │ ├── __init__.py │ │ │ │ └── test_aqlm.py │ │ │ ├── autoawq │ │ │ │ ├── __init__.py │ │ │ │ └── test_awq.py │ │ │ ├── bitnet_integration │ │ │ │ ├── __init__.py │ │ │ │ └── test_bitnet.py │ │ │ ├── bnb │ │ │ │ ├── README.md │ │ │ │ ├── __init__.py │ │ │ │ ├── test_4bit.py │ │ │ │ └── test_mixed_int8.py │ │ │ ├── compressed_tensors │ │ │ │ ├── __init__.py │ │ │ │ ├── test_compressed_models.py │ │ │ │ └── test_compressed_tensors.py │ │ │ ├── eetq_integration │ │ │ │ ├── __init__.py │ │ │ │ └── test_eetq.py │ │ │ ├── fbgemm_fp8 │ │ │ │ ├── __init__.py │ │ │ │ └── test_fbgemm_fp8.py │ │ │ ├── finegrained_fp8 │ │ │ │ ├── __init__.py │ │ │ │ └── test_fp8.py │ │ │ ├── ggml │ │ │ │ ├── __init__.py │ │ │ │ └── test_ggml.py │ │ │ ├── gptq │ │ │ │ ├── __init__.py │ │ │ │ └── test_gptq.py │ │ │ ├── higgs │ │ │ │ ├── __init__.py │ │ │ │ └── test_higgs.py │ │ │ ├── hqq │ │ │ │ └── test_hqq.py │ │ │ ├── quanto_integration │ │ │ │ ├── __init__.py │ │ │ │ └── test_quanto.py │ │ │ ├── spqr_integration │ │ │ │ ├── __init__.py │ │ │ │ └── test_spqr.py │ │ │ ├── torchao_integration │ │ │ │ ├── __init__.py │ │ │ │ └── test_torchao.py │ │ │ └── vptq_integration │ │ │ │ ├── __init__.py │ │ │ │ └── test_vptq.py │ │ ├── repo_utils │ │ │ ├── modular │ │ │ │ └── test_conversion_order.py │ │ │ ├── test_check_copies.py │ │ │ ├── test_check_docstrings.py │ │ │ ├── test_check_dummies.py │ │ │ ├── test_get_test_info.py │ │ │ └── test_tests_fetcher.py │ │ ├── sagemaker │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── conftest.py │ │ │ ├── scripts │ │ │ │ ├── pytorch │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_ddp.py │ │ │ │ │ └── run_glue_model_parallelism.py │ │ │ │ └── tensorflow │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_tf.py │ │ │ │ │ └── run_tf_dist.py │ │ │ ├── test_multi_node_data_parallel.py │ │ │ ├── test_multi_node_model_parallel.py │ │ │ └── test_single_node_gpu.py │ │ ├── tensor_parallel │ │ │ └── test_tensor_parallel.py │ │ ├── test_backbone_common.py │ │ ├── test_configuration_common.py │ │ ├── test_feature_extraction_common.py │ │ ├── test_image_processing_common.py │ │ ├── test_image_transforms.py │ │ ├── test_modeling_common.py │ │ ├── test_modeling_flax_common.py │ │ ├── test_modeling_tf_common.py │ │ ├── test_pipeline_mixin.py │ │ ├── test_processing_common.py │ │ ├── test_sequence_feature_extraction_common.py │ │ ├── test_tokenization_common.py │ │ ├── test_training_args.py │ │ ├── tokenization │ │ │ ├── __init__.py │ │ │ ├── test_tokenization_fast.py │ │ │ └── test_tokenization_utils.py │ │ ├── trainer │ │ │ ├── __init__.py │ │ │ ├── test_data_collator.py │ │ │ ├── test_trainer.py │ │ │ ├── test_trainer_callback.py │ │ │ ├── test_trainer_distributed.py │ │ │ ├── test_trainer_distributed_loss.py │ │ │ ├── test_trainer_fsdp.py │ │ │ ├── test_trainer_seq2seq.py │ │ │ ├── test_trainer_tpu.py │ │ │ └── test_trainer_utils.py │ │ └── utils │ │ │ ├── __init__.py │ │ │ ├── import_structures │ │ │ ├── failing_export.py │ │ │ ├── import_structure_raw_register.py │ │ │ ├── import_structure_register_with_comments.py │ │ │ └── import_structure_register_with_duplicates.py │ │ │ ├── test_activations.py │ │ │ ├── test_activations_tf.py │ │ │ ├── test_add_new_model_like.py │ │ │ ├── test_audio_utils.py │ │ │ ├── test_backbone_utils.py │ │ │ ├── test_cache_utils.py │ │ │ ├── test_chat_template_utils.py │ │ │ ├── test_cli.py │ │ │ ├── test_configuration_utils.py │ │ │ ├── test_convert_slow_tokenizer.py │ │ │ ├── test_deprecation.py │ │ │ ├── test_doc_samples.py │ │ │ ├── test_dynamic_module_utils.py │ │ │ ├── test_expectations.py │ │ │ ├── test_feature_extraction_utils.py │ │ │ ├── test_file_utils.py │ │ │ ├── test_generic.py │ │ │ ├── test_hf_argparser.py │ │ │ ├── test_hub_utils.py │ │ │ ├── test_image_processing_utils.py │ │ │ ├── test_image_utils.py │ │ │ ├── test_import_structure.py │ │ │ ├── test_import_utils.py │ │ │ ├── test_logging.py │ │ │ ├── test_model_card.py │ │ │ ├── test_model_output.py │ │ │ ├── test_modeling_flax_utils.py │ │ │ ├── test_modeling_rope_utils.py │ │ │ ├── test_modeling_tf_core.py │ │ │ ├── test_modeling_tf_utils.py │ │ │ ├── test_modeling_utils.py │ │ │ ├── test_offline.py │ │ │ ├── test_processing_utils.py │ │ │ ├── test_skip_decorators.py │ │ │ ├── test_tokenization_utils.py │ │ │ ├── test_versions_utils.py │ │ │ └── tiny_model_summary.json │ │ └── utils │ │ ├── add_pipeline_model_mapping_to_test.py │ │ ├── check_bad_commit.py │ │ ├── check_build.py │ │ ├── check_config_attributes.py │ │ ├── check_config_docstrings.py │ │ ├── check_copies.py │ │ ├── check_doc_toc.py │ │ ├── check_docstrings.py │ │ ├── check_doctest_list.py │ │ ├── check_dummies.py │ │ ├── check_inits.py │ │ ├── check_model_tester.py │ │ ├── check_modular_conversion.py │ │ ├── check_repo.py │ │ ├── check_self_hosted_runner.py │ │ ├── check_tf_ops.py │ │ ├── create_dependency_mapping.py │ │ ├── create_dummy_models.py │ │ ├── custom_init_isort.py │ │ ├── deprecate_models.py │ │ ├── download_glue_data.py │ │ ├── extract_warnings.py │ │ ├── get_ci_error_statistics.py │ │ ├── get_github_job_time.py │ │ ├── get_modified_files.py │ │ ├── get_previous_daily_ci.py │ │ ├── get_test_info.py │ │ ├── important_models.txt │ │ ├── models_to_deprecate.py │ │ ├── modular_model_converter.py │ │ ├── not_doctested.txt │ │ ├── notification_service.py │ │ ├── notification_service_doc_tests.py │ │ ├── notification_service_quantization.py │ │ ├── past_ci_versions.py │ │ ├── patch_helper.py │ │ ├── pr_slow_ci_models.py │ │ ├── print_env.py │ │ ├── process_bad_commit_report.py │ │ ├── process_circleci_workflow_test_reports.py │ │ ├── process_test_artifacts.py │ │ ├── release.py │ │ ├── set_cuda_devices_for_ci.py │ │ ├── slow_documentation_tests.txt │ │ ├── sort_auto_mappings.py │ │ ├── split_doctest_jobs.py │ │ ├── split_model_tests.py │ │ ├── test_module │ │ ├── __init__.py │ │ ├── custom_configuration.py │ │ ├── custom_feature_extraction.py │ │ ├── custom_image_processing.py │ │ ├── custom_modeling.py │ │ ├── custom_pipeline.py │ │ ├── custom_processing.py │ │ ├── custom_tokenization.py │ │ └── custom_tokenization_fast.py │ │ ├── tests_fetcher.py │ │ ├── tf_ops │ │ └── onnx.json │ │ ├── update_metadata.py │ │ └── update_tiny_models.py └── stage2 │ ├── package │ └── trl │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-310.pyc │ │ ├── cli.cpython-310.pyc │ │ ├── core.cpython-310.pyc │ │ ├── data_utils.cpython-310.pyc │ │ ├── import_utils.cpython-310.pyc │ │ └── mergekit_utils.cpython-310.pyc │ │ ├── cli.py │ │ ├── core.py │ │ ├── data_utils.py │ │ ├── environment │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ └── base_environment.cpython-310.pyc │ │ └── base_environment.py │ │ ├── extras │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ ├── best_of_n_sampler.cpython-310.pyc │ │ │ ├── dataset_formatting.cpython-310.pyc │ │ │ ├── profiling.cpython-310.pyc │ │ │ └── vllm_client.cpython-310.pyc │ │ ├── best_of_n_sampler.py │ │ ├── dataset_formatting.py │ │ ├── profiling.py │ │ └── vllm_client.py │ │ ├── import_utils.py │ │ ├── mergekit_utils.py │ │ ├── models │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ ├── auxiliary_modules.cpython-310.pyc │ │ │ ├── modeling_base.cpython-310.pyc │ │ │ ├── modeling_sd_base.cpython-310.pyc │ │ │ ├── modeling_value_head.cpython-310.pyc │ │ │ ├── sd_utils.cpython-310.pyc │ │ │ └── utils.cpython-310.pyc │ │ ├── auxiliary_modules.py │ │ ├── modeling_base.py │ │ ├── modeling_sd_base.py │ │ ├── modeling_value_head.py │ │ ├── sd_utils.py │ │ └── utils.py │ │ ├── scripts │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ ├── chat.cpython-310.pyc │ │ │ ├── dpo.cpython-310.pyc │ │ │ ├── env.cpython-310.pyc │ │ │ ├── grpo.cpython-310.pyc │ │ │ ├── kto.cpython-310.pyc │ │ │ ├── sft.cpython-310.pyc │ │ │ ├── utils.cpython-310.pyc │ │ │ └── vllm_serve.cpython-310.pyc │ │ ├── chat.py │ │ ├── dpo.py │ │ ├── env.py │ │ ├── grpo.py │ │ ├── kto.py │ │ ├── sft.py │ │ ├── utils.py │ │ └── vllm_serve.py │ │ ├── templates │ │ └── lm_model_card.md │ │ └── trainer │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-310.pyc │ │ ├── alignprop_config.cpython-310.pyc │ │ ├── alignprop_trainer.cpython-310.pyc │ │ ├── bco_config.cpython-310.pyc │ │ ├── bco_trainer.cpython-310.pyc │ │ ├── callbacks.cpython-310.pyc │ │ ├── cpo_config.cpython-310.pyc │ │ ├── cpo_trainer.cpython-310.pyc │ │ ├── ddpo_config.cpython-310.pyc │ │ ├── ddpo_trainer.cpython-310.pyc │ │ ├── dpo_config.cpython-310.pyc │ │ ├── dpo_trainer.cpython-310.pyc │ │ ├── gkd_config.cpython-310.pyc │ │ ├── gkd_trainer.cpython-310.pyc │ │ ├── grpo_config.cpython-310.pyc │ │ ├── grpo_trainer.cpython-310.pyc │ │ ├── iterative_sft_trainer.cpython-310.pyc │ │ ├── judges.cpython-310.pyc │ │ ├── kto_config.cpython-310.pyc │ │ ├── kto_trainer.cpython-310.pyc │ │ ├── model_config.cpython-310.pyc │ │ ├── nash_md_config.cpython-310.pyc │ │ ├── nash_md_trainer.cpython-310.pyc │ │ ├── online_dpo_config.cpython-310.pyc │ │ ├── online_dpo_trainer.cpython-310.pyc │ │ ├── orpo_config.cpython-310.pyc │ │ ├── orpo_trainer.cpython-310.pyc │ │ ├── ppo_config.cpython-310.pyc │ │ ├── ppo_trainer.cpython-310.pyc │ │ ├── prm_config.cpython-310.pyc │ │ ├── prm_trainer.cpython-310.pyc │ │ ├── reward_config.cpython-310.pyc │ │ ├── reward_trainer.cpython-310.pyc │ │ ├── rloo_config.cpython-310.pyc │ │ ├── rloo_trainer.cpython-310.pyc │ │ ├── sft_config.cpython-310.pyc │ │ ├── sft_trainer.cpython-310.pyc │ │ ├── utils.cpython-310.pyc │ │ ├── xpo_config.cpython-310.pyc │ │ └── xpo_trainer.cpython-310.pyc │ │ ├── alignprop_config.py │ │ ├── alignprop_trainer.py │ │ ├── bco_config.py │ │ ├── bco_trainer.py │ │ ├── callbacks.py │ │ ├── cpo_config.py │ │ ├── cpo_trainer.py │ │ ├── ddpo_config.py │ │ ├── ddpo_trainer.py │ │ ├── dpo_config.py │ │ ├── dpo_trainer.py │ │ ├── gkd_config.py │ │ ├── gkd_trainer.py │ │ ├── grpo_config.py │ │ ├── grpo_trainer.py │ │ ├── iterative_sft_trainer.py │ │ ├── judges.py │ │ ├── kto_config.py │ │ ├── kto_trainer.py │ │ ├── model_config.py │ │ ├── nash_md_config.py │ │ ├── nash_md_trainer.py │ │ ├── online_dpo_config.py │ │ ├── online_dpo_trainer.py │ │ ├── orpo_config.py │ │ ├── orpo_trainer.py │ │ ├── ppo_config.py │ │ ├── ppo_trainer.py │ │ ├── prm_config.py │ │ ├── prm_trainer.py │ │ ├── reward_config.py │ │ ├── reward_trainer.py │ │ ├── rloo_config.py │ │ ├── rloo_trainer.py │ │ ├── sft_config.py │ │ ├── sft_trainer.py │ │ ├── utils.py │ │ ├── xpo_config.py │ │ └── xpo_trainer.py │ ├── run_scripts │ ├── multinode_training_args.yaml │ ├── multinode_training_demo.sh │ └── train.sh │ ├── setup.sh │ └── src │ └── open-r1-multimodal │ ├── .gitignore │ ├── Makefile │ ├── configs │ ├── ddp.yaml │ ├── zero2.yaml │ └── zero3.yaml │ ├── local_scripts │ ├── zero2.json │ ├── zero3.json │ ├── zero3.yaml │ ├── zero3_offload.json │ └── zero_stage2_config.json │ ├── setup.cfg │ ├── setup.py │ └── src │ └── open_r1 │ ├── __init__.py │ ├── configs.py │ ├── evaluate.py │ ├── generate.py │ ├── grpo.py │ ├── grpo_jsonl.py │ ├── qwen2_5vl_monkey_patch.py │ ├── sft.py │ ├── trainer │ ├── __init__.py │ ├── grpo_config.py │ ├── grpo_trainer.py │ ├── record.py │ └── vllm_grpo_trainer.py │ ├── utils │ ├── __init__.py │ ├── callbacks.py │ ├── evaluation.py │ ├── hub.py │ ├── math.py │ └── pycocotools │ │ ├── coco.py │ │ └── cocoeval.py │ └── vlm_modules │ ├── __init__.py │ ├── internvl_module.py │ ├── qwen_module.py │ └── vlm_module.py ├── CODE_OF_CONDUCT.md ├── LICENSE ├── README.md ├── SFT ├── env │ ├── .env.local │ ├── README.md │ ├── pyproject.toml │ ├── requirements.txt │ ├── setup.py │ └── src │ │ ├── api.py │ │ ├── llamafactory │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ ├── __init__.cpython-311.pyc │ │ │ ├── cli.cpython-310.pyc │ │ │ ├── cli.cpython-311.pyc │ │ │ ├── launcher.cpython-310.pyc │ │ │ └── launcher.cpython-311.pyc │ │ ├── api │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ ├── app.cpython-310.pyc │ │ │ │ ├── app.cpython-311.pyc │ │ │ │ ├── chat.cpython-310.pyc │ │ │ │ ├── chat.cpython-311.pyc │ │ │ │ ├── common.cpython-310.pyc │ │ │ │ ├── common.cpython-311.pyc │ │ │ │ ├── protocol.cpython-310.pyc │ │ │ │ └── protocol.cpython-311.pyc │ │ │ ├── app.py │ │ │ ├── chat.py │ │ │ ├── common.py │ │ │ └── protocol.py │ │ ├── chat │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ ├── base_engine.cpython-310.pyc │ │ │ │ ├── base_engine.cpython-311.pyc │ │ │ │ ├── chat_model.cpython-310.pyc │ │ │ │ ├── chat_model.cpython-311.pyc │ │ │ │ ├── hf_engine.cpython-310.pyc │ │ │ │ ├── hf_engine.cpython-311.pyc │ │ │ │ ├── sglang_engine.cpython-310.pyc │ │ │ │ ├── sglang_engine.cpython-311.pyc │ │ │ │ ├── vllm_engine.cpython-310.pyc │ │ │ │ └── vllm_engine.cpython-311.pyc │ │ │ ├── base_engine.py │ │ │ ├── chat_model.py │ │ │ ├── hf_engine.py │ │ │ ├── sglang_engine.py │ │ │ └── vllm_engine.py │ │ ├── cli.py │ │ ├── data │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ ├── collator.cpython-310.pyc │ │ │ │ ├── collator.cpython-311.pyc │ │ │ │ ├── converter.cpython-310.pyc │ │ │ │ ├── converter.cpython-311.pyc │ │ │ │ ├── data_utils.cpython-310.pyc │ │ │ │ ├── data_utils.cpython-311.pyc │ │ │ │ ├── formatter.cpython-310.pyc │ │ │ │ ├── formatter.cpython-311.pyc │ │ │ │ ├── loader.cpython-310.pyc │ │ │ │ ├── loader.cpython-311.pyc │ │ │ │ ├── mm_plugin.cpython-310.pyc │ │ │ │ ├── mm_plugin.cpython-311.pyc │ │ │ │ ├── parser.cpython-310.pyc │ │ │ │ ├── parser.cpython-311.pyc │ │ │ │ ├── template.cpython-310.pyc │ │ │ │ ├── template.cpython-311.pyc │ │ │ │ ├── tool_utils.cpython-310.pyc │ │ │ │ └── tool_utils.cpython-311.pyc │ │ │ ├── collator.py │ │ │ ├── converter.py │ │ │ ├── data_utils.py │ │ │ ├── formatter.py │ │ │ ├── loader.py │ │ │ ├── mm_plugin.py │ │ │ ├── parser.py │ │ │ ├── processor │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ │ ├── feedback.cpython-310.pyc │ │ │ │ │ ├── feedback.cpython-311.pyc │ │ │ │ │ ├── pairwise.cpython-310.pyc │ │ │ │ │ ├── pairwise.cpython-311.pyc │ │ │ │ │ ├── pretrain.cpython-310.pyc │ │ │ │ │ ├── pretrain.cpython-311.pyc │ │ │ │ │ ├── processor_utils.cpython-310.pyc │ │ │ │ │ ├── processor_utils.cpython-311.pyc │ │ │ │ │ ├── supervised.cpython-310.pyc │ │ │ │ │ ├── supervised.cpython-311.pyc │ │ │ │ │ ├── unsupervised.cpython-310.pyc │ │ │ │ │ └── unsupervised.cpython-311.pyc │ │ │ │ ├── feedback.py │ │ │ │ ├── pairwise.py │ │ │ │ ├── pretrain.py │ │ │ │ ├── processor_utils.py │ │ │ │ ├── supervised.py │ │ │ │ └── unsupervised.py │ │ │ ├── template.py │ │ │ └── tool_utils.py │ │ ├── eval │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ ├── evaluator.cpython-310.pyc │ │ │ │ ├── evaluator.cpython-311.pyc │ │ │ │ ├── template.cpython-310.pyc │ │ │ │ └── template.cpython-311.pyc │ │ │ ├── evaluator.py │ │ │ └── template.py │ │ ├── extras │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ ├── constants.cpython-310.pyc │ │ │ │ ├── constants.cpython-311.pyc │ │ │ │ ├── env.cpython-310.pyc │ │ │ │ ├── env.cpython-311.pyc │ │ │ │ ├── logging.cpython-310.pyc │ │ │ │ ├── logging.cpython-311.pyc │ │ │ │ ├── misc.cpython-310.pyc │ │ │ │ ├── misc.cpython-311.pyc │ │ │ │ ├── packages.cpython-310.pyc │ │ │ │ ├── packages.cpython-311.pyc │ │ │ │ ├── ploting.cpython-310.pyc │ │ │ │ └── ploting.cpython-311.pyc │ │ │ ├── constants.py │ │ │ ├── env.py │ │ │ ├── logging.py │ │ │ ├── misc.py │ │ │ ├── packages.py │ │ │ └── ploting.py │ │ ├── hparams │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ ├── data_args.cpython-310.pyc │ │ │ │ ├── data_args.cpython-311.pyc │ │ │ │ ├── evaluation_args.cpython-310.pyc │ │ │ │ ├── evaluation_args.cpython-311.pyc │ │ │ │ ├── finetuning_args.cpython-310.pyc │ │ │ │ ├── finetuning_args.cpython-311.pyc │ │ │ │ ├── generating_args.cpython-310.pyc │ │ │ │ ├── generating_args.cpython-311.pyc │ │ │ │ ├── model_args.cpython-310.pyc │ │ │ │ ├── model_args.cpython-311.pyc │ │ │ │ ├── parser.cpython-310.pyc │ │ │ │ ├── parser.cpython-311.pyc │ │ │ │ ├── training_args.cpython-310.pyc │ │ │ │ └── training_args.cpython-311.pyc │ │ │ ├── data_args.py │ │ │ ├── evaluation_args.py │ │ │ ├── finetuning_args.py │ │ │ ├── generating_args.py │ │ │ ├── model_args.py │ │ │ ├── parser.py │ │ │ └── training_args.py │ │ ├── launcher.py │ │ ├── model │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ ├── adapter.cpython-310.pyc │ │ │ │ ├── adapter.cpython-311.pyc │ │ │ │ ├── loader.cpython-310.pyc │ │ │ │ ├── loader.cpython-311.pyc │ │ │ │ ├── patcher.cpython-310.pyc │ │ │ │ └── patcher.cpython-311.pyc │ │ │ ├── adapter.py │ │ │ ├── loader.py │ │ │ ├── model_utils │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ │ ├── attention.cpython-310.pyc │ │ │ │ │ ├── attention.cpython-311.pyc │ │ │ │ │ ├── checkpointing.cpython-310.pyc │ │ │ │ │ ├── checkpointing.cpython-311.pyc │ │ │ │ │ ├── embedding.cpython-310.pyc │ │ │ │ │ ├── embedding.cpython-311.pyc │ │ │ │ │ ├── kv_cache.cpython-310.pyc │ │ │ │ │ ├── kv_cache.cpython-311.pyc │ │ │ │ │ ├── liger_kernel.cpython-310.pyc │ │ │ │ │ ├── liger_kernel.cpython-311.pyc │ │ │ │ │ ├── longlora.cpython-310.pyc │ │ │ │ │ ├── longlora.cpython-311.pyc │ │ │ │ │ ├── misc.cpython-310.pyc │ │ │ │ │ ├── misc.cpython-311.pyc │ │ │ │ │ ├── mod.cpython-310.pyc │ │ │ │ │ ├── mod.cpython-311.pyc │ │ │ │ │ ├── moe.cpython-310.pyc │ │ │ │ │ ├── moe.cpython-311.pyc │ │ │ │ │ ├── packing.cpython-310.pyc │ │ │ │ │ ├── packing.cpython-311.pyc │ │ │ │ │ ├── quantization.cpython-310.pyc │ │ │ │ │ ├── quantization.cpython-311.pyc │ │ │ │ │ ├── rope.cpython-310.pyc │ │ │ │ │ ├── rope.cpython-311.pyc │ │ │ │ │ ├── unsloth.cpython-310.pyc │ │ │ │ │ ├── unsloth.cpython-311.pyc │ │ │ │ │ ├── valuehead.cpython-310.pyc │ │ │ │ │ ├── valuehead.cpython-311.pyc │ │ │ │ │ ├── visual.cpython-310.pyc │ │ │ │ │ └── visual.cpython-311.pyc │ │ │ │ ├── attention.py │ │ │ │ ├── checkpointing.py │ │ │ │ ├── embedding.py │ │ │ │ ├── kv_cache.py │ │ │ │ ├── liger_kernel.py │ │ │ │ ├── longlora.py │ │ │ │ ├── misc.py │ │ │ │ ├── mod.py │ │ │ │ ├── moe.py │ │ │ │ ├── packing.py │ │ │ │ ├── quantization.py │ │ │ │ ├── rope.py │ │ │ │ ├── unsloth.py │ │ │ │ ├── valuehead.py │ │ │ │ └── visual.py │ │ │ └── patcher.py │ │ ├── train │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ ├── callbacks.cpython-310.pyc │ │ │ │ ├── callbacks.cpython-311.pyc │ │ │ │ ├── trainer_utils.cpython-310.pyc │ │ │ │ ├── trainer_utils.cpython-311.pyc │ │ │ │ ├── tuner.cpython-310.pyc │ │ │ │ └── tuner.cpython-311.pyc │ │ │ ├── callbacks.py │ │ │ ├── dpo │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ │ ├── trainer.cpython-310.pyc │ │ │ │ │ ├── trainer.cpython-311.pyc │ │ │ │ │ ├── workflow.cpython-310.pyc │ │ │ │ │ └── workflow.cpython-311.pyc │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── kto │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ │ ├── trainer.cpython-310.pyc │ │ │ │ │ ├── trainer.cpython-311.pyc │ │ │ │ │ ├── workflow.cpython-310.pyc │ │ │ │ │ └── workflow.cpython-311.pyc │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── ppo │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ │ ├── ppo_utils.cpython-310.pyc │ │ │ │ │ ├── ppo_utils.cpython-311.pyc │ │ │ │ │ ├── trainer.cpython-310.pyc │ │ │ │ │ ├── trainer.cpython-311.pyc │ │ │ │ │ ├── workflow.cpython-310.pyc │ │ │ │ │ └── workflow.cpython-311.pyc │ │ │ │ ├── ppo_utils.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── pt │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ │ ├── trainer.cpython-310.pyc │ │ │ │ │ ├── trainer.cpython-311.pyc │ │ │ │ │ ├── workflow.cpython-310.pyc │ │ │ │ │ └── workflow.cpython-311.pyc │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── rm │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ │ ├── metric.cpython-310.pyc │ │ │ │ │ ├── metric.cpython-311.pyc │ │ │ │ │ ├── trainer.cpython-310.pyc │ │ │ │ │ ├── trainer.cpython-311.pyc │ │ │ │ │ ├── workflow.cpython-310.pyc │ │ │ │ │ └── workflow.cpython-311.pyc │ │ │ │ ├── metric.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── sft │ │ │ │ ├── __init__.py │ │ │ │ ├── __pycache__ │ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ │ ├── metric.cpython-310.pyc │ │ │ │ │ ├── metric.cpython-311.pyc │ │ │ │ │ ├── trainer.cpython-310.pyc │ │ │ │ │ ├── trainer.cpython-311.pyc │ │ │ │ │ ├── workflow.cpython-310.pyc │ │ │ │ │ └── workflow.cpython-311.pyc │ │ │ │ ├── metric.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── test_utils.py │ │ │ ├── trainer_utils.py │ │ │ └── tuner.py │ │ └── webui │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ ├── __init__.cpython-311.pyc │ │ │ ├── chatter.cpython-310.pyc │ │ │ ├── chatter.cpython-311.pyc │ │ │ ├── common.cpython-310.pyc │ │ │ ├── common.cpython-311.pyc │ │ │ ├── control.cpython-310.pyc │ │ │ ├── control.cpython-311.pyc │ │ │ ├── css.cpython-310.pyc │ │ │ ├── css.cpython-311.pyc │ │ │ ├── engine.cpython-310.pyc │ │ │ ├── engine.cpython-311.pyc │ │ │ ├── interface.cpython-310.pyc │ │ │ ├── interface.cpython-311.pyc │ │ │ ├── locales.cpython-310.pyc │ │ │ ├── locales.cpython-311.pyc │ │ │ ├── manager.cpython-310.pyc │ │ │ ├── manager.cpython-311.pyc │ │ │ ├── runner.cpython-310.pyc │ │ │ └── runner.cpython-311.pyc │ │ │ ├── chatter.py │ │ │ ├── common.py │ │ │ ├── components │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── __init__.cpython-311.pyc │ │ │ │ ├── chatbot.cpython-310.pyc │ │ │ │ ├── chatbot.cpython-311.pyc │ │ │ │ ├── data.cpython-310.pyc │ │ │ │ ├── data.cpython-311.pyc │ │ │ │ ├── eval.cpython-310.pyc │ │ │ │ ├── eval.cpython-311.pyc │ │ │ │ ├── export.cpython-310.pyc │ │ │ │ ├── export.cpython-311.pyc │ │ │ │ ├── infer.cpython-310.pyc │ │ │ │ ├── infer.cpython-311.pyc │ │ │ │ ├── top.cpython-310.pyc │ │ │ │ ├── top.cpython-311.pyc │ │ │ │ ├── train.cpython-310.pyc │ │ │ │ └── train.cpython-311.pyc │ │ │ ├── chatbot.py │ │ │ ├── data.py │ │ │ ├── eval.py │ │ │ ├── export.py │ │ │ ├── infer.py │ │ │ ├── top.py │ │ │ └── train.py │ │ │ ├── control.py │ │ │ ├── css.py │ │ │ ├── engine.py │ │ │ ├── interface.py │ │ │ ├── locales.py │ │ │ ├── manager.py │ │ │ └── runner.py │ │ ├── train.py │ │ └── webui.py └── train_sft.yaml ├── assets └── teaser.png ├── data ├── MindCube_tinybench_raw_qa_work-3dthinker-qwen2.5-vl-3b-instruct_begin_align_vggt_mlp6_lr1e-4_latent12_flash_74000_best_responses.jsonl ├── data_output3d_begin_10k_resized.jsonl └── idx.jsonl ├── envs ├── requirements_sft.txt ├── requirements_stage1.txt └── requirements_stage2.txt ├── eval ├── eval_close_source.py ├── eval_internvl.py ├── eval_llava.py ├── eval_mindcube.sh ├── eval_qwen3.py ├── get_result.sh ├── scripts │ ├── run_evaluation.py │ └── run_inference_clean.py └── src │ ├── __init__.py │ ├── __pycache__ │ └── __init__.cpython-310.pyc │ ├── evaluation │ ├── __init__.py │ ├── cli.py │ ├── cogmap │ │ ├── __init__.py │ │ ├── cogmap_evaluator.py │ │ ├── cogmap_metrics.py │ │ └── graph_operations.py │ ├── core │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ ├── base_metrics.cpython-310.pyc │ │ │ ├── extractors.cpython-310.pyc │ │ │ └── io_utils.cpython-310.pyc │ │ ├── base_metrics.py │ │ ├── extractors.py │ │ ├── io_utils.py │ │ └── mindcube_eval.py │ └── evaluator.py │ ├── inference │ ├── __init__.py │ ├── base.py │ ├── closed_source.py │ ├── engines │ │ ├── __init__.py │ │ └── qwen_engine.py │ ├── open_source.py │ └── utils.py │ ├── inference_mindcube │ ├── __init__.py │ ├── base.py │ ├── closed_source.py │ ├── open_source.py │ └── utils.py │ └── utils │ ├── __init__.py │ ├── io_utils.py │ ├── spatial_utils.py │ └── text_utils.py ├── preprocessing ├── clean.py ├── feature │ ├── extract_vggt_feature.py │ └── vggt │ │ ├── dependency │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ ├── distortion.cpython-310.pyc │ │ │ ├── np_to_pycolmap.cpython-310.pyc │ │ │ ├── projection.cpython-310.pyc │ │ │ ├── track_predict.cpython-310.pyc │ │ │ ├── vggsfm_tracker.cpython-310.pyc │ │ │ └── vggsfm_utils.cpython-310.pyc │ │ ├── distortion.py │ │ ├── np_to_pycolmap.py │ │ ├── projection.py │ │ ├── track_modules │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── base_track_predictor.cpython-310.pyc │ │ │ │ ├── blocks.cpython-310.pyc │ │ │ │ ├── modules.cpython-310.pyc │ │ │ │ ├── track_refine.cpython-310.pyc │ │ │ │ └── utils.cpython-310.pyc │ │ │ ├── base_track_predictor.py │ │ │ ├── blocks.py │ │ │ ├── modules.py │ │ │ ├── track_refine.py │ │ │ └── utils.py │ │ ├── track_predict.py │ │ ├── vggsfm_tracker.py │ │ └── vggsfm_utils.py │ │ ├── heads │ │ ├── __pycache__ │ │ │ ├── camera_head.cpython-310.pyc │ │ │ ├── dpt_head.cpython-310.pyc │ │ │ ├── head_act.cpython-310.pyc │ │ │ ├── track_head.cpython-310.pyc │ │ │ └── utils.cpython-310.pyc │ │ ├── camera_head.py │ │ ├── dpt_head.py │ │ ├── head_act.py │ │ ├── track_head.py │ │ ├── track_modules │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ │ ├── __init__.cpython-310.pyc │ │ │ │ ├── base_track_predictor.cpython-310.pyc │ │ │ │ ├── blocks.cpython-310.pyc │ │ │ │ ├── modules.cpython-310.pyc │ │ │ │ └── utils.cpython-310.pyc │ │ │ ├── base_track_predictor.py │ │ │ ├── blocks.py │ │ │ ├── modules.py │ │ │ └── utils.py │ │ └── utils.py │ │ ├── layers │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-310.pyc │ │ │ ├── attention.cpython-310.pyc │ │ │ ├── block.cpython-310.pyc │ │ │ ├── drop_path.cpython-310.pyc │ │ │ ├── layer_scale.cpython-310.pyc │ │ │ ├── mlp.cpython-310.pyc │ │ │ ├── patch_embed.cpython-310.pyc │ │ │ ├── rope.cpython-310.pyc │ │ │ ├── swiglu_ffn.cpython-310.pyc │ │ │ └── vision_transformer.cpython-310.pyc │ │ ├── attention.py │ │ ├── block.py │ │ ├── drop_path.py │ │ ├── layer_scale.py │ │ ├── mlp.py │ │ ├── patch_embed.py │ │ ├── rope.py │ │ ├── swiglu_ffn.py │ │ └── vision_transformer.py │ │ ├── models │ │ ├── __pycache__ │ │ │ ├── aggregator.cpython-310.pyc │ │ │ └── vggt.cpython-310.pyc │ │ ├── aggregator.py │ │ └── vggt.py │ │ └── utils │ │ ├── __pycache__ │ │ ├── geometry.cpython-310.pyc │ │ ├── helper.cpython-310.pyc │ │ ├── load_fn.cpython-310.pyc │ │ ├── pose_enc.cpython-310.pyc │ │ └── rotation.cpython-310.pyc │ │ ├── geometry.py │ │ ├── helper.py │ │ ├── load_fn.py │ │ ├── pose_enc.py │ │ ├── rotation.py │ │ └── visual_track.py ├── jsonl_add_idx.py ├── produce_cot.py └── remove.py └── tests ├── infer.py └── visual_decoder.py /3dthinker/stage1/deepspeed_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/deepspeed_config.json -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/.github/workflows/codeQL.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/.github/workflows/codeQL.yml -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/.github/workflows/tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/.github/workflows/tests.yml -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/.gitignore -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/.pre-commit-config.yaml -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/CITATION.cff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/CITATION.cff -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/CONTRIBUTING.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/LICENSE -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/MANIFEST.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/MANIFEST.in -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/Makefile -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/README.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/RELEASE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/RELEASE.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/VERSION: -------------------------------------------------------------------------------- 1 | 0.23.0.dev0 -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/commands/run_dpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/commands/run_dpo.sh -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/commands/run_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/commands/run_sft.sh -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/_toctree.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/_toctree.yml -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/bco_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/bco_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/best_of_n.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/best_of_n.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/callbacks.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/callbacks.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/clis.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/clis.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/cpo_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/cpo_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/customization.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/customization.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/data_utils.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/data_utils.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/ddpo_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/ddpo_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/dpo_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/dpo_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/gkd_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/gkd_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/grpo_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/grpo_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/how_to_train.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/how_to_train.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/index.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/installation.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/installation.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/jobs_training.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/jobs_training.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/judges.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/judges.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/kto_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/kto_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/logging.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/logging.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/model_utils.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/model_utils.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/models.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/models.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/orpo_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/orpo_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/others.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/others.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/paper_index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/paper_index.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/ppo_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/ppo_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/prm_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/prm_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/quickstart.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/quickstart.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/rewards.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/rewards.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/rloo_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/rloo_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/script_utils.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/script_utils.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/sft_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/sft_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/use_model.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/use_model.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/docs/source/xpo_trainer.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/docs/source/xpo_trainer.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/README.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/datasets/prm800k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/datasets/prm800k.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/datasets/rlaif-v.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/datasets/rlaif-v.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/datasets/tldr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/datasets/tldr.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/notebooks/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/notebooks/README.md -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/bco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/bco.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/cpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/cpo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/ddpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/ddpo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/dpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/dpo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/dpo_vlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/dpo_vlm.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/gkd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/gkd.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/grpo_vlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/grpo_vlm.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/gspo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/gspo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/gspo_vlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/gspo_vlm.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/kto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/kto.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/mpo_vlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/mpo_vlm.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/nash_md.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/nash_md.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/orpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/orpo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/ppo/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/ppo/ppo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/prm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/prm.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/rloo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/rloo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/sft.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/sft_vlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/sft_vlm.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/examples/scripts/xpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/examples/scripts/xpo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/pyproject.toml -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/requirements.txt -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/scripts/add_copyrights.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/scripts/add_copyrights.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/scripts/log_reports.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/scripts/log_reports.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/setup.cfg -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/setup.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/data/template.jinja: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/data/template.jinja -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/slow/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/slow/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/slow/test_dpo_slow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/slow/test_dpo_slow.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/slow/test_grpo_slow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/slow/test_grpo_slow.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/slow/test_sft_slow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/slow/test_sft_slow.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_bco_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_bco_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_callbacks.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_cli.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_cli_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_cli_utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_collators.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_collators.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_core.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_cpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_cpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_data_utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_ddpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_ddpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_dpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_dpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_gkd_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_gkd_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_grpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_grpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_judges.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_judges.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_kto_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_kto_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_orpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_orpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_peft_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_peft_models.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_ppo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_ppo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_prm_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_prm_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_reward_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_reward_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_rewards.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_rewards.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_rloo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_rloo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_sft_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_trainers_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_trainers_args.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/test_xpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/test_xpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/testing_constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/testing_constants.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/tests/testing_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/tests/testing_utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/cli.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/core.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/data_utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/extras/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/extras/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/extras/profiling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/extras/profiling.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/extras/vllm_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/extras/vllm_client.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/import_utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/mergekit_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/mergekit_utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/models/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/models/modeling_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/models/modeling_base.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/models/sd_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/models/sd_utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/models/utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/py.typed: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/rewards/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/rewards/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/rewards/other_rewards.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/rewards/other_rewards.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/scripts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/scripts/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/scripts/dpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/scripts/dpo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/scripts/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/scripts/env.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/scripts/grpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/scripts/grpo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/scripts/kto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/scripts/kto.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/scripts/rloo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/scripts/rloo.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/scripts/sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/scripts/sft.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/scripts/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/scripts/utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/scripts/vllm_serve.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/scripts/vllm_serve.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/bco_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/bco_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/bco_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/bco_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/callbacks.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/cpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/cpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/cpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/cpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/ddpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/ddpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/ddpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/ddpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/dpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/dpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/dpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/dpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/gkd_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/gkd_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/gkd_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/gkd_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/grpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/grpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/grpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/grpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/judges.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/judges.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/kto_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/kto_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/kto_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/kto_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/model_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/model_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/orpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/orpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/orpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/orpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/ppo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/ppo_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/ppo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/ppo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/prm_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/prm_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/prm_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/prm_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/reward_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/reward_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/rloo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/rloo_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/rloo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/rloo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/sft_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/sft_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/sft_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/xpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/xpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/envs/trl/trl/trainer/xpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/envs/trl/trl/trainer/xpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage1/src/__pycache__/task.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/__pycache__/task.cpython-310.pyc -------------------------------------------------------------------------------- /3dthinker/stage1/src/__pycache__/utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/__pycache__/utils.cpython-310.pyc -------------------------------------------------------------------------------- /3dthinker/stage1/src/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/main.py -------------------------------------------------------------------------------- /3dthinker/stage1/src/main_deepspeed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/main_deepspeed.py -------------------------------------------------------------------------------- /3dthinker/stage1/src/main_multi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/main_multi.py -------------------------------------------------------------------------------- /3dthinker/stage1/src/multimodal_projector/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/multimodal_projector/builder.py -------------------------------------------------------------------------------- /3dthinker/stage1/src/task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/task.py -------------------------------------------------------------------------------- /3dthinker/stage1/src/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/test.py -------------------------------------------------------------------------------- /3dthinker/stage1/src/trainer_deepspeed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/trainer_deepspeed.py -------------------------------------------------------------------------------- /3dthinker/stage1/src/trainer_multi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/trainer_multi.py -------------------------------------------------------------------------------- /3dthinker/stage1/src/trainer_single.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/trainer_single.py -------------------------------------------------------------------------------- /3dthinker/stage1/src/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/src/utils.py -------------------------------------------------------------------------------- /3dthinker/stage1/train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/train.sh -------------------------------------------------------------------------------- /3dthinker/stage1/train_deepspeed.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/train_deepspeed.sh -------------------------------------------------------------------------------- /3dthinker/stage1/train_multi.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/train_multi.sh -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/.circleci/config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/.circleci/config.yml -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/.gitattributes -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/.github/conda/build.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/.github/conda/build.sh -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/.github/conda/meta.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/.github/conda/meta.yaml -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/.gitignore -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/CITATION.cff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/CITATION.cff -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/CONTRIBUTING.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/ISSUES.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/ISSUES.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/LICENSE -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/Makefile -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/README.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/SECURITY.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/SECURITY.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/awesome-transformers.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/awesome-transformers.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/benchmark/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/benchmark/README.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/benchmark/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/benchmark/benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/benchmark/benchmark.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/benchmark/default.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/benchmark/default.yml -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/benchmark/init_db.sql: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/benchmark/init_db.sql -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/benchmark/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/benchmark/llama.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/conftest.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docker/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docker/README.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/README.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/TRANSLATING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/TRANSLATING.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/_config.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ar/agents.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ar/agents.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ar/gguf.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ar/gguf.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ar/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ar/index.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ar/peft.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ar/peft.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ar/tflite.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ar/tflite.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/de/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/de/index.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/de/peft.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/de/peft.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/en/agents.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/en/agents.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/en/fsdp.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/en/fsdp.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/en/gguf.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/en/gguf.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/en/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/en/index.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/en/models.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/en/models.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/en/peft.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/en/peft.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/en/tf_xla.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/en/tf_xla.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/en/tflite.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/en/tflite.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/en/tools.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/en/tools.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/es/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/es/index.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/fr/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/fr/index.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/hi/tflite.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/hi/tflite.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/it/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/it/index.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ja/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ja/index.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ja/peft.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ja/peft.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ja/tf_xla.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ja/tf_xla.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ja/tflite.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ja/tflite.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ko/fsdp.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ko/fsdp.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ko/gguf.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ko/gguf.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ko/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ko/index.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ko/peft.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ko/peft.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ko/tf_xla.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ko/tf_xla.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/ko/tflite.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/ko/tflite.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/zh/fsdp.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/zh/fsdp.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/zh/gguf.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/zh/gguf.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/docs/source/zh/peft.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/docs/source/zh/peft.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/examples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/examples/README.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/examples/legacy/benchmarking/requirements.txt: -------------------------------------------------------------------------------- 1 | torch >= 1.3 -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/examples/modular-transformers/configuration_dummy.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/examples/modular-transformers/configuration_super.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/examples/tensorflow/contrastive-image-text/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow>=2.6.0 2 | datasets>=1.8.0 -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/examples/tensorflow/image-classification/requirements.txt: -------------------------------------------------------------------------------- 1 | datasets>=1.17.0 2 | evaluate 3 | tensorflow>=2.4 4 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/examples/tensorflow/language-modeling/requirements.txt: -------------------------------------------------------------------------------- 1 | datasets >= 1.8.0 2 | sentencepiece != 0.1.92 -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/examples/tensorflow/multiple-choice/requirements.txt: -------------------------------------------------------------------------------- 1 | sentencepiece != 0.1.92 2 | protobuf 3 | tensorflow >= 2.3 4 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/hubconf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/hubconf.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_ar.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_ar.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_de.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_de.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_es.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_es.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_fr.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_fr.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_hd.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_hd.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_ja.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_ja.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_ko.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_ko.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_pt-br.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_pt-br.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_ru.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_ru.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_te.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_te.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_ur.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_ur.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_vi.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_vi.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_zh-hans.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_zh-hans.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/i18n/README_zh-hant.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/i18n/README_zh-hant.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/model_cards/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/model_cards/README.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/notebooks/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/notebooks/README.md -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/pyproject.toml -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/scripts/stale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/scripts/stale.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/setup.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/src/transformers/kernels/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/src/transformers/models/deprecated/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/src/transformers/models/deprecated/bort/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/src/transformers/models/dialogpt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/src/transformers/models/dit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/agents/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/bettertransformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/fixtures/dummy-config.json: -------------------------------------------------------------------------------- 1 | { 2 | "model_type": "roberta" 3 | } -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/fixtures/empty.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/generation/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/albert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/align/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/altclip/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/aria/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/audio_spectrogram_transformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/auto/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/autoformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/aya_vision/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bamba/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bark/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bart/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/barthez/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bartpho/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/beit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bert_generation/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bert_japanese/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bertweet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/big_bird/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bigbird_pegasus/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/biogpt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/blenderbot/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/blenderbot_small/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/blip/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/blip_2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bloom/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bridgetower/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/bros/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/byt5/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/camembert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/canine/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/chameleon/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/chinese_clip/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/clap/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/clip/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/clipseg/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/clvp/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/code_llama/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/codegen/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/cohere/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/cohere2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/colpali/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/conditional_detr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/convbert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/convnext/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/convnextv2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/cpm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/cpmant/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/ctrl/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/cvt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/dab_detr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/dac/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/data2vec/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/dbrx/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/deberta/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/deberta_v2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/decision_transformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/deformable_detr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/deit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/depth_anything/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/depth_pro/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/detr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/diffllama/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/dinat/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/dinov2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/dinov2_with_registers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/distilbert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/dit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/donut/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/dpr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/dpt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/efficientnet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/electra/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/emu3/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/encodec/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/encoder_decoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/ernie/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/esm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/falcon/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/falcon_mamba/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/fastspeech2_conformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/flaubert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/flava/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/fnet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/focalnet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/fsmt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/funnel/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/fuyu/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/gemma/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/gemma2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/gemma3/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/git/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/glm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/glpn/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/got_ocr2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/gpt2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/gpt_bigcode/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/gpt_neo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/gpt_neox/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/gpt_neox_japanese/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/gpt_sw3/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/gptj/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/granite/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/granitemoe/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/granitemoeshared/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/grounding_dino/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/groupvit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/helium/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/herbert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/hiera/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/hubert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/ibert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/idefics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/idefics2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/idefics3/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/ijepa/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/imagegpt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/informer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/instructblip/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/instructblipvideo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/jamba/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/jetmoe/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/kosmos2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/layoutlm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/layoutlmv2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/layoutlmv3/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/layoutxlm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/led/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/levit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/lilt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/llama/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/llava/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/llava_next/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/llava_next_video/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/llava_onevision/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/longformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/longt5/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/luke/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/lxmert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/m2m_100/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mamba/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mamba2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/marian/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/markuplm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mask2former/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/maskformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mbart/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mbart50/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/megatron_bert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/megatron_gpt2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mgp_str/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mimi/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mistral/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mistral3/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mixtral/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mllama/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mluke/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mobilebert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mobilenet_v1/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mobilenet_v2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mobilevit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mobilevitv2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/modernbert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/moonshine/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/moshi/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mpnet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mpt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mra/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mt5/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/musicgen/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/musicgen_melody/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/mvp/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/myt5/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/nemotron/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/nllb/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/nllb_moe/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/nougat/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/nystromformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/olmo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/olmo2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/olmoe/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/omdet_turbo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/oneformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/openai/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/opt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/owlv2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/owlvit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/paligemma/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/paligemma2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/patchtsmixer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/patchtst/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/pegasus/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/pegasus_x/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/perceiver/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/persimmon/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/phi/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/phi3/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/phimoe/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/phobert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/pix2struct/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/pixtral/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/plbart/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/poolformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/pop2piano/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/prophetnet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/pvt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/pvt_v2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/qwen2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/qwen2_5_vl/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/qwen2_audio/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/qwen2_moe/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/qwen2_vl/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/rag/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/recurrent_gemma/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/reformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/regnet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/rembert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/resnet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/roberta/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/roberta_prelayernorm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/roc_bert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/roformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/rt_detr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/rt_detr_v2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/rwkv/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/sam/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/seamless_m4t/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/seamless_m4t_v2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/segformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/seggpt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/sew/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/sew_d/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/siglip/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/siglip2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/smolvlm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/speech_encoder_decoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/speech_to_text/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/speecht5/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/splinter/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/squeezebert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/stablelm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/starcoder2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/superglue/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/superpoint/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/swiftformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/swin/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/swin2sr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/swinv2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/switch_transformers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/t5/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/table_transformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/tapas/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/textnet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/time_series_transformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/timesformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/timm_backbone/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/timm_wrapper/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/trocr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/tvp/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/udop/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/umt5/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/unispeech/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/unispeech_sat/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/univnet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/upernet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/video_llava/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/videomae/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vilt/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vipllava/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vision_encoder_decoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vision_text_dual_encoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/visual_bert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vit_mae/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vit_msn/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vitdet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vitmatte/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vitpose/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vitpose_backbone/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vits/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/vivit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/wav2vec2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/wav2vec2_bert/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/wav2vec2_conformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/wav2vec2_phoneme/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/wav2vec2_with_lm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/wavlm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/whisper/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/x_clip/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/xglm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/xlm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/xlm_roberta/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/xlm_roberta_xl/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/xlnet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/xmod/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/yolos/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/yoso/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/zamba/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/zamba2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/models/zoedepth/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/optimization/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/pipelines/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/aqlm_integration/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/autoawq/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/bitnet_integration/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/bnb/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/compressed_tensors/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/eetq_integration/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/fbgemm_fp8/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/finegrained_fp8/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/ggml/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/gptq/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/higgs/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/quanto_integration/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/spqr_integration/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/torchao_integration/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/quantization/vptq_integration/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/tokenization/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/trainer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/tests/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/check_build.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/check_build.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/check_copies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/check_copies.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/check_doc_toc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/check_doc_toc.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/check_dummies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/check_dummies.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/check_inits.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/check_inits.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/check_repo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/check_repo.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/check_tf_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/check_tf_ops.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/get_test_info.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/get_test_info.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/patch_helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/patch_helper.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/print_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/print_env.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/release.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/release.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/test_module/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/tests_fetcher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/tests_fetcher.py -------------------------------------------------------------------------------- /3dthinker/stage1/transformers/utils/tf_ops/onnx.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage1/transformers/utils/tf_ops/onnx.json -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/cli.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/core.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/data_utils.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/environment/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/environment/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/extras/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/extras/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/extras/profiling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/extras/profiling.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/extras/vllm_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/extras/vllm_client.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/import_utils.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/mergekit_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/mergekit_utils.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/models/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/models/modeling_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/models/modeling_base.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/models/sd_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/models/sd_utils.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/models/utils.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/scripts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/scripts/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/scripts/chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/scripts/chat.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/scripts/dpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/scripts/dpo.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/scripts/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/scripts/env.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/scripts/grpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/scripts/grpo.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/scripts/kto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/scripts/kto.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/scripts/sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/scripts/sft.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/scripts/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/scripts/utils.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/scripts/vllm_serve.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/scripts/vllm_serve.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/__init__.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/bco_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/bco_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/bco_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/bco_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/callbacks.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/cpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/cpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/cpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/cpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/ddpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/ddpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/ddpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/ddpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/dpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/dpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/dpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/dpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/gkd_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/gkd_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/gkd_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/gkd_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/grpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/grpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/grpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/grpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/judges.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/judges.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/kto_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/kto_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/kto_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/kto_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/model_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/model_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/orpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/orpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/orpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/orpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/ppo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/ppo_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/ppo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/ppo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/prm_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/prm_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/prm_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/prm_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/rloo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/rloo_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/rloo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/rloo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/sft_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/sft_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/sft_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/utils.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/xpo_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/xpo_config.py -------------------------------------------------------------------------------- /3dthinker/stage2/package/trl/trainer/xpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/package/trl/trainer/xpo_trainer.py -------------------------------------------------------------------------------- /3dthinker/stage2/run_scripts/train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/run_scripts/train.sh -------------------------------------------------------------------------------- /3dthinker/stage2/setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/setup.sh -------------------------------------------------------------------------------- /3dthinker/stage2/src/open-r1-multimodal/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/src/open-r1-multimodal/.gitignore -------------------------------------------------------------------------------- /3dthinker/stage2/src/open-r1-multimodal/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/src/open-r1-multimodal/Makefile -------------------------------------------------------------------------------- /3dthinker/stage2/src/open-r1-multimodal/setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/src/open-r1-multimodal/setup.cfg -------------------------------------------------------------------------------- /3dthinker/stage2/src/open-r1-multimodal/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/3dthinker/stage2/src/open-r1-multimodal/setup.py -------------------------------------------------------------------------------- /3dthinker/stage2/src/open-r1-multimodal/src/open_r1/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3dthinker/stage2/src/open-r1-multimodal/src/open_r1/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/README.md -------------------------------------------------------------------------------- /SFT/env/.env.local: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/.env.local -------------------------------------------------------------------------------- /SFT/env/README.md: -------------------------------------------------------------------------------- 1 | Install the environment from LlamaFactory -------------------------------------------------------------------------------- /SFT/env/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/pyproject.toml -------------------------------------------------------------------------------- /SFT/env/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/requirements.txt -------------------------------------------------------------------------------- /SFT/env/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/setup.py -------------------------------------------------------------------------------- /SFT/env/src/api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/api.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/api/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/api/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/api/app.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/api/chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/api/chat.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/api/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/api/common.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/api/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/api/protocol.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/chat/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/chat/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/chat/base_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/chat/base_engine.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/chat/chat_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/chat/chat_model.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/chat/hf_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/chat/hf_engine.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/chat/sglang_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/chat/sglang_engine.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/chat/vllm_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/chat/vllm_engine.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/cli.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/collator.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/converter.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/data_utils.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/formatter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/formatter.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/loader.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/mm_plugin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/mm_plugin.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/parser.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/processor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/processor/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/processor/feedback.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/processor/feedback.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/processor/pairwise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/processor/pairwise.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/processor/pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/processor/pretrain.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/template.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/data/tool_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/data/tool_utils.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/eval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/eval/evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/eval/evaluator.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/eval/template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/eval/template.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/extras/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/extras/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/extras/constants.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/extras/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/extras/env.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/extras/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/extras/logging.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/extras/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/extras/misc.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/extras/packages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/extras/packages.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/extras/ploting.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/extras/ploting.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/hparams/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/hparams/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/hparams/data_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/hparams/data_args.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/hparams/evaluation_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/hparams/evaluation_args.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/hparams/finetuning_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/hparams/finetuning_args.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/hparams/generating_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/hparams/generating_args.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/hparams/model_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/hparams/model_args.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/hparams/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/hparams/parser.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/hparams/training_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/hparams/training_args.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/launcher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/launcher.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/model/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/model/adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/model/adapter.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/model/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/model/loader.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/model/model_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/model/model_utils/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/model/model_utils/misc.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/model/model_utils/mod.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/model/model_utils/mod.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/model/model_utils/moe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/model/model_utils/moe.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/model/model_utils/rope.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/model/model_utils/rope.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/model/model_utils/visual.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/model/model_utils/visual.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/model/patcher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/model/patcher.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/callbacks.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/dpo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/dpo/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/dpo/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/dpo/trainer.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/dpo/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/dpo/workflow.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/kto/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/kto/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/kto/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/kto/trainer.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/kto/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/kto/workflow.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/ppo/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/ppo/ppo_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/ppo/ppo_utils.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/ppo/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/ppo/trainer.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/ppo/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/ppo/workflow.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/pt/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/pt/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/pt/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/pt/trainer.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/pt/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/pt/workflow.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/rm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/rm/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/rm/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/rm/metric.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/rm/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/rm/trainer.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/rm/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/rm/workflow.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/sft/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/sft/__init__.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/sft/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/sft/metric.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/sft/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/sft/trainer.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/sft/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/sft/workflow.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/test_utils.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/trainer_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/trainer_utils.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/train/tuner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/train/tuner.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/chatter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/chatter.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/common.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/components/chatbot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/components/chatbot.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/components/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/components/data.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/components/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/components/eval.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/components/export.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/components/export.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/components/infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/components/infer.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/components/top.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/components/top.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/components/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/components/train.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/control.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/control.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/css.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/css.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/engine.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/interface.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/interface.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/locales.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/locales.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/manager.py -------------------------------------------------------------------------------- /SFT/env/src/llamafactory/webui/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/llamafactory/webui/runner.py -------------------------------------------------------------------------------- /SFT/env/src/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/train.py -------------------------------------------------------------------------------- /SFT/env/src/webui.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/env/src/webui.py -------------------------------------------------------------------------------- /SFT/train_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/SFT/train_sft.yaml -------------------------------------------------------------------------------- /assets/teaser.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/assets/teaser.png -------------------------------------------------------------------------------- /data/data_output3d_begin_10k_resized.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/data/data_output3d_begin_10k_resized.jsonl -------------------------------------------------------------------------------- /data/idx.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/data/idx.jsonl -------------------------------------------------------------------------------- /envs/requirements_sft.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/envs/requirements_sft.txt -------------------------------------------------------------------------------- /envs/requirements_stage1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/envs/requirements_stage1.txt -------------------------------------------------------------------------------- /envs/requirements_stage2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/envs/requirements_stage2.txt -------------------------------------------------------------------------------- /eval/eval_close_source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/eval_close_source.py -------------------------------------------------------------------------------- /eval/eval_internvl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/eval_internvl.py -------------------------------------------------------------------------------- /eval/eval_llava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/eval_llava.py -------------------------------------------------------------------------------- /eval/eval_mindcube.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/eval_mindcube.sh -------------------------------------------------------------------------------- /eval/eval_qwen3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/eval_qwen3.py -------------------------------------------------------------------------------- /eval/get_result.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/get_result.sh -------------------------------------------------------------------------------- /eval/scripts/run_evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/scripts/run_evaluation.py -------------------------------------------------------------------------------- /eval/scripts/run_inference_clean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/scripts/run_inference_clean.py -------------------------------------------------------------------------------- /eval/src/__init__.py: -------------------------------------------------------------------------------- 1 | # MindCube Source Package -------------------------------------------------------------------------------- /eval/src/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /eval/src/evaluation/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/__init__.py -------------------------------------------------------------------------------- /eval/src/evaluation/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/cli.py -------------------------------------------------------------------------------- /eval/src/evaluation/cogmap/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/cogmap/__init__.py -------------------------------------------------------------------------------- /eval/src/evaluation/cogmap/cogmap_evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/cogmap/cogmap_evaluator.py -------------------------------------------------------------------------------- /eval/src/evaluation/cogmap/cogmap_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/cogmap/cogmap_metrics.py -------------------------------------------------------------------------------- /eval/src/evaluation/cogmap/graph_operations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/cogmap/graph_operations.py -------------------------------------------------------------------------------- /eval/src/evaluation/core/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/core/__init__.py -------------------------------------------------------------------------------- /eval/src/evaluation/core/base_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/core/base_metrics.py -------------------------------------------------------------------------------- /eval/src/evaluation/core/extractors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/core/extractors.py -------------------------------------------------------------------------------- /eval/src/evaluation/core/io_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/core/io_utils.py -------------------------------------------------------------------------------- /eval/src/evaluation/core/mindcube_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/core/mindcube_eval.py -------------------------------------------------------------------------------- /eval/src/evaluation/evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/evaluation/evaluator.py -------------------------------------------------------------------------------- /eval/src/inference/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference/__init__.py -------------------------------------------------------------------------------- /eval/src/inference/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference/base.py -------------------------------------------------------------------------------- /eval/src/inference/closed_source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference/closed_source.py -------------------------------------------------------------------------------- /eval/src/inference/engines/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference/engines/__init__.py -------------------------------------------------------------------------------- /eval/src/inference/engines/qwen_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference/engines/qwen_engine.py -------------------------------------------------------------------------------- /eval/src/inference/open_source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference/open_source.py -------------------------------------------------------------------------------- /eval/src/inference/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference/utils.py -------------------------------------------------------------------------------- /eval/src/inference_mindcube/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference_mindcube/__init__.py -------------------------------------------------------------------------------- /eval/src/inference_mindcube/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference_mindcube/base.py -------------------------------------------------------------------------------- /eval/src/inference_mindcube/closed_source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference_mindcube/closed_source.py -------------------------------------------------------------------------------- /eval/src/inference_mindcube/open_source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference_mindcube/open_source.py -------------------------------------------------------------------------------- /eval/src/inference_mindcube/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/inference_mindcube/utils.py -------------------------------------------------------------------------------- /eval/src/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/utils/__init__.py -------------------------------------------------------------------------------- /eval/src/utils/io_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/utils/io_utils.py -------------------------------------------------------------------------------- /eval/src/utils/spatial_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/utils/spatial_utils.py -------------------------------------------------------------------------------- /eval/src/utils/text_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/eval/src/utils/text_utils.py -------------------------------------------------------------------------------- /preprocessing/clean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/clean.py -------------------------------------------------------------------------------- /preprocessing/feature/extract_vggt_feature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/extract_vggt_feature.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/dependency/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/dependency/__init__.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/dependency/distortion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/dependency/distortion.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/dependency/projection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/dependency/projection.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/dependency/track_modules/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /preprocessing/feature/vggt/heads/camera_head.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/heads/camera_head.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/heads/dpt_head.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/heads/dpt_head.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/heads/head_act.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/heads/head_act.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/heads/track_head.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/heads/track_head.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/heads/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/heads/utils.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/layers/__init__.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/layers/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/layers/attention.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/layers/block.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/layers/block.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/layers/drop_path.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/layers/drop_path.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/layers/layer_scale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/layers/layer_scale.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/layers/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/layers/mlp.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/layers/patch_embed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/layers/patch_embed.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/layers/rope.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/layers/rope.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/layers/swiglu_ffn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/layers/swiglu_ffn.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/models/aggregator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/models/aggregator.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/models/vggt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/models/vggt.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/utils/geometry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/utils/geometry.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/utils/helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/utils/helper.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/utils/load_fn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/utils/load_fn.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/utils/pose_enc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/utils/pose_enc.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/utils/rotation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/utils/rotation.py -------------------------------------------------------------------------------- /preprocessing/feature/vggt/utils/visual_track.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/feature/vggt/utils/visual_track.py -------------------------------------------------------------------------------- /preprocessing/jsonl_add_idx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/jsonl_add_idx.py -------------------------------------------------------------------------------- /preprocessing/produce_cot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/produce_cot.py -------------------------------------------------------------------------------- /preprocessing/remove.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/preprocessing/remove.py -------------------------------------------------------------------------------- /tests/infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/tests/infer.py -------------------------------------------------------------------------------- /tests/visual_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhangquanchen/3DThinker/HEAD/tests/visual_decoder.py --------------------------------------------------------------------------------