├── .gitignore ├── LICENSE ├── LLaMA-Factory ├── CITATION.cff ├── LICENSE ├── MANIFEST.in ├── Makefile ├── README.md ├── README_zh.md ├── assets │ ├── alaya_new.svg │ ├── logo.png │ ├── wechat.jpg │ ├── wechat_alaya.png │ └── wechat_npu.jpg ├── data │ ├── README.md │ ├── README_zh.md │ ├── alpaca_en_demo.json │ ├── alpaca_zh_demo.json │ ├── belle_multiturn │ │ └── belle_multiturn.py │ ├── c4_demo.jsonl │ ├── dataset_info.json │ ├── dpo_en_demo.json │ ├── dpo_zh_demo.json │ ├── glaive_toolcall_en_demo.json │ ├── glaive_toolcall_zh_demo.json │ ├── hh_rlhf_en │ │ └── hh_rlhf_en.py │ ├── identity.json │ ├── kto_en_demo.json │ ├── mllm_audio_demo.json │ ├── mllm_demo.json │ ├── mllm_demo_data │ │ ├── 1.jpg │ │ ├── 1.mp3 │ │ ├── 1.mp4 │ │ ├── 2.avi │ │ ├── 2.jpg │ │ ├── 2.wav │ │ ├── 3.flac │ │ ├── 3.jpg │ │ ├── 3.mp4 │ │ ├── 4.mp3 │ │ └── 4.mp4 │ ├── mllm_video_audio_demo.json │ ├── mllm_video_demo.json │ ├── ultra_chat │ │ └── ultra_chat.py │ └── wiki_demo.txt ├── docker │ ├── docker-cuda │ │ ├── Dockerfile │ │ ├── Dockerfile.base │ │ ├── README.md │ │ └── docker-compose.yml │ ├── docker-npu │ │ ├── Dockerfile │ │ └── docker-compose.yml │ └── docker-rocm │ │ ├── Dockerfile │ │ └── docker-compose.yml ├── evaluation │ ├── ceval │ │ ├── ceval.py │ │ ├── ceval.zip │ │ └── mapping.json │ ├── cmmlu │ │ ├── cmmlu.py │ │ ├── cmmlu.zip │ │ └── mapping.json │ └── mmlu │ │ ├── mapping.json │ │ ├── mmlu.py │ │ └── mmlu.zip ├── examples │ ├── README.md │ ├── README_zh.md │ ├── accelerate │ │ ├── fsdp_config.yaml │ │ └── fsdp_config_offload.yaml │ ├── deepspeed │ │ ├── ds_z0_config.json │ │ ├── ds_z2_config.json │ │ ├── ds_z2_offload_config.json │ │ ├── ds_z3_config.json │ │ └── ds_z3_offload_config.json │ ├── extras │ │ ├── adam_mini │ │ │ └── qwen2_full_sft.yaml │ │ ├── apollo │ │ │ └── llama3_full_sft.yaml │ │ ├── badam │ │ │ └── llama3_full_sft.yaml │ │ ├── fsdp_qlora │ │ │ ├── llama3_lora_sft.yaml │ │ │ └── train.sh │ │ ├── galore │ │ │ └── llama3_full_sft.yaml │ │ ├── llama_pro │ │ │ ├── expand.sh │ │ │ └── llama3_freeze_sft.yaml │ │ ├── loraplus │ │ │ └── llama3_lora_sft.yaml │ │ ├── mod │ │ │ └── llama3_full_sft.yaml │ │ ├── muon │ │ │ └── qwen2_full_sft.yaml │ │ ├── nlg_eval │ │ │ └── llama3_lora_predict.yaml │ │ └── pissa │ │ │ ├── init.sh │ │ │ └── llama3_lora_sft.yaml │ ├── inference │ │ ├── llama3.yaml │ │ ├── llama3_full_sft.yaml │ │ ├── llama3_lora_sft.yaml │ │ └── qwen2_5vl.yaml │ ├── merge_lora │ │ ├── llama3_full_sft.yaml │ │ ├── llama3_gptq.yaml │ │ ├── llama3_lora_sft.yaml │ │ ├── qwen2_5vl_lora_sft.yaml │ │ └── qwen_lora_sft.yaml │ ├── train_full │ │ ├── llama3_full_sft.yaml │ │ ├── qwen2_5vl_full_sft.yaml │ │ └── qwen_full_sft.yaml │ ├── train_lora │ │ ├── llama3_lora_dpo.yaml │ │ ├── llama3_lora_eval.yaml │ │ ├── llama3_lora_kto.yaml │ │ ├── llama3_lora_ppo.yaml │ │ ├── llama3_lora_pretrain.yaml │ │ ├── llama3_lora_reward.yaml │ │ ├── llama3_lora_sft.sh │ │ ├── llama3_lora_sft_ds3.yaml │ │ ├── llama3_lora_sft_ray.yaml │ │ ├── llama3_preprocess.yaml │ │ ├── llama4_lora_sft_ds3.yaml │ │ ├── qwen2_5vl_lora_dpo.yaml │ │ ├── qwen2_5vl_lora_sft.yaml │ │ └── qwen_lora_sft.yaml │ └── train_qlora │ │ ├── llama3_lora_sft_aqlm.yaml │ │ ├── llama3_lora_sft_awq.yaml │ │ ├── llama3_lora_sft_bnb_npu.yaml │ │ ├── llama3_lora_sft_gptq.yaml │ │ └── llama3_lora_sft_otfq.yaml ├── pyproject.toml ├── requirements.txt ├── run_train.sh ├── run_train_lora.sh ├── scripts │ ├── api_example │ │ ├── test_image.py │ │ └── test_toolcall.py │ ├── convert_ckpt │ │ ├── llamafy_baichuan2.py │ │ ├── llamafy_qwen.py │ │ └── tiny_llama4.py │ ├── eval_bleu_rouge.py │ ├── llama_pro.py │ ├── loftq_init.py │ ├── pissa_init.py │ ├── qwen_omni_merge.py │ ├── stat_utils │ │ ├── cal_flops.py │ │ ├── cal_lr.py │ │ ├── cal_mfu.py │ │ ├── cal_ppl.py │ │ └── length_cdf.py │ └── vllm_infer.py ├── setup.py ├── src │ ├── api.py │ ├── llamafactory │ │ ├── __init__.py │ │ ├── api │ │ │ ├── __init__.py │ │ │ ├── app.py │ │ │ ├── chat.py │ │ │ ├── common.py │ │ │ └── protocol.py │ │ ├── chat │ │ │ ├── __init__.py │ │ │ ├── base_engine.py │ │ │ ├── chat_model.py │ │ │ ├── hf_engine.py │ │ │ ├── sglang_engine.py │ │ │ └── vllm_engine.py │ │ ├── cli.py │ │ ├── data │ │ │ ├── __init__.py │ │ │ ├── collator.py │ │ │ ├── converter.py │ │ │ ├── data_utils.py │ │ │ ├── formatter.py │ │ │ ├── loader.py │ │ │ ├── mm_plugin.py │ │ │ ├── parser.py │ │ │ ├── processor │ │ │ │ ├── __init__.py │ │ │ │ ├── feedback.py │ │ │ │ ├── pairwise.py │ │ │ │ ├── pretrain.py │ │ │ │ ├── processor_utils.py │ │ │ │ ├── supervised.py │ │ │ │ └── unsupervised.py │ │ │ ├── template.py │ │ │ └── tool_utils.py │ │ ├── eval │ │ │ ├── __init__.py │ │ │ ├── evaluator.py │ │ │ └── template.py │ │ ├── extras │ │ │ ├── __init__.py │ │ │ ├── constants.py │ │ │ ├── env.py │ │ │ ├── logging.py │ │ │ ├── misc.py │ │ │ ├── packages.py │ │ │ └── ploting.py │ │ ├── hparams │ │ │ ├── __init__.py │ │ │ ├── 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 │ │ │ ├── adapter.py │ │ │ ├── loader.py │ │ │ ├── model_utils │ │ │ │ ├── __init__.py │ │ │ │ ├── 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 │ │ ├── third_party │ │ │ ├── __init__.py │ │ │ └── muon │ │ │ │ ├── __init__.py │ │ │ │ └── muon.py │ │ ├── train │ │ │ ├── __init__.py │ │ │ ├── callbacks.py │ │ │ ├── dpo │ │ │ │ ├── __init__.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── kto │ │ │ │ ├── __init__.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── ppo │ │ │ │ ├── __init__.py │ │ │ │ ├── ppo_utils.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── pt │ │ │ │ ├── __init__.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── rm │ │ │ │ ├── __init__.py │ │ │ │ ├── metric.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── sft │ │ │ │ ├── __init__.py │ │ │ │ ├── metric.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── test_utils.py │ │ │ ├── trainer_utils.py │ │ │ └── tuner.py │ │ └── webui │ │ │ ├── __init__.py │ │ │ ├── chatter.py │ │ │ ├── common.py │ │ │ ├── components │ │ │ ├── __init__.py │ │ │ ├── chatbot.py │ │ │ ├── data.py │ │ │ ├── eval.py │ │ │ ├── export.py │ │ │ ├── footer.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 └── tests │ ├── check_license.py │ ├── data │ ├── processor │ │ ├── test_feedback.py │ │ ├── test_pairwise.py │ │ ├── test_processor_utils.py │ │ ├── test_supervised.py │ │ └── test_unsupervised.py │ ├── test_collator.py │ ├── test_converter.py │ ├── test_formatter.py │ ├── test_loader.py │ ├── test_mm_plugin.py │ └── test_template.py │ ├── e2e │ ├── test_chat.py │ ├── test_sglang.py │ └── test_train.py │ ├── eval │ └── test_eval_template.py │ ├── model │ ├── model_utils │ │ ├── test_add_tokens.py │ │ ├── test_attention.py │ │ ├── test_checkpointing.py │ │ ├── test_misc.py │ │ ├── test_packing.py │ │ └── test_visual.py │ ├── test_base.py │ ├── test_freeze.py │ ├── test_full.py │ ├── test_lora.py │ └── test_pissa.py │ ├── train │ └── test_sft_trainer.py │ └── version.txt ├── README.md ├── __init__.py ├── config.py ├── data.py ├── index_and_topics.py ├── listwise_prompt_r1.toml ├── rerank ├── __init__.py ├── api_keys.py ├── rank_gpt.py ├── rank_listwise_os_llm.py ├── rankllm.py └── reranker.py ├── results ├── economics.json └── robotics.json ├── run_rank_llm.py ├── run_rank_llm.sh ├── runs └── economics │ ├── custom.txt │ └── reasonir_gpt4cot_top100.txt ├── trec_eval.py ├── utils.py └── verl ├── LICENSE ├── Notice.txt ├── README.md ├── docker ├── Apptainerfile.rocm ├── Dockerfile.awsefa ├── Dockerfile.ngc.vllm ├── Dockerfile.ngc.vllm0.8 ├── Dockerfile.ngc.vllm0.8.sagemaker ├── Dockerfile.rocm ├── Dockerfile.sglang ├── Dockerfile.vemlp.vllm.te ├── Dockerfile.vllm.sglang.megatron └── Dockerfile.vllm.sglang.megatron.deepseek ├── docs ├── Makefile ├── README.md ├── README_vllm0.7.md ├── README_vllm0.8.md ├── _static │ ├── js │ │ └── runllm-widget.js │ └── logo.png ├── advance │ ├── checkpoint.rst │ ├── dpo_extension.rst │ ├── fsdp_extension.rst │ ├── megatron_extension.rst │ ├── placement.rst │ ├── ppo_lora.rst │ └── rope.rst ├── algo │ ├── baseline.md │ ├── dapo.md │ ├── grpo.md │ ├── opo.md │ ├── ppo.md │ ├── spin.md │ └── sppo.md ├── amd_tutorial │ ├── amd_build_dockerfile_page.rst │ └── amd_vllm_page.rst ├── api │ ├── data.rst │ ├── single_controller.rst │ ├── trainer.rst │ └── utils.rst ├── ascend_tutorial │ └── ascend_quick_start.rst ├── conf.py ├── examples │ ├── config.rst │ ├── gsm8k_example.rst │ ├── multi_modal_example.rst │ ├── ppo_code_architecture.rst │ └── sandbox_fusion_example.rst ├── faq │ └── faq.rst ├── hybrid_flow.rst ├── index.rst ├── perf │ ├── device_tuning.rst │ └── perf_tuning.rst ├── preparation │ ├── prepare_data.rst │ └── reward_function.rst ├── requirements-docs.txt ├── sglang_multiturn │ ├── multiturn.rst │ ├── sandbox_fusion.rst │ └── search_tool_example.rst ├── single_controller.rst ├── start │ ├── install.rst │ ├── multinode.rst │ ├── quickstart.rst │ └── ray_debug_tutorial.rst └── workers │ ├── fsdp_workers.rst │ ├── megatron_workers.rst │ ├── ray_trainer.rst │ └── sglang_worker.rst ├── examples ├── data_preprocess │ ├── aime2024_multiturn_w_tool.py │ ├── dapo_multiturn_w_tool.py │ ├── full_hh_rlhf.py │ ├── geo3k.py │ ├── gsm8k.py │ ├── gsm8k_multiturn_w_tool.py │ ├── hellaswag.py │ ├── math_dataset.py │ ├── multiturn.py │ └── preprocess_search_r1_dataset.py ├── generation │ ├── run_deepseek7b_mutli_node.sh │ └── run_deepseek_v2_lite_math.sh ├── grpo_trainer │ ├── README.md │ ├── run_deepseek671b_math_megatron.sh │ ├── run_deepseek7b_llm.sh │ ├── run_deepseek7b_llm_math.sh │ ├── run_deepseek7b_llm_math_megatron.sh │ ├── run_deepseek7b_llm_seq_balance.sh │ ├── run_moonlight16b_math_megatron.sh │ ├── run_qwen2-7b.sh │ ├── run_qwen2-7b_math.sh │ ├── run_qwen2-7b_math_megatron.sh │ ├── run_qwen2-7b_seq_balance.sh │ ├── run_qwen2-7b_seq_balance_math_megatron.sh │ ├── run_qwen2-7b_sgl_megatron.sh │ ├── run_qwen2_5-3b_gsm8k_grpo_lora.sh │ ├── run_qwen2_5-7b_math_megatron_diff_tp.sh │ ├── run_qwen2_5_vl-7b.sh │ ├── run_qwen3-236b_megatron.sh │ ├── run_qwen3-8b.sh │ └── run_qwen3moe-30b_megatron.sh ├── ppo_trainer │ ├── README.md │ ├── naive_chat_scheduler.py │ ├── run_deepseek7b_llm.sh │ ├── run_deepseek7b_llm_modelscope.sh │ ├── run_deepseek7b_llm_pfppo.sh │ ├── run_deepseek7b_llm_sandbox_fusion.sh │ ├── run_deepseek7b_llm_sp2.sh │ ├── run_deepseek_full_hh_rlhf.sh │ ├── run_deepseek_math_gsm8k_megatron.sh │ ├── run_gemma.sh │ ├── run_moonlight16b_a3b_gsm8k_megatron.sh │ ├── run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh │ ├── run_qwen2-7b_math_gsm8k_megatron.sh │ ├── run_qwen2-7b_rm.sh │ ├── run_qwen2-7b_rm_seq_balance.sh │ ├── run_qwen2-7b_seq_balance.sh │ ├── run_qwen2-7b_sglang_seq_balance.sh │ └── run_qwen2.5-32b.sh ├── ray │ └── tutorial.ipynb ├── reinforce_plus_plus_trainer │ ├── run_qwen2-7b_math_rf.sh │ └── run_qwen2-7b_math_rf_baseline.sh ├── remax_trainer │ ├── run_qwen2.5-3b_seq_balance.sh │ └── run_qwen2.5-7b_seq_balance.sh ├── rloo_trainer │ └── run_qwen2-7b.sh ├── sft │ ├── gsm8k │ │ ├── run_deepseek_6b7.sh │ │ ├── run_gemma_2b.sh │ │ ├── run_gemma_7b.sh │ │ ├── run_qwen_05_peft.sh │ │ ├── run_qwen_05_sp2.sh │ │ └── run_qwen_05_sp2_liger.sh │ └── multiturn │ │ └── run_qwen_05_sp2.sh ├── sglang_multiturn │ ├── README.md │ ├── config │ │ ├── gsm8k_multiturn_grpo.yaml │ │ ├── gsm8k_multiturn_megatron_grpo.yaml │ │ ├── retool_multiturn_grpo.yaml │ │ ├── search_multiturn_grpo.yaml │ │ └── tool_config │ │ │ ├── gsm8k_tool_config.yaml │ │ │ ├── sandbox_fusion_tool_config.yaml │ │ │ └── search_tool_config.yaml │ ├── run_qwen2.5-3b_gsm8k_multiturn.sh │ ├── run_qwen2.5-3b_gsm8k_multiturn_4xgpu.sh │ ├── run_qwen2.5-3b_megatron_gsm8k_multiturn.sh │ └── search_r1_like │ │ ├── local_dense_retriever │ │ ├── download.py │ │ └── retrieval_server.py │ │ └── run_qwen2.5-3b_instruct_search_multiturn.sh ├── slurm │ └── ray_on_slurm.slurm ├── split_placement │ ├── README.md │ ├── config │ │ └── ppo_trainer_split.yaml │ ├── main_ppo_split.py │ ├── run_deepseek7b_llm.sh │ └── split_monkey_patch.py └── tuning │ ├── 14b │ └── qwen2_14b_grpo_4_h800_fsdp_vllm.sh │ ├── 32b │ └── qwen2_32B_grpo_8_h20_megatron_vllm.sh │ ├── 70b │ ├── qwen2-70b_grpo_32_h20_fsdp_vllm.sh │ └── qwen2-70b_grpo_32_h800_fsdp_vllm.sh │ └── 7b │ └── qwen2-7b_grpo_2_h800_fsdp_vllm.sh ├── pyproject.toml ├── recipe ├── README.md ├── dapo │ ├── README.md │ ├── config │ │ └── dapo_trainer.yaml │ ├── dapo_ray_trainer.py │ ├── main_dapo.py │ ├── prepare_dapo_data.sh │ ├── run_dapo_early_qwen2.5_32b.sh │ ├── run_dapo_qwen2.5_32b.sh │ ├── run_dapo_wo_ds_qwen2.5_32b.sh │ ├── test_dapo_7b.sh │ ├── test_dapo_7b_math.sh │ ├── test_dapo_7b_math_megatron.sh │ └── test_dapo_qwen3_30b_math.sh ├── prime │ ├── __init__.py │ ├── config │ │ └── prime_trainer.yaml │ ├── main_prime.py │ ├── prime_core_algos.py │ ├── prime_dp_rm.py │ ├── prime_fsdp_workers.py │ ├── prime_ray_trainer.py │ ├── run_prime_qwen.sh │ └── run_prime_qwen_code.sh ├── r1 │ ├── README.md │ ├── __init__.py │ ├── config │ │ └── evaluation.yaml │ ├── data_process.py │ ├── main_eval.py │ ├── reward_score.py │ ├── run_r1_distill_qwen.sh │ └── tasks │ │ ├── __init__.py │ │ ├── gpqa.py │ │ ├── livecodebench.py │ │ └── math.py ├── retool │ └── run_sft.sh ├── spin │ ├── README.md │ ├── config │ │ └── spin_trainer.yaml │ ├── core_algos.py │ ├── dp_actor.py │ ├── fsdp_workers.py │ ├── main_spin.py │ ├── run_spin.sh │ └── spin_trainer.py └── sppo │ ├── README.md │ ├── __init__.py │ ├── config │ └── sppo_trainer.yaml │ ├── dp_actor.py │ ├── main_sppo.py │ ├── run_qwen2.5-7b_rm.sh │ ├── sppo_ray_trainer.py │ └── sppo_worker.py ├── requirements-npu.txt ├── requirements.txt ├── requirements_sglang.txt ├── scripts ├── converter_hf_to_mcore.py ├── diagnose.py ├── init_random_model.py ├── install_vllm_sglang_mcore.sh ├── legacy_model_merger.py ├── merge.sh └── model_merger.py ├── setup.py ├── tests ├── __init__.py ├── distributed │ ├── run_all.sh │ └── test_tensor_dict.py ├── e2e │ ├── __init__.py │ ├── arithmetic_sequence │ │ ├── data │ │ │ ├── create_dataset.py │ │ │ ├── test.parquet │ │ │ └── train.parquet │ │ ├── model │ │ │ ├── config.json │ │ │ ├── create_model_tokenizer.py │ │ │ ├── generation_config.json │ │ │ ├── model.safetensors │ │ │ └── tokenizer_config.json │ │ └── rl │ │ │ ├── README.md │ │ │ └── main_trainer.py │ ├── check_custom_rwd_fn.py │ ├── check_results.py │ ├── envs │ │ ├── __init__.py │ │ └── digit_completion │ │ │ ├── __init__.py │ │ │ ├── task.py │ │ │ └── tokenizer.py │ ├── generation │ │ └── run_gen_qwen05.sh │ ├── ppo_trainer │ │ ├── expert_parallel │ │ │ └── qwen2moe_minimal.json │ │ ├── run_function_reward.sh │ │ └── run_model_reward.sh │ ├── run_dapo.sh │ ├── run_gsm8k_fsdp_sgl_multiturn_sf_tool.sh │ ├── run_gsm8k_fsdp_sgl_multiturn_w_tool.sh │ ├── run_ppo_trainer_megatron.sh │ ├── run_prime.sh │ ├── run_r1_distill_qwen_aime24_eval.sh │ ├── run_ray_trainer.sh │ ├── run_ray_trainer_fire_sampling.sh │ ├── run_ray_trainer_rmpad.sh │ ├── run_spin.sh │ ├── run_sppo.sh │ ├── run_test.sh │ └── sft │ │ ├── run_sft.sh │ │ └── test_sp_loss_match.py ├── gpu_utility │ ├── test_memory_buffers.py │ ├── test_ops.py │ └── test_torch_functional.py ├── kernels │ └── test_linear_cross_entropy.py ├── kill_github_tests.sh ├── models │ ├── test_transformer.py │ └── test_transformers_ulysses.py ├── npu │ ├── run_qwen2_5_05b_dapo.sh │ ├── run_qwen2_5_05b_grpo.sh │ ├── run_qwen2_5_32b_grpo.sh │ └── run_qwen2_5_7b_grpo.sh ├── ray_cpu │ ├── check_worker_alive │ │ └── main.py │ ├── test_auto_padding.py │ ├── test_check_worker_alive.py │ ├── test_decorator.py │ ├── test_fused_workers.py │ ├── test_ray_local_envs.py │ └── test_ray_utils.py ├── ray_gpu │ ├── detached_worker │ │ ├── README.md │ │ ├── client.py │ │ ├── run.sh │ │ └── server.py │ ├── test_colocated_workers.py │ ├── test_colocated_workers_fused.py │ ├── test_data_transfer.py │ ├── test_driverfunc_to_worker.py │ ├── test_high_level_scheduling_api.py │ ├── test_rvdz.py │ ├── test_worker_group_basics.py │ └── test_worker_group_torch.py ├── reward_score │ └── test_sandbox_fusion.py ├── sandbox │ └── test_sandbox.py ├── sanity │ ├── check_license.py │ └── test_import.py ├── single_controller │ └── base │ │ └── test_decorator.py ├── test_protocol.py ├── trainer │ ├── __init__.py │ └── ppo │ │ ├── __init__.py │ │ └── test_metric_utils.py ├── utils │ ├── cpu_tests │ │ ├── _test_module.py │ │ ├── test_fs.py │ │ ├── test_import_utils.py │ │ ├── test_model.py │ │ └── test_timeout_decorator.py │ └── gpu_tests │ │ ├── checkpoint │ │ └── test_fsdp_ckpt.py │ │ ├── dataset │ │ ├── test_multiturn_sft_dataset.py │ │ ├── test_rl_dataset.py │ │ ├── test_rm_dataset.py │ │ └── test_sft_dataset.py │ │ ├── megatron │ │ └── test_pipeline_parallel.py │ │ ├── test_activation_offload.py │ │ ├── test_flops_counter.py │ │ ├── test_seqlen_balancing.py │ │ └── test_torch_functional.py └── workers │ └── rollout │ ├── async_rollout_utils.py │ ├── resource │ └── tool_configs │ │ ├── sandbox_fusion_tool_config │ │ └── search_tool_config │ ├── run_fsdp_vllm.py │ ├── test_async_sglang_server.py │ ├── test_hf_rollout.py │ ├── test_sglang_async_rollout_search_tools.py │ ├── test_sglang_async_rollout_sf_tools.py │ ├── test_sglang_async_rollout_w_tools.py │ ├── test_sglang_spmd.py │ ├── test_vllm_hf_loader.py │ ├── test_vllm_multi_turn.py │ ├── test_vllm_spmd.py │ ├── test_vllm_tool_calling.py │ └── utils_sglang.py ├── train_grpo.sh ├── train_grpo_lora.sh └── verl ├── __init__.py ├── models ├── README.md ├── __init__.py ├── llama │ ├── __init__.py │ └── megatron │ │ ├── __init__.py │ │ ├── checkpoint_utils │ │ ├── __init__.py │ │ ├── llama_loader.py │ │ ├── llama_loader_depracated.py │ │ └── llama_saver.py │ │ ├── layers │ │ ├── __init__.py │ │ ├── parallel_attention.py │ │ ├── parallel_decoder.py │ │ ├── parallel_linear.py │ │ ├── parallel_mlp.py │ │ └── parallel_rmsnorm.py │ │ └── modeling_llama_megatron.py ├── mcore │ ├── __init__.py │ ├── config_converter.py │ ├── loader.py │ ├── model_forward.py │ ├── model_initializer.py │ ├── patch_v012.py │ ├── readme.md │ ├── registry.py │ ├── saver.py │ ├── util.py │ └── weight_converter.py ├── qwen2 │ ├── __init__.py │ └── megatron │ │ ├── __init__.py │ │ ├── checkpoint_utils │ │ ├── __init__.py │ │ ├── qwen2_loader.py │ │ ├── qwen2_loader_depracated.py │ │ └── qwen2_saver.py │ │ ├── layers │ │ ├── __init__.py │ │ ├── parallel_attention.py │ │ ├── parallel_decoder.py │ │ ├── parallel_linear.py │ │ ├── parallel_mlp.py │ │ └── parallel_rmsnorm.py │ │ └── modeling_qwen2_megatron.py ├── registry.py ├── transformers │ ├── __init__.py │ ├── kimi_vl.py │ ├── llama.py │ ├── monkey_patch.py │ ├── qwen2.py │ ├── qwen2_5_vl.py │ └── qwen2_vl.py └── weight_loader_registry.py ├── protocol.py ├── single_controller ├── __init__.py ├── base │ ├── __init__.py │ ├── decorator.py │ ├── megatron │ │ ├── __init__.py │ │ ├── worker.py │ │ └── worker_group.py │ ├── register_center │ │ ├── __init__.py │ │ └── ray.py │ ├── worker.py │ └── worker_group.py └── ray │ ├── __init__.py │ ├── base.py │ └── megatron.py ├── third_party ├── __init__.py ├── sglang │ ├── __init__.py │ └── parallel_state.py └── vllm │ ├── __init__.py │ ├── vllm_v_0_5_4 │ ├── __init__.py │ ├── arg_utils.py │ ├── config.py │ ├── dtensor_weight_loaders.py │ ├── hf_weight_loader.py │ ├── llm.py │ ├── llm_engine_sp.py │ ├── megatron_weight_loaders.py │ ├── model_loader.py │ ├── model_runner.py │ ├── parallel_state.py │ ├── spmd_gpu_executor.py │ ├── tokenizer.py │ └── worker.py │ └── vllm_v_0_6_3 │ ├── __init__.py │ ├── arg_utils.py │ ├── config.py │ ├── dtensor_weight_loaders.py │ ├── hf_weight_loader.py │ ├── llm.py │ ├── llm_engine_sp.py │ ├── megatron_weight_loaders.py │ ├── model_loader.py │ ├── model_runner.py │ ├── parallel_state.py │ ├── spmd_gpu_executor.py │ ├── tokenizer.py │ └── worker.py ├── tools ├── __init__.py ├── base_tool.py ├── gsm8k_tool.py ├── sandbox_fusion_tools.py ├── schemas.py ├── search_tool.py └── utils │ ├── __init__.py │ └── search_r1_like_utils.py ├── trainer ├── __init__.py ├── config │ ├── evaluation.yaml │ ├── generation.yaml │ ├── ppo_megatron_trainer.yaml │ ├── ppo_trainer.yaml │ └── sft_trainer.yaml ├── fsdp_sft_trainer.py ├── main_eval.py ├── main_generation.py ├── main_ppo.py ├── ppo │ ├── __init__.py │ ├── core_algos.py │ ├── metric_utils.py │ ├── ray_trainer.py │ └── reward.py └── runtime_env.yaml ├── utils ├── __init__.py ├── activation_offload.py ├── checkpoint │ ├── __init__.py │ ├── checkpoint_manager.py │ ├── fsdp_checkpoint_manager.py │ └── megatron_checkpoint_manager.py ├── config.py ├── dataset │ ├── README.md │ ├── __init__.py │ ├── multiturn_sft_dataset.py │ ├── rl_dataset.py │ ├── rm_dataset.py │ ├── sft_dataset.py │ └── vision_utils.py ├── debug │ ├── __init__.py │ ├── performance.py │ ├── profile.py │ └── trajectory_tracker.py ├── device.py ├── distributed.py ├── experimental │ ├── __init__.py │ └── torch_functional.py ├── flops_counter.py ├── fs.py ├── fsdp_utils.py ├── hdfs_io.py ├── import_utils.py ├── logger │ ├── __init__.py │ └── aggregate_logger.py ├── logging_utils.py ├── megatron │ ├── __init__.py │ ├── memory.py │ ├── optimizer.py │ ├── pipeline_parallel.py │ ├── sequence_parallel.py │ └── tensor_parallel.py ├── megatron_utils.py ├── memory_buffer.py ├── metric │ ├── __init__.py │ └── utils.py ├── model.py ├── net_utils.py ├── py_functional.py ├── ray_utils.py ├── rendezvous │ ├── __init__.py │ └── ray_backend.py ├── reward_score │ ├── __init__.py │ ├── geo3k.py │ ├── gsm8k.py │ ├── math.py │ ├── math_batch.py │ ├── math_dapo.py │ ├── math_verify.py │ ├── prime_code │ │ ├── __init__.py │ │ ├── testing_util.py │ │ └── utils.py │ ├── prime_math │ │ ├── __init__.py │ │ ├── grader.py │ │ └── math_normalize.py │ ├── ranking.py │ ├── sandbox_fusion │ │ ├── __init__.py │ │ └── utils.py │ └── search_r1_like_qa_em.py ├── seqlen_balancing.py ├── tokenizer.py ├── torch_dtypes.py ├── torch_functional.py ├── tracking.py ├── ulysses.py └── vllm_utils.py ├── version └── version └── workers ├── __init__.py ├── actor ├── __init__.py ├── base.py ├── dp_actor.py └── megatron_actor.py ├── critic ├── __init__.py ├── base.py ├── dp_critic.py └── megatron_critic.py ├── fsdp_workers.py ├── megatron_workers.py ├── reward_manager ├── __init__.py ├── batch.py ├── dapo.py ├── naive.py └── prime.py ├── reward_model ├── __init__.py ├── base.py └── megatron │ ├── __init__.py │ └── reward_model.py ├── rollout ├── __init__.py ├── async_server.py ├── base.py ├── hf_rollout.py ├── naive │ ├── __init__.py │ └── naive_rollout.py ├── schemas.py ├── sglang_rollout │ ├── __init__.py │ ├── async_sglang_server.py │ ├── sglang_rollout.py │ └── utils.py ├── tokenizer.py └── vllm_rollout │ ├── __init__.py │ ├── fire_vllm_rollout.py │ ├── vllm_async_server.py │ ├── vllm_rollout.py │ └── vllm_rollout_spmd.py └── sharding_manager ├── __init__.py ├── base.py ├── fsdp_sglang.py ├── fsdp_ulysses.py ├── fsdp_vllm.py ├── megatron_sglang.py └── megatron_vllm.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LICENSE -------------------------------------------------------------------------------- /LLaMA-Factory/CITATION.cff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/CITATION.cff -------------------------------------------------------------------------------- /LLaMA-Factory/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/LICENSE -------------------------------------------------------------------------------- /LLaMA-Factory/MANIFEST.in: -------------------------------------------------------------------------------- 1 | include LICENSE requirements.txt 2 | -------------------------------------------------------------------------------- /LLaMA-Factory/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/Makefile -------------------------------------------------------------------------------- /LLaMA-Factory/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/README.md -------------------------------------------------------------------------------- /LLaMA-Factory/README_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/README_zh.md -------------------------------------------------------------------------------- /LLaMA-Factory/assets/alaya_new.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/assets/alaya_new.svg -------------------------------------------------------------------------------- /LLaMA-Factory/assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/assets/logo.png -------------------------------------------------------------------------------- /LLaMA-Factory/assets/wechat.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/assets/wechat.jpg -------------------------------------------------------------------------------- /LLaMA-Factory/assets/wechat_alaya.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/assets/wechat_alaya.png -------------------------------------------------------------------------------- /LLaMA-Factory/assets/wechat_npu.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/assets/wechat_npu.jpg -------------------------------------------------------------------------------- /LLaMA-Factory/data/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/README.md -------------------------------------------------------------------------------- /LLaMA-Factory/data/README_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/README_zh.md -------------------------------------------------------------------------------- /LLaMA-Factory/data/alpaca_en_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/alpaca_en_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/alpaca_zh_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/alpaca_zh_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/belle_multiturn/belle_multiturn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/belle_multiturn/belle_multiturn.py -------------------------------------------------------------------------------- /LLaMA-Factory/data/c4_demo.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/c4_demo.jsonl -------------------------------------------------------------------------------- /LLaMA-Factory/data/dataset_info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/dataset_info.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/dpo_en_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/dpo_en_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/dpo_zh_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/dpo_zh_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/glaive_toolcall_en_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/glaive_toolcall_en_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/glaive_toolcall_zh_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/glaive_toolcall_zh_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/hh_rlhf_en/hh_rlhf_en.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/hh_rlhf_en/hh_rlhf_en.py -------------------------------------------------------------------------------- /LLaMA-Factory/data/identity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/identity.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/kto_en_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/kto_en_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_audio_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_audio_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/1.jpg -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/1.mp3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/1.mp3 -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/1.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/1.mp4 -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/2.avi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/2.avi -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/2.jpg -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/2.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/2.wav -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/3.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/3.flac -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/3.jpg -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/3.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/3.mp4 -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/4.mp3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/4.mp3 -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/4.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_demo_data/4.mp4 -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_video_audio_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_video_audio_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_video_demo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/mllm_video_demo.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/ultra_chat/ultra_chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/ultra_chat/ultra_chat.py -------------------------------------------------------------------------------- /LLaMA-Factory/data/wiki_demo.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/data/wiki_demo.txt -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-cuda/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/docker/docker-cuda/Dockerfile -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-cuda/Dockerfile.base: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/docker/docker-cuda/Dockerfile.base -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-cuda/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/docker/docker-cuda/README.md -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-cuda/docker-compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/docker/docker-cuda/docker-compose.yml -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-npu/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/docker/docker-npu/Dockerfile -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-npu/docker-compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/docker/docker-npu/docker-compose.yml -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-rocm/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/docker/docker-rocm/Dockerfile -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-rocm/docker-compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/docker/docker-rocm/docker-compose.yml -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/ceval/ceval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/evaluation/ceval/ceval.py -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/ceval/ceval.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/evaluation/ceval/ceval.zip -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/ceval/mapping.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/evaluation/ceval/mapping.json -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/cmmlu/cmmlu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/evaluation/cmmlu/cmmlu.py -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/cmmlu/cmmlu.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/evaluation/cmmlu/cmmlu.zip -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/cmmlu/mapping.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/evaluation/cmmlu/mapping.json -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/mmlu/mapping.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/evaluation/mmlu/mapping.json -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/mmlu/mmlu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/evaluation/mmlu/mmlu.py -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/mmlu/mmlu.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/evaluation/mmlu/mmlu.zip -------------------------------------------------------------------------------- /LLaMA-Factory/examples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/README.md -------------------------------------------------------------------------------- /LLaMA-Factory/examples/README_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/README_zh.md -------------------------------------------------------------------------------- /LLaMA-Factory/examples/accelerate/fsdp_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/accelerate/fsdp_config.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/accelerate/fsdp_config_offload.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/accelerate/fsdp_config_offload.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/deepspeed/ds_z0_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/deepspeed/ds_z0_config.json -------------------------------------------------------------------------------- /LLaMA-Factory/examples/deepspeed/ds_z2_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/deepspeed/ds_z2_config.json -------------------------------------------------------------------------------- /LLaMA-Factory/examples/deepspeed/ds_z2_offload_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/deepspeed/ds_z2_offload_config.json -------------------------------------------------------------------------------- /LLaMA-Factory/examples/deepspeed/ds_z3_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/deepspeed/ds_z3_config.json -------------------------------------------------------------------------------- /LLaMA-Factory/examples/deepspeed/ds_z3_offload_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/deepspeed/ds_z3_offload_config.json -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/adam_mini/qwen2_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/adam_mini/qwen2_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/apollo/llama3_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/apollo/llama3_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/badam/llama3_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/badam/llama3_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/fsdp_qlora/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/fsdp_qlora/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/fsdp_qlora/train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/fsdp_qlora/train.sh -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/galore/llama3_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/galore/llama3_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/llama_pro/expand.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/llama_pro/expand.sh -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/llama_pro/llama3_freeze_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/llama_pro/llama3_freeze_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/loraplus/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/loraplus/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/mod/llama3_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/mod/llama3_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/muon/qwen2_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/muon/qwen2_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/pissa/init.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/pissa/init.sh -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/pissa/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/extras/pissa/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/inference/llama3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/inference/llama3.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/inference/llama3_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/inference/llama3_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/inference/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/inference/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/inference/qwen2_5vl.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/inference/qwen2_5vl.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/merge_lora/llama3_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/merge_lora/llama3_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/merge_lora/llama3_gptq.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/merge_lora/llama3_gptq.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/merge_lora/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/merge_lora/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/merge_lora/qwen2_5vl_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/merge_lora/qwen2_5vl_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/merge_lora/qwen_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/merge_lora/qwen_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_full/llama3_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_full/llama3_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_full/qwen2_5vl_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_full/qwen2_5vl_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_full/qwen_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_full/qwen_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_dpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_dpo.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_eval.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_eval.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_kto.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_kto.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_ppo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_ppo.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_pretrain.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_pretrain.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_reward.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_reward.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_sft.sh -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_sft_ds3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_sft_ds3.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_sft_ray.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_sft_ray.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_preprocess.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama3_preprocess.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama4_lora_sft_ds3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/llama4_lora_sft_ds3.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/qwen2_5vl_lora_dpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/qwen2_5vl_lora_dpo.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/qwen2_5vl_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/qwen2_5vl_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/qwen_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_lora/qwen_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_qlora/llama3_lora_sft_aqlm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_qlora/llama3_lora_sft_aqlm.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_qlora/llama3_lora_sft_awq.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_qlora/llama3_lora_sft_awq.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_qlora/llama3_lora_sft_gptq.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_qlora/llama3_lora_sft_gptq.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_qlora/llama3_lora_sft_otfq.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/examples/train_qlora/llama3_lora_sft_otfq.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/pyproject.toml -------------------------------------------------------------------------------- /LLaMA-Factory/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/requirements.txt -------------------------------------------------------------------------------- /LLaMA-Factory/run_train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/run_train.sh -------------------------------------------------------------------------------- /LLaMA-Factory/run_train_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/run_train_lora.sh -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/api_example/test_image.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/api_example/test_image.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/api_example/test_toolcall.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/api_example/test_toolcall.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/convert_ckpt/llamafy_baichuan2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/convert_ckpt/llamafy_baichuan2.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/convert_ckpt/llamafy_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/convert_ckpt/llamafy_qwen.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/convert_ckpt/tiny_llama4.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/convert_ckpt/tiny_llama4.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/eval_bleu_rouge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/eval_bleu_rouge.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/llama_pro.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/llama_pro.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/loftq_init.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/loftq_init.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/pissa_init.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/pissa_init.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/qwen_omni_merge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/qwen_omni_merge.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/stat_utils/cal_flops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/stat_utils/cal_flops.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/stat_utils/cal_lr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/stat_utils/cal_lr.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/stat_utils/cal_mfu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/stat_utils/cal_mfu.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/stat_utils/cal_ppl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/stat_utils/cal_ppl.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/stat_utils/length_cdf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/stat_utils/length_cdf.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/vllm_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/scripts/vllm_infer.py -------------------------------------------------------------------------------- /LLaMA-Factory/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/setup.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/api.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/api/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/api/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/api/app.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/api/chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/api/chat.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/api/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/api/common.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/api/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/api/protocol.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/chat/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/base_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/chat/base_engine.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/chat_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/chat/chat_model.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/hf_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/chat/hf_engine.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/sglang_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/chat/sglang_engine.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/vllm_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/chat/vllm_engine.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/cli.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/collator.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/converter.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/data_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/formatter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/formatter.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/loader.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/mm_plugin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/mm_plugin.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/parser.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/processor/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processor/feedback.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/processor/feedback.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processor/pairwise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/processor/pairwise.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processor/pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/processor/pretrain.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processor/supervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/processor/supervised.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processor/unsupervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/processor/unsupervised.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/template.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/tool_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/data/tool_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/eval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/eval/evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/eval/evaluator.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/eval/template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/eval/template.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/extras/constants.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/extras/env.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/extras/logging.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/extras/misc.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/packages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/extras/packages.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/ploting.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/extras/ploting.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/hparams/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/data_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/hparams/data_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/evaluation_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/hparams/evaluation_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/finetuning_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/hparams/finetuning_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/generating_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/hparams/generating_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/model_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/hparams/model_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/hparams/parser.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/training_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/hparams/training_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/launcher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/launcher.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/adapter.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/loader.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/attention.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/embedding.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/kv_cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/kv_cache.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/longlora.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/longlora.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/misc.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/mod.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/mod.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/moe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/moe.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/packing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/packing.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/rope.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/rope.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/unsloth.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/unsloth.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/valuehead.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/valuehead.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/visual.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/visual.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/patcher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/model/patcher.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/third_party/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/third_party/muon/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/third_party/muon/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/third_party/muon/muon.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/third_party/muon/muon.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/callbacks.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/dpo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/dpo/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/dpo/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/dpo/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/dpo/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/dpo/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/kto/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/kto/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/kto/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/kto/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/kto/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/kto/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/ppo/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/ppo/ppo_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/ppo/ppo_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/ppo/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/ppo/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/ppo/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/ppo/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/pt/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/pt/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/pt/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/pt/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/pt/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/pt/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/rm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/rm/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/rm/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/rm/metric.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/rm/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/rm/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/rm/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/rm/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/sft/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/sft/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/sft/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/sft/metric.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/sft/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/sft/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/sft/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/sft/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/test_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/trainer_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/trainer_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/tuner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/train/tuner.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/chatter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/chatter.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/common.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/components/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/chatbot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/components/chatbot.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/components/data.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/components/eval.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/export.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/components/export.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/footer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/components/footer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/components/infer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/top.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/components/top.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/components/train.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/control.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/control.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/css.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/css.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/engine.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/interface.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/interface.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/locales.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/locales.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/manager.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/llamafactory/webui/runner.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/train.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/webui.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/src/webui.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/check_license.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/check_license.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/processor/test_feedback.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/processor/test_feedback.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/processor/test_pairwise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/processor/test_pairwise.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/processor/test_processor_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/processor/test_processor_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/processor/test_supervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/processor/test_supervised.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/processor/test_unsupervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/processor/test_unsupervised.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/test_collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/test_collator.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/test_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/test_converter.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/test_formatter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/test_formatter.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/test_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/test_loader.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/test_mm_plugin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/test_mm_plugin.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/test_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/data/test_template.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/e2e/test_chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/e2e/test_chat.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/e2e/test_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/e2e/test_sglang.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/e2e/test_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/e2e/test_train.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/eval/test_eval_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/eval/test_eval_template.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/model_utils/test_add_tokens.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/model_utils/test_add_tokens.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/model_utils/test_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/model_utils/test_attention.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/model_utils/test_checkpointing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/model_utils/test_checkpointing.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/model_utils/test_misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/model_utils/test_misc.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/model_utils/test_packing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/model_utils/test_packing.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/model_utils/test_visual.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/model_utils/test_visual.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/test_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/test_base.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/test_freeze.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/test_freeze.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/test_full.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/test_full.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/test_lora.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/test_lora.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/test_pissa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/model/test_pissa.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/train/test_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/train/test_sft_trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/version.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/LLaMA-Factory/tests/version.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/README.md -------------------------------------------------------------------------------- /__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/config.py -------------------------------------------------------------------------------- /data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/data.py -------------------------------------------------------------------------------- /index_and_topics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/index_and_topics.py -------------------------------------------------------------------------------- /listwise_prompt_r1.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/listwise_prompt_r1.toml -------------------------------------------------------------------------------- /rerank/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rerank/api_keys.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/rerank/api_keys.py -------------------------------------------------------------------------------- /rerank/rank_gpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/rerank/rank_gpt.py -------------------------------------------------------------------------------- /rerank/rank_listwise_os_llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/rerank/rank_listwise_os_llm.py -------------------------------------------------------------------------------- /rerank/rankllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/rerank/rankllm.py -------------------------------------------------------------------------------- /rerank/reranker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/rerank/reranker.py -------------------------------------------------------------------------------- /results/economics.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/results/economics.json -------------------------------------------------------------------------------- /results/robotics.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/results/robotics.json -------------------------------------------------------------------------------- /run_rank_llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/run_rank_llm.py -------------------------------------------------------------------------------- /run_rank_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/run_rank_llm.sh -------------------------------------------------------------------------------- /runs/economics/custom.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/runs/economics/custom.txt -------------------------------------------------------------------------------- /runs/economics/reasonir_gpt4cot_top100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/runs/economics/reasonir_gpt4cot_top100.txt -------------------------------------------------------------------------------- /trec_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/trec_eval.py -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/utils.py -------------------------------------------------------------------------------- /verl/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/LICENSE -------------------------------------------------------------------------------- /verl/Notice.txt: -------------------------------------------------------------------------------- 1 | Copyright 2023-2024 Bytedance Ltd. and/or its affiliates -------------------------------------------------------------------------------- /verl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/README.md -------------------------------------------------------------------------------- /verl/docker/Apptainerfile.rocm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docker/Apptainerfile.rocm -------------------------------------------------------------------------------- /verl/docker/Dockerfile.awsefa: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docker/Dockerfile.awsefa -------------------------------------------------------------------------------- /verl/docker/Dockerfile.ngc.vllm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docker/Dockerfile.ngc.vllm -------------------------------------------------------------------------------- /verl/docker/Dockerfile.ngc.vllm0.8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docker/Dockerfile.ngc.vllm0.8 -------------------------------------------------------------------------------- /verl/docker/Dockerfile.ngc.vllm0.8.sagemaker: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docker/Dockerfile.ngc.vllm0.8.sagemaker -------------------------------------------------------------------------------- /verl/docker/Dockerfile.rocm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docker/Dockerfile.rocm -------------------------------------------------------------------------------- /verl/docker/Dockerfile.sglang: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docker/Dockerfile.sglang -------------------------------------------------------------------------------- /verl/docker/Dockerfile.vemlp.vllm.te: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docker/Dockerfile.vemlp.vllm.te -------------------------------------------------------------------------------- /verl/docker/Dockerfile.vllm.sglang.megatron: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docker/Dockerfile.vllm.sglang.megatron -------------------------------------------------------------------------------- /verl/docker/Dockerfile.vllm.sglang.megatron.deepseek: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docker/Dockerfile.vllm.sglang.megatron.deepseek -------------------------------------------------------------------------------- /verl/docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/Makefile -------------------------------------------------------------------------------- /verl/docs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/README.md -------------------------------------------------------------------------------- /verl/docs/README_vllm0.7.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/README_vllm0.7.md -------------------------------------------------------------------------------- /verl/docs/README_vllm0.8.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/README_vllm0.8.md -------------------------------------------------------------------------------- /verl/docs/_static/js/runllm-widget.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/_static/js/runllm-widget.js -------------------------------------------------------------------------------- /verl/docs/_static/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/_static/logo.png -------------------------------------------------------------------------------- /verl/docs/advance/checkpoint.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/advance/checkpoint.rst -------------------------------------------------------------------------------- /verl/docs/advance/dpo_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/advance/dpo_extension.rst -------------------------------------------------------------------------------- /verl/docs/advance/fsdp_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/advance/fsdp_extension.rst -------------------------------------------------------------------------------- /verl/docs/advance/megatron_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/advance/megatron_extension.rst -------------------------------------------------------------------------------- /verl/docs/advance/placement.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/advance/placement.rst -------------------------------------------------------------------------------- /verl/docs/advance/ppo_lora.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/advance/ppo_lora.rst -------------------------------------------------------------------------------- /verl/docs/advance/rope.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/advance/rope.rst -------------------------------------------------------------------------------- /verl/docs/algo/baseline.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/algo/baseline.md -------------------------------------------------------------------------------- /verl/docs/algo/dapo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/algo/dapo.md -------------------------------------------------------------------------------- /verl/docs/algo/grpo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/algo/grpo.md -------------------------------------------------------------------------------- /verl/docs/algo/opo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/algo/opo.md -------------------------------------------------------------------------------- /verl/docs/algo/ppo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/algo/ppo.md -------------------------------------------------------------------------------- /verl/docs/algo/spin.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/algo/spin.md -------------------------------------------------------------------------------- /verl/docs/algo/sppo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/algo/sppo.md -------------------------------------------------------------------------------- /verl/docs/amd_tutorial/amd_build_dockerfile_page.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/amd_tutorial/amd_build_dockerfile_page.rst -------------------------------------------------------------------------------- /verl/docs/amd_tutorial/amd_vllm_page.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/amd_tutorial/amd_vllm_page.rst -------------------------------------------------------------------------------- /verl/docs/api/data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/api/data.rst -------------------------------------------------------------------------------- /verl/docs/api/single_controller.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/api/single_controller.rst -------------------------------------------------------------------------------- /verl/docs/api/trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/api/trainer.rst -------------------------------------------------------------------------------- /verl/docs/api/utils.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/api/utils.rst -------------------------------------------------------------------------------- /verl/docs/ascend_tutorial/ascend_quick_start.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/ascend_tutorial/ascend_quick_start.rst -------------------------------------------------------------------------------- /verl/docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/conf.py -------------------------------------------------------------------------------- /verl/docs/examples/config.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/examples/config.rst -------------------------------------------------------------------------------- /verl/docs/examples/gsm8k_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/examples/gsm8k_example.rst -------------------------------------------------------------------------------- /verl/docs/examples/multi_modal_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/examples/multi_modal_example.rst -------------------------------------------------------------------------------- /verl/docs/examples/ppo_code_architecture.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/examples/ppo_code_architecture.rst -------------------------------------------------------------------------------- /verl/docs/examples/sandbox_fusion_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/examples/sandbox_fusion_example.rst -------------------------------------------------------------------------------- /verl/docs/faq/faq.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/faq/faq.rst -------------------------------------------------------------------------------- /verl/docs/hybrid_flow.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/hybrid_flow.rst -------------------------------------------------------------------------------- /verl/docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/index.rst -------------------------------------------------------------------------------- /verl/docs/perf/device_tuning.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/perf/device_tuning.rst -------------------------------------------------------------------------------- /verl/docs/perf/perf_tuning.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/perf/perf_tuning.rst -------------------------------------------------------------------------------- /verl/docs/preparation/prepare_data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/preparation/prepare_data.rst -------------------------------------------------------------------------------- /verl/docs/preparation/reward_function.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/preparation/reward_function.rst -------------------------------------------------------------------------------- /verl/docs/requirements-docs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/requirements-docs.txt -------------------------------------------------------------------------------- /verl/docs/sglang_multiturn/multiturn.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/sglang_multiturn/multiturn.rst -------------------------------------------------------------------------------- /verl/docs/sglang_multiturn/sandbox_fusion.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/sglang_multiturn/sandbox_fusion.rst -------------------------------------------------------------------------------- /verl/docs/sglang_multiturn/search_tool_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/sglang_multiturn/search_tool_example.rst -------------------------------------------------------------------------------- /verl/docs/single_controller.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/single_controller.rst -------------------------------------------------------------------------------- /verl/docs/start/install.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/start/install.rst -------------------------------------------------------------------------------- /verl/docs/start/multinode.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/start/multinode.rst -------------------------------------------------------------------------------- /verl/docs/start/quickstart.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/start/quickstart.rst -------------------------------------------------------------------------------- /verl/docs/start/ray_debug_tutorial.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/start/ray_debug_tutorial.rst -------------------------------------------------------------------------------- /verl/docs/workers/fsdp_workers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/workers/fsdp_workers.rst -------------------------------------------------------------------------------- /verl/docs/workers/megatron_workers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/workers/megatron_workers.rst -------------------------------------------------------------------------------- /verl/docs/workers/ray_trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/workers/ray_trainer.rst -------------------------------------------------------------------------------- /verl/docs/workers/sglang_worker.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/docs/workers/sglang_worker.rst -------------------------------------------------------------------------------- /verl/examples/data_preprocess/aime2024_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/data_preprocess/aime2024_multiturn_w_tool.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/dapo_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/data_preprocess/dapo_multiturn_w_tool.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/full_hh_rlhf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/data_preprocess/full_hh_rlhf.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/geo3k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/data_preprocess/geo3k.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/data_preprocess/gsm8k.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/gsm8k_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/data_preprocess/gsm8k_multiturn_w_tool.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/hellaswag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/data_preprocess/hellaswag.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/math_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/data_preprocess/math_dataset.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/multiturn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/data_preprocess/multiturn.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/preprocess_search_r1_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/data_preprocess/preprocess_search_r1_dataset.py -------------------------------------------------------------------------------- /verl/examples/generation/run_deepseek7b_mutli_node.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/generation/run_deepseek7b_mutli_node.sh -------------------------------------------------------------------------------- /verl/examples/generation/run_deepseek_v2_lite_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/generation/run_deepseek_v2_lite_math.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/README.md -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_deepseek671b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_deepseek671b_math_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_deepseek7b_llm_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_deepseek7b_llm_math.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_deepseek7b_llm_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_deepseek7b_llm_math_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_deepseek7b_llm_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_deepseek7b_llm_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_moonlight16b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_moonlight16b_math_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_qwen2-7b.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_qwen2-7b_math.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_qwen2-7b_math_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_qwen2-7b_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b_sgl_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_qwen2-7b_sgl_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2_5-3b_gsm8k_grpo_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_qwen2_5-3b_gsm8k_grpo_lora.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2_5_vl-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_qwen2_5_vl-7b.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen3-236b_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_qwen3-236b_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen3-8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_qwen3-8b.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen3moe-30b_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/grpo_trainer/run_qwen3moe-30b_megatron.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/README.md -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/naive_chat_scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/naive_chat_scheduler.py -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek7b_llm_modelscope.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_deepseek7b_llm_modelscope.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek7b_llm_pfppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_deepseek7b_llm_pfppo.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek7b_llm_sandbox_fusion.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_deepseek7b_llm_sandbox_fusion.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek7b_llm_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_deepseek7b_llm_sp2.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek_math_gsm8k_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_deepseek_math_gsm8k_megatron.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_gemma.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_gemma.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2-7b_rm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_qwen2-7b_rm.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_qwen2-7b_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2.5-32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ppo_trainer/run_qwen2.5-32b.sh -------------------------------------------------------------------------------- /verl/examples/ray/tutorial.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/ray/tutorial.ipynb -------------------------------------------------------------------------------- /verl/examples/remax_trainer/run_qwen2.5-3b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/remax_trainer/run_qwen2.5-3b_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/remax_trainer/run_qwen2.5-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/remax_trainer/run_qwen2.5-7b_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/rloo_trainer/run_qwen2-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/rloo_trainer/run_qwen2-7b.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_deepseek_6b7.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/sft/gsm8k/run_deepseek_6b7.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_gemma_2b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/sft/gsm8k/run_gemma_2b.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_gemma_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/sft/gsm8k/run_gemma_7b.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_qwen_05_peft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/sft/gsm8k/run_qwen_05_peft.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_qwen_05_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/sft/gsm8k/run_qwen_05_sp2.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_qwen_05_sp2_liger.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/sft/gsm8k/run_qwen_05_sp2_liger.sh -------------------------------------------------------------------------------- /verl/examples/sft/multiturn/run_qwen_05_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/sft/multiturn/run_qwen_05_sp2.sh -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/sglang_multiturn/README.md -------------------------------------------------------------------------------- /verl/examples/slurm/ray_on_slurm.slurm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/slurm/ray_on_slurm.slurm -------------------------------------------------------------------------------- /verl/examples/split_placement/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/split_placement/README.md -------------------------------------------------------------------------------- /verl/examples/split_placement/config/ppo_trainer_split.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/split_placement/config/ppo_trainer_split.yaml -------------------------------------------------------------------------------- /verl/examples/split_placement/main_ppo_split.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/split_placement/main_ppo_split.py -------------------------------------------------------------------------------- /verl/examples/split_placement/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/split_placement/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /verl/examples/split_placement/split_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/split_placement/split_monkey_patch.py -------------------------------------------------------------------------------- /verl/examples/tuning/14b/qwen2_14b_grpo_4_h800_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/tuning/14b/qwen2_14b_grpo_4_h800_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/70b/qwen2-70b_grpo_32_h20_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/tuning/70b/qwen2-70b_grpo_32_h20_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/7b/qwen2-7b_grpo_2_h800_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/examples/tuning/7b/qwen2-7b_grpo_2_h800_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/pyproject.toml -------------------------------------------------------------------------------- /verl/recipe/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/README.md -------------------------------------------------------------------------------- /verl/recipe/dapo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/README.md -------------------------------------------------------------------------------- /verl/recipe/dapo/config/dapo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/config/dapo_trainer.yaml -------------------------------------------------------------------------------- /verl/recipe/dapo/dapo_ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/dapo_ray_trainer.py -------------------------------------------------------------------------------- /verl/recipe/dapo/main_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/main_dapo.py -------------------------------------------------------------------------------- /verl/recipe/dapo/prepare_dapo_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/prepare_dapo_data.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/run_dapo_early_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/run_dapo_early_qwen2.5_32b.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/run_dapo_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/run_dapo_qwen2.5_32b.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/run_dapo_wo_ds_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/run_dapo_wo_ds_qwen2.5_32b.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/test_dapo_7b.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_7b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/test_dapo_7b_math.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_7b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/test_dapo_7b_math_megatron.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_qwen3_30b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/dapo/test_dapo_qwen3_30b_math.sh -------------------------------------------------------------------------------- /verl/recipe/prime/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/prime/__init__.py -------------------------------------------------------------------------------- /verl/recipe/prime/config/prime_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/prime/config/prime_trainer.yaml -------------------------------------------------------------------------------- /verl/recipe/prime/main_prime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/prime/main_prime.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/prime/prime_core_algos.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_dp_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/prime/prime_dp_rm.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/prime/prime_fsdp_workers.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/prime/prime_ray_trainer.py -------------------------------------------------------------------------------- /verl/recipe/prime/run_prime_qwen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/prime/run_prime_qwen.sh -------------------------------------------------------------------------------- /verl/recipe/prime/run_prime_qwen_code.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/prime/run_prime_qwen_code.sh -------------------------------------------------------------------------------- /verl/recipe/r1/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/README.md -------------------------------------------------------------------------------- /verl/recipe/r1/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/__init__.py -------------------------------------------------------------------------------- /verl/recipe/r1/config/evaluation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/config/evaluation.yaml -------------------------------------------------------------------------------- /verl/recipe/r1/data_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/data_process.py -------------------------------------------------------------------------------- /verl/recipe/r1/main_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/main_eval.py -------------------------------------------------------------------------------- /verl/recipe/r1/reward_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/reward_score.py -------------------------------------------------------------------------------- /verl/recipe/r1/run_r1_distill_qwen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/run_r1_distill_qwen.sh -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/tasks/__init__.py -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/gpqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/tasks/gpqa.py -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/livecodebench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/tasks/livecodebench.py -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/r1/tasks/math.py -------------------------------------------------------------------------------- /verl/recipe/retool/run_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/retool/run_sft.sh -------------------------------------------------------------------------------- /verl/recipe/spin/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/spin/README.md -------------------------------------------------------------------------------- /verl/recipe/spin/config/spin_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/spin/config/spin_trainer.yaml -------------------------------------------------------------------------------- /verl/recipe/spin/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/spin/core_algos.py -------------------------------------------------------------------------------- /verl/recipe/spin/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/spin/dp_actor.py -------------------------------------------------------------------------------- /verl/recipe/spin/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/spin/fsdp_workers.py -------------------------------------------------------------------------------- /verl/recipe/spin/main_spin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/spin/main_spin.py -------------------------------------------------------------------------------- /verl/recipe/spin/run_spin.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/spin/run_spin.sh -------------------------------------------------------------------------------- /verl/recipe/spin/spin_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/spin/spin_trainer.py -------------------------------------------------------------------------------- /verl/recipe/sppo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/sppo/README.md -------------------------------------------------------------------------------- /verl/recipe/sppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/sppo/__init__.py -------------------------------------------------------------------------------- /verl/recipe/sppo/config/sppo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/sppo/config/sppo_trainer.yaml -------------------------------------------------------------------------------- /verl/recipe/sppo/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/sppo/dp_actor.py -------------------------------------------------------------------------------- /verl/recipe/sppo/main_sppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/sppo/main_sppo.py -------------------------------------------------------------------------------- /verl/recipe/sppo/run_qwen2.5-7b_rm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/sppo/run_qwen2.5-7b_rm.sh -------------------------------------------------------------------------------- /verl/recipe/sppo/sppo_ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/sppo/sppo_ray_trainer.py -------------------------------------------------------------------------------- /verl/recipe/sppo/sppo_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/recipe/sppo/sppo_worker.py -------------------------------------------------------------------------------- /verl/requirements-npu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/requirements-npu.txt -------------------------------------------------------------------------------- /verl/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/requirements.txt -------------------------------------------------------------------------------- /verl/requirements_sglang.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/requirements_sglang.txt -------------------------------------------------------------------------------- /verl/scripts/converter_hf_to_mcore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/scripts/converter_hf_to_mcore.py -------------------------------------------------------------------------------- /verl/scripts/diagnose.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/scripts/diagnose.py -------------------------------------------------------------------------------- /verl/scripts/init_random_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/scripts/init_random_model.py -------------------------------------------------------------------------------- /verl/scripts/install_vllm_sglang_mcore.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/scripts/install_vllm_sglang_mcore.sh -------------------------------------------------------------------------------- /verl/scripts/legacy_model_merger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/scripts/legacy_model_merger.py -------------------------------------------------------------------------------- /verl/scripts/merge.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/scripts/merge.sh -------------------------------------------------------------------------------- /verl/scripts/model_merger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/scripts/model_merger.py -------------------------------------------------------------------------------- /verl/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/setup.py -------------------------------------------------------------------------------- /verl/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/__init__.py -------------------------------------------------------------------------------- /verl/tests/distributed/run_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/distributed/run_all.sh -------------------------------------------------------------------------------- /verl/tests/distributed/test_tensor_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/distributed/test_tensor_dict.py -------------------------------------------------------------------------------- /verl/tests/e2e/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/__init__.py -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/data/create_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/arithmetic_sequence/data/create_dataset.py -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/data/test.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/arithmetic_sequence/data/test.parquet -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/data/train.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/arithmetic_sequence/data/train.parquet -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/model/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/arithmetic_sequence/model/config.json -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/model/model.safetensors: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/arithmetic_sequence/model/model.safetensors -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/rl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/arithmetic_sequence/rl/README.md -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/rl/main_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/arithmetic_sequence/rl/main_trainer.py -------------------------------------------------------------------------------- /verl/tests/e2e/check_custom_rwd_fn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/check_custom_rwd_fn.py -------------------------------------------------------------------------------- /verl/tests/e2e/check_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/check_results.py -------------------------------------------------------------------------------- /verl/tests/e2e/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/envs/__init__.py -------------------------------------------------------------------------------- /verl/tests/e2e/envs/digit_completion/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/envs/digit_completion/__init__.py -------------------------------------------------------------------------------- /verl/tests/e2e/envs/digit_completion/task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/envs/digit_completion/task.py -------------------------------------------------------------------------------- /verl/tests/e2e/envs/digit_completion/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/envs/digit_completion/tokenizer.py -------------------------------------------------------------------------------- /verl/tests/e2e/generation/run_gen_qwen05.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/generation/run_gen_qwen05.sh -------------------------------------------------------------------------------- /verl/tests/e2e/ppo_trainer/run_function_reward.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/ppo_trainer/run_function_reward.sh -------------------------------------------------------------------------------- /verl/tests/e2e/ppo_trainer/run_model_reward.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/ppo_trainer/run_model_reward.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_dapo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_dapo.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_gsm8k_fsdp_sgl_multiturn_sf_tool.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_gsm8k_fsdp_sgl_multiturn_sf_tool.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_gsm8k_fsdp_sgl_multiturn_w_tool.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_gsm8k_fsdp_sgl_multiturn_w_tool.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_ppo_trainer_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_ppo_trainer_megatron.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_prime.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_prime.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_r1_distill_qwen_aime24_eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_r1_distill_qwen_aime24_eval.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_ray_trainer.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_ray_trainer.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_ray_trainer_fire_sampling.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_ray_trainer_fire_sampling.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_ray_trainer_rmpad.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_ray_trainer_rmpad.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_spin.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_spin.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_sppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_sppo.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/run_test.sh -------------------------------------------------------------------------------- /verl/tests/e2e/sft/run_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/sft/run_sft.sh -------------------------------------------------------------------------------- /verl/tests/e2e/sft/test_sp_loss_match.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/e2e/sft/test_sp_loss_match.py -------------------------------------------------------------------------------- /verl/tests/gpu_utility/test_memory_buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/gpu_utility/test_memory_buffers.py -------------------------------------------------------------------------------- /verl/tests/gpu_utility/test_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/gpu_utility/test_ops.py -------------------------------------------------------------------------------- /verl/tests/gpu_utility/test_torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/gpu_utility/test_torch_functional.py -------------------------------------------------------------------------------- /verl/tests/kernels/test_linear_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/kernels/test_linear_cross_entropy.py -------------------------------------------------------------------------------- /verl/tests/kill_github_tests.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/kill_github_tests.sh -------------------------------------------------------------------------------- /verl/tests/models/test_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/models/test_transformer.py -------------------------------------------------------------------------------- /verl/tests/models/test_transformers_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/models/test_transformers_ulysses.py -------------------------------------------------------------------------------- /verl/tests/npu/run_qwen2_5_05b_dapo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/npu/run_qwen2_5_05b_dapo.sh -------------------------------------------------------------------------------- /verl/tests/npu/run_qwen2_5_05b_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/npu/run_qwen2_5_05b_grpo.sh -------------------------------------------------------------------------------- /verl/tests/npu/run_qwen2_5_32b_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/npu/run_qwen2_5_32b_grpo.sh -------------------------------------------------------------------------------- /verl/tests/npu/run_qwen2_5_7b_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/npu/run_qwen2_5_7b_grpo.sh -------------------------------------------------------------------------------- /verl/tests/ray_cpu/check_worker_alive/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_cpu/check_worker_alive/main.py -------------------------------------------------------------------------------- /verl/tests/ray_cpu/test_auto_padding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_cpu/test_auto_padding.py -------------------------------------------------------------------------------- /verl/tests/ray_cpu/test_check_worker_alive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_cpu/test_check_worker_alive.py -------------------------------------------------------------------------------- /verl/tests/ray_cpu/test_decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_cpu/test_decorator.py -------------------------------------------------------------------------------- /verl/tests/ray_cpu/test_fused_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_cpu/test_fused_workers.py -------------------------------------------------------------------------------- /verl/tests/ray_cpu/test_ray_local_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_cpu/test_ray_local_envs.py -------------------------------------------------------------------------------- /verl/tests/ray_cpu/test_ray_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_cpu/test_ray_utils.py -------------------------------------------------------------------------------- /verl/tests/ray_gpu/detached_worker/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/detached_worker/README.md -------------------------------------------------------------------------------- /verl/tests/ray_gpu/detached_worker/client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/detached_worker/client.py -------------------------------------------------------------------------------- /verl/tests/ray_gpu/detached_worker/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/detached_worker/run.sh -------------------------------------------------------------------------------- /verl/tests/ray_gpu/detached_worker/server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/detached_worker/server.py -------------------------------------------------------------------------------- /verl/tests/ray_gpu/test_colocated_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/test_colocated_workers.py -------------------------------------------------------------------------------- /verl/tests/ray_gpu/test_colocated_workers_fused.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/test_colocated_workers_fused.py -------------------------------------------------------------------------------- /verl/tests/ray_gpu/test_data_transfer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/test_data_transfer.py -------------------------------------------------------------------------------- /verl/tests/ray_gpu/test_driverfunc_to_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/test_driverfunc_to_worker.py -------------------------------------------------------------------------------- /verl/tests/ray_gpu/test_high_level_scheduling_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/test_high_level_scheduling_api.py -------------------------------------------------------------------------------- /verl/tests/ray_gpu/test_rvdz.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/test_rvdz.py -------------------------------------------------------------------------------- /verl/tests/ray_gpu/test_worker_group_basics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/test_worker_group_basics.py -------------------------------------------------------------------------------- /verl/tests/ray_gpu/test_worker_group_torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/ray_gpu/test_worker_group_torch.py -------------------------------------------------------------------------------- /verl/tests/reward_score/test_sandbox_fusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/reward_score/test_sandbox_fusion.py -------------------------------------------------------------------------------- /verl/tests/sandbox/test_sandbox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/sandbox/test_sandbox.py -------------------------------------------------------------------------------- /verl/tests/sanity/check_license.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/sanity/check_license.py -------------------------------------------------------------------------------- /verl/tests/sanity/test_import.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/sanity/test_import.py -------------------------------------------------------------------------------- /verl/tests/single_controller/base/test_decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/single_controller/base/test_decorator.py -------------------------------------------------------------------------------- /verl/tests/test_protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/test_protocol.py -------------------------------------------------------------------------------- /verl/tests/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/trainer/__init__.py -------------------------------------------------------------------------------- /verl/tests/trainer/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/trainer/ppo/__init__.py -------------------------------------------------------------------------------- /verl/tests/trainer/ppo/test_metric_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/trainer/ppo/test_metric_utils.py -------------------------------------------------------------------------------- /verl/tests/utils/cpu_tests/_test_module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/cpu_tests/_test_module.py -------------------------------------------------------------------------------- /verl/tests/utils/cpu_tests/test_fs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/cpu_tests/test_fs.py -------------------------------------------------------------------------------- /verl/tests/utils/cpu_tests/test_import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/cpu_tests/test_import_utils.py -------------------------------------------------------------------------------- /verl/tests/utils/cpu_tests/test_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/cpu_tests/test_model.py -------------------------------------------------------------------------------- /verl/tests/utils/cpu_tests/test_timeout_decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/cpu_tests/test_timeout_decorator.py -------------------------------------------------------------------------------- /verl/tests/utils/gpu_tests/checkpoint/test_fsdp_ckpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/gpu_tests/checkpoint/test_fsdp_ckpt.py -------------------------------------------------------------------------------- /verl/tests/utils/gpu_tests/dataset/test_rl_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/gpu_tests/dataset/test_rl_dataset.py -------------------------------------------------------------------------------- /verl/tests/utils/gpu_tests/dataset/test_rm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/gpu_tests/dataset/test_rm_dataset.py -------------------------------------------------------------------------------- /verl/tests/utils/gpu_tests/dataset/test_sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/gpu_tests/dataset/test_sft_dataset.py -------------------------------------------------------------------------------- /verl/tests/utils/gpu_tests/test_activation_offload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/gpu_tests/test_activation_offload.py -------------------------------------------------------------------------------- /verl/tests/utils/gpu_tests/test_flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/gpu_tests/test_flops_counter.py -------------------------------------------------------------------------------- /verl/tests/utils/gpu_tests/test_seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/gpu_tests/test_seqlen_balancing.py -------------------------------------------------------------------------------- /verl/tests/utils/gpu_tests/test_torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/utils/gpu_tests/test_torch_functional.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/async_rollout_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/workers/rollout/async_rollout_utils.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/run_fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/workers/rollout/run_fsdp_vllm.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_async_sglang_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/workers/rollout/test_async_sglang_server.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_hf_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/workers/rollout/test_hf_rollout.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_sglang_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/workers/rollout/test_sglang_spmd.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_vllm_hf_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/workers/rollout/test_vllm_hf_loader.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_vllm_multi_turn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/workers/rollout/test_vllm_multi_turn.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_vllm_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/workers/rollout/test_vllm_spmd.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_vllm_tool_calling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/workers/rollout/test_vllm_tool_calling.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/utils_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/tests/workers/rollout/utils_sglang.py -------------------------------------------------------------------------------- /verl/train_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/train_grpo.sh -------------------------------------------------------------------------------- /verl/train_grpo_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/train_grpo_lora.sh -------------------------------------------------------------------------------- /verl/verl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/README.md -------------------------------------------------------------------------------- /verl/verl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/llama/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/llama/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/llama/megatron/layers/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/llama/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/llama/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/llama/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/llama/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/modeling_llama_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/llama/megatron/modeling_llama_megatron.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/config_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/config_converter.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/loader.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/model_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/model_forward.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/model_initializer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/model_initializer.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/patch_v012.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/patch_v012.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/readme.md -------------------------------------------------------------------------------- /verl/verl/models/mcore/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/registry.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/saver.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/util.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/weight_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/mcore/weight_converter.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/qwen2/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/qwen2/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/qwen2/megatron/layers/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py -------------------------------------------------------------------------------- /verl/verl/models/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/registry.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/transformers/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/kimi_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/transformers/kimi_vl.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/transformers/llama.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/transformers/monkey_patch.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/qwen2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/transformers/qwen2.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/qwen2_5_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/transformers/qwen2_5_vl.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/qwen2_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/transformers/qwen2_vl.py -------------------------------------------------------------------------------- /verl/verl/models/weight_loader_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/models/weight_loader_registry.py -------------------------------------------------------------------------------- /verl/verl/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/protocol.py -------------------------------------------------------------------------------- /verl/verl/single_controller/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/base/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/base/decorator.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/base/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/megatron/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/base/megatron/worker.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/megatron/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/base/megatron/worker_group.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/register_center/ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/base/register_center/ray.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/base/worker.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/base/worker_group.py -------------------------------------------------------------------------------- /verl/verl/single_controller/ray/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/ray/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/ray/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/ray/base.py -------------------------------------------------------------------------------- /verl/verl/single_controller/ray/megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/single_controller/ray/megatron.py -------------------------------------------------------------------------------- /verl/verl/third_party/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/sglang/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/sglang/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/sglang/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/sglang/parallel_state.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/config.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/llm.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/model_runner.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/worker.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/config.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/llm.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/model_runner.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/worker.py -------------------------------------------------------------------------------- /verl/verl/tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/tools/__init__.py -------------------------------------------------------------------------------- /verl/verl/tools/base_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/tools/base_tool.py -------------------------------------------------------------------------------- /verl/verl/tools/gsm8k_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/tools/gsm8k_tool.py -------------------------------------------------------------------------------- /verl/verl/tools/sandbox_fusion_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/tools/sandbox_fusion_tools.py -------------------------------------------------------------------------------- /verl/verl/tools/schemas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/tools/schemas.py -------------------------------------------------------------------------------- /verl/verl/tools/search_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/tools/search_tool.py -------------------------------------------------------------------------------- /verl/verl/tools/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/tools/utils/__init__.py -------------------------------------------------------------------------------- /verl/verl/tools/utils/search_r1_like_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/tools/utils/search_r1_like_utils.py -------------------------------------------------------------------------------- /verl/verl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/__init__.py -------------------------------------------------------------------------------- /verl/verl/trainer/config/evaluation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/config/evaluation.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/generation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/config/generation.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/ppo_megatron_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/config/ppo_megatron_trainer.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/ppo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/config/ppo_trainer.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/sft_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/config/sft_trainer.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/fsdp_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/fsdp_sft_trainer.py -------------------------------------------------------------------------------- /verl/verl/trainer/main_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/main_eval.py -------------------------------------------------------------------------------- /verl/verl/trainer/main_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/main_generation.py -------------------------------------------------------------------------------- /verl/verl/trainer/main_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/main_ppo.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/ppo/__init__.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/ppo/core_algos.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/metric_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/ppo/metric_utils.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/ppo/ray_trainer.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/ppo/reward.py -------------------------------------------------------------------------------- /verl/verl/trainer/runtime_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/trainer/runtime_env.yaml -------------------------------------------------------------------------------- /verl/verl/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/activation_offload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/activation_offload.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/checkpoint/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/checkpoint/checkpoint_manager.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/fsdp_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/checkpoint/fsdp_checkpoint_manager.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/megatron_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/checkpoint/megatron_checkpoint_manager.py -------------------------------------------------------------------------------- /verl/verl/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/config.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/dataset/README.md -------------------------------------------------------------------------------- /verl/verl/utils/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/dataset/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/multiturn_sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/dataset/multiturn_sft_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/rl_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/dataset/rl_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/rm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/dataset/rm_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/dataset/sft_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/vision_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/dataset/vision_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/debug/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/debug/performance.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/profile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/debug/profile.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/trajectory_tracker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/debug/trajectory_tracker.py -------------------------------------------------------------------------------- /verl/verl/utils/device.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/device.py -------------------------------------------------------------------------------- /verl/verl/utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/distributed.py -------------------------------------------------------------------------------- /verl/verl/utils/experimental/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/experimental/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/experimental/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/experimental/torch_functional.py -------------------------------------------------------------------------------- /verl/verl/utils/flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/flops_counter.py -------------------------------------------------------------------------------- /verl/verl/utils/fs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/fs.py -------------------------------------------------------------------------------- /verl/verl/utils/fsdp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/fsdp_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/hdfs_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/hdfs_io.py -------------------------------------------------------------------------------- /verl/verl/utils/import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/import_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/logger/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/logger/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/logger/aggregate_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/logger/aggregate_logger.py -------------------------------------------------------------------------------- /verl/verl/utils/logging_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/logging_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/megatron/memory.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/megatron/optimizer.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/pipeline_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/megatron/pipeline_parallel.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/sequence_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/megatron/sequence_parallel.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/tensor_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/megatron/tensor_parallel.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/megatron_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/memory_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/memory_buffer.py -------------------------------------------------------------------------------- /verl/verl/utils/metric/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/metric/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/metric/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/metric/utils.py -------------------------------------------------------------------------------- /verl/verl/utils/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/model.py -------------------------------------------------------------------------------- /verl/verl/utils/net_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/net_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/py_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/py_functional.py -------------------------------------------------------------------------------- /verl/verl/utils/ray_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/ray_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/rendezvous/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/rendezvous/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/rendezvous/ray_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/rendezvous/ray_backend.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/geo3k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/geo3k.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/gsm8k.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/math.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/math_batch.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/math_dapo.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math_verify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/math_verify.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_code/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/prime_code/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_code/testing_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/prime_code/testing_util.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_code/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/prime_code/utils.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_math/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/prime_math/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_math/grader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/prime_math/grader.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_math/math_normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/prime_math/math_normalize.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ranking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/ranking.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/sandbox_fusion/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/sandbox_fusion/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/sandbox_fusion/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/sandbox_fusion/utils.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/search_r1_like_qa_em.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/reward_score/search_r1_like_qa_em.py -------------------------------------------------------------------------------- /verl/verl/utils/seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/seqlen_balancing.py -------------------------------------------------------------------------------- /verl/verl/utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/utils/torch_dtypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/torch_dtypes.py -------------------------------------------------------------------------------- /verl/verl/utils/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/torch_functional.py -------------------------------------------------------------------------------- /verl/verl/utils/tracking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/tracking.py -------------------------------------------------------------------------------- /verl/verl/utils/ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/ulysses.py -------------------------------------------------------------------------------- /verl/verl/utils/vllm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/utils/vllm_utils.py -------------------------------------------------------------------------------- /verl/verl/version/version: -------------------------------------------------------------------------------- 1 | 0.4.0 2 | -------------------------------------------------------------------------------- /verl/verl/workers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/actor/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/actor/base.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/actor/dp_actor.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/megatron_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/actor/megatron_actor.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/critic/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/critic/base.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/dp_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/critic/dp_critic.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/megatron_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/critic/megatron_critic.py -------------------------------------------------------------------------------- /verl/verl/workers/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/fsdp_workers.py -------------------------------------------------------------------------------- /verl/verl/workers/megatron_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/megatron_workers.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/reward_manager/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/reward_manager/batch.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/reward_manager/dapo.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/reward_manager/naive.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/prime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/reward_manager/prime.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/reward_model/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/reward_model/base.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/reward_model/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/megatron/reward_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/reward_model/megatron/reward_model.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/async_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/async_server.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/base.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/hf_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/hf_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/naive/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/naive/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/naive/naive_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/naive/naive_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/schemas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/schemas.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/sglang_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/sglang_rollout/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/sglang_rollout/sglang_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/sglang_rollout/sglang_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/sglang_rollout/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/sglang_rollout/utils.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/vllm_rollout/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/vllm_async_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/vllm_rollout/vllm_async_server.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/vllm_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/vllm_rollout/vllm_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/sharding_manager/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/sharding_manager/base.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/fsdp_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/sharding_manager/fsdp_sglang.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/fsdp_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/sharding_manager/fsdp_ulysses.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/sharding_manager/fsdp_vllm.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/megatron_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/sharding_manager/megatron_sglang.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/megatron_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/8421BCD/ReasonRank/HEAD/verl/verl/workers/sharding_manager/megatron_vllm.py --------------------------------------------------------------------------------