├── LLaMA-Factory ├── .dockerignore ├── .gitattributes ├── .github │ ├── CODE_OF_CONDUCT.md │ ├── CONTRIBUTING.md │ ├── ISSUE_TEMPLATE │ │ └── bug-report.yml │ ├── PULL_REQUEST_TEMPLATE.md │ ├── SECURITY.md │ └── workflows │ │ ├── label_issue.yml │ │ ├── publish.yml │ │ └── tests.yml ├── .gitignore ├── =0.4.3 ├── CITATION.cff ├── LICENSE ├── MANIFEST.in ├── Makefile ├── README.md ├── README_zh.md ├── assets │ ├── benchmark.svg │ ├── logo.png │ ├── wechat.jpg │ └── wechat_npu.jpg ├── data │ ├── README.md │ ├── README_zh.md │ ├── belle_multiturn │ │ └── belle_multiturn.py │ ├── dataset_info.json │ ├── hh_rlhf_en │ │ └── hh_rlhf_en.py │ ├── mllm_demo_data │ │ ├── 1.jpg │ │ ├── 2.jpg │ │ └── 3.jpg │ ├── ultra_chat │ │ └── ultra_chat.py │ ├── web_policy_sft.json │ └── wiki_demo.txt ├── docker │ ├── docker-cuda │ │ ├── Dockerfile │ │ └── 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 │ ├── deepspeed │ │ ├── ds_z0_config.json │ │ ├── ds_z2_config.json │ │ ├── ds_z2_offload_config.json │ │ ├── ds_z3_config.json │ │ └── ds_z3_offload_config.json │ ├── extras │ │ ├── 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 │ │ └── pissa │ │ │ └── llama3_lora_sft.yaml │ ├── inference │ │ ├── glm4.yaml │ │ ├── llama3.yaml │ │ ├── llama3_lora_sft.yaml │ │ ├── llama3_vllm.yaml │ │ └── llava1_5.yaml │ ├── merge_lora │ │ ├── llama3_gptq.yaml │ │ └── llama3_lora_sft.yaml │ ├── train_full │ │ ├── llama3_full_orm_web.yaml │ │ ├── llama3_full_policy_web.yaml │ │ ├── llama3_full_predict.yaml │ │ └── llama3_full_sft_ds3.yaml │ ├── train_lora │ │ ├── llama3_lora_dpo.yaml │ │ ├── llama3_lora_eval.yaml │ │ ├── llama3_lora_kto.yaml │ │ ├── llama3_lora_ppo.yaml │ │ ├── llama3_lora_predict.yaml │ │ ├── llama3_lora_pretrain.yaml │ │ ├── llama3_lora_reward.yaml │ │ ├── llama3_lora_sft.yaml │ │ ├── llama3_lora_sft_ds0.yaml │ │ ├── llama3_lora_sft_ds3.yaml │ │ ├── llama3_preprocess.yaml │ │ └── llava1_5_lora_sft.yaml │ └── train_qlora │ │ ├── llama3_lora_sft_aqlm.yaml │ │ ├── llama3_lora_sft_awq.yaml │ │ ├── llama3_lora_sft_gptq.yaml │ │ └── llama3_lora_sft_otfq.yaml ├── pyproject.toml ├── requirements.txt ├── run.sh ├── scripts │ ├── cal_flops.py │ ├── cal_lr.py │ ├── cal_ppl.py │ ├── length_cdf.py │ ├── llama_pro.py │ ├── llamafy_baichuan2.py │ ├── llamafy_qwen.py │ ├── loftq_init.py │ ├── pissa_init.py │ └── test_toolcall.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 │ │ │ └── vllm_engine.py │ │ ├── cli.py │ │ ├── data │ │ │ ├── __init__.py │ │ │ ├── aligner.py │ │ │ ├── collator.py │ │ │ ├── data_utils.py │ │ │ ├── formatter.py │ │ │ ├── loader.py │ │ │ ├── parser.py │ │ │ ├── preprocess.py │ │ │ ├── processors │ │ │ │ ├── __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 │ │ ├── launcher.py │ │ ├── model │ │ │ ├── __init__.py │ │ │ ├── adapter.py │ │ │ ├── loader.py │ │ │ ├── model_utils │ │ │ │ ├── __init__.py │ │ │ │ ├── attention.py │ │ │ │ ├── checkpointing.py │ │ │ │ ├── embedding.py │ │ │ │ ├── longlora.py │ │ │ │ ├── misc.py │ │ │ │ ├── mod.py │ │ │ │ ├── moe.py │ │ │ │ ├── packing.py │ │ │ │ ├── quantization.py │ │ │ │ ├── rope.py │ │ │ │ ├── unsloth.py │ │ │ │ ├── valuehead.py │ │ │ │ └── visual.py │ │ │ └── patcher.py │ │ ├── train │ │ │ ├── __init__.py │ │ │ ├── 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 │ │ │ ├── infer.py │ │ │ ├── top.py │ │ │ └── train.py │ │ │ ├── css.py │ │ │ ├── engine.py │ │ │ ├── interface.py │ │ │ ├── locales.py │ │ │ ├── manager.py │ │ │ ├── runner.py │ │ │ └── utils.py │ ├── train.py │ └── webui.py └── tests │ ├── data │ ├── processors │ │ ├── test_feedback.py │ │ ├── test_pairwise.py │ │ ├── test_processor_utils.py │ │ ├── test_supervised.py │ │ └── test_unsupervised.py │ ├── test_collator.py │ ├── test_formatter.py │ └── test_template.py │ ├── eval │ └── test_eval_template.py │ └── model │ ├── model_utils │ ├── test_attention.py │ ├── test_checkpointing.py │ └── test_packing.py │ ├── test_base.py │ ├── test_freeze.py │ ├── test_full.py │ ├── test_lora.py │ └── test_pissa.py ├── README.md ├── WebArena-Lite_info.json ├── __init__.py ├── assets └── webrl.png ├── extras ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ ├── constants.cpython-310.pyc │ ├── env.cpython-310.pyc │ ├── logging.cpython-310.pyc │ ├── misc.cpython-310.pyc │ ├── packages.cpython-310.pyc │ └── ploting.cpython-310.pyc ├── constants.py ├── env.py ├── logging.py ├── misc.py ├── packages.py └── ploting.py ├── hparams ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ ├── data_args.cpython-310.pyc │ ├── evaluation_args.cpython-310.pyc │ ├── finetuning_args.cpython-310.pyc │ ├── generating_args.cpython-310.pyc │ ├── model_args.cpython-310.pyc │ └── parser.cpython-310.pyc ├── data_args.py ├── evaluation_args.py ├── finetuning_args.py ├── generating_args.py ├── model_args.py └── parser.py ├── requirements.txt ├── run_multinode.sh ├── scripts ├── __pycache__ │ └── utils.cpython-310.pyc ├── config │ ├── accelerate_config │ │ └── web_config.yaml │ ├── deepspeed_config │ │ └── zero-3-offload.json │ └── main │ │ ├── default.yaml │ │ └── webrl.yaml ├── gen_task.py ├── process_data.py ├── run.py ├── utils.py └── webarena_lite_sft.pt ├── setup.py ├── webrl.egg-info ├── PKG-INFO ├── SOURCES.txt ├── dependency_links.txt ├── requires.txt └── top_level.txt └── webrl ├── __init__.py ├── __pycache__ ├── __init__.cpython-310.pyc └── misc.cpython-310.pyc ├── algorithms ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ ├── eval_loop.cpython-310.pyc │ ├── offpolicy_train_loop.cpython-310.pyc │ ├── parallel_utils.cpython-310.pyc │ └── worker_collect_loop.cpython-310.pyc ├── offpolicy_train_loop.py └── webrl │ ├── __init__.py │ ├── __pycache__ │ ├── __init__.cpython-310.pyc │ └── trainer.cpython-310.pyc │ └── trainer.py ├── data ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ └── utils.cpython-310.pyc ├── htmls.json └── utils.py ├── environment ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ └── env_utils.cpython-310.pyc └── env_utils.py ├── misc.py └── models ├── __init__.py ├── __pycache__ ├── __init__.cpython-310.pyc ├── critic.cpython-310.pyc ├── llama_agent.cpython-310.pyc └── model.cpython-310.pyc ├── critic.py └── llama_agent.py /LLaMA-Factory/.dockerignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.dockerignore -------------------------------------------------------------------------------- /LLaMA-Factory/.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.gitattributes -------------------------------------------------------------------------------- /LLaMA-Factory/.github/CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.github/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /LLaMA-Factory/.github/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.github/CONTRIBUTING.md -------------------------------------------------------------------------------- /LLaMA-Factory/.github/ISSUE_TEMPLATE/bug-report.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.github/ISSUE_TEMPLATE/bug-report.yml -------------------------------------------------------------------------------- /LLaMA-Factory/.github/PULL_REQUEST_TEMPLATE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.github/PULL_REQUEST_TEMPLATE.md -------------------------------------------------------------------------------- /LLaMA-Factory/.github/SECURITY.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.github/SECURITY.md -------------------------------------------------------------------------------- /LLaMA-Factory/.github/workflows/label_issue.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.github/workflows/label_issue.yml -------------------------------------------------------------------------------- /LLaMA-Factory/.github/workflows/publish.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.github/workflows/publish.yml -------------------------------------------------------------------------------- /LLaMA-Factory/.github/workflows/tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.github/workflows/tests.yml -------------------------------------------------------------------------------- /LLaMA-Factory/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/.gitignore -------------------------------------------------------------------------------- /LLaMA-Factory/=0.4.3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/=0.4.3 -------------------------------------------------------------------------------- /LLaMA-Factory/CITATION.cff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/CITATION.cff -------------------------------------------------------------------------------- /LLaMA-Factory/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/LICENSE -------------------------------------------------------------------------------- /LLaMA-Factory/MANIFEST.in: -------------------------------------------------------------------------------- 1 | include LICENSE requirements.txt 2 | -------------------------------------------------------------------------------- /LLaMA-Factory/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/Makefile -------------------------------------------------------------------------------- /LLaMA-Factory/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/README.md -------------------------------------------------------------------------------- /LLaMA-Factory/README_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/README_zh.md -------------------------------------------------------------------------------- /LLaMA-Factory/assets/benchmark.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/assets/benchmark.svg -------------------------------------------------------------------------------- /LLaMA-Factory/assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/assets/logo.png -------------------------------------------------------------------------------- /LLaMA-Factory/assets/wechat.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/assets/wechat.jpg -------------------------------------------------------------------------------- /LLaMA-Factory/assets/wechat_npu.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/assets/wechat_npu.jpg -------------------------------------------------------------------------------- /LLaMA-Factory/data/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/README.md -------------------------------------------------------------------------------- /LLaMA-Factory/data/README_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/README_zh.md -------------------------------------------------------------------------------- /LLaMA-Factory/data/belle_multiturn/belle_multiturn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/belle_multiturn/belle_multiturn.py -------------------------------------------------------------------------------- /LLaMA-Factory/data/dataset_info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/dataset_info.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/hh_rlhf_en/hh_rlhf_en.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/hh_rlhf_en/hh_rlhf_en.py -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/mllm_demo_data/1.jpg -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/mllm_demo_data/2.jpg -------------------------------------------------------------------------------- /LLaMA-Factory/data/mllm_demo_data/3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/mllm_demo_data/3.jpg -------------------------------------------------------------------------------- /LLaMA-Factory/data/ultra_chat/ultra_chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/ultra_chat/ultra_chat.py -------------------------------------------------------------------------------- /LLaMA-Factory/data/web_policy_sft.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/web_policy_sft.json -------------------------------------------------------------------------------- /LLaMA-Factory/data/wiki_demo.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/data/wiki_demo.txt -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-cuda/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/docker/docker-cuda/Dockerfile -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-cuda/docker-compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/docker/docker-cuda/docker-compose.yml -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-npu/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/docker/docker-npu/Dockerfile -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-npu/docker-compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/docker/docker-npu/docker-compose.yml -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-rocm/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/docker/docker-rocm/Dockerfile -------------------------------------------------------------------------------- /LLaMA-Factory/docker/docker-rocm/docker-compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/docker/docker-rocm/docker-compose.yml -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/ceval/ceval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/evaluation/ceval/ceval.py -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/ceval/ceval.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/evaluation/ceval/ceval.zip -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/ceval/mapping.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/evaluation/ceval/mapping.json -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/cmmlu/cmmlu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/evaluation/cmmlu/cmmlu.py -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/cmmlu/cmmlu.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/evaluation/cmmlu/cmmlu.zip -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/cmmlu/mapping.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/evaluation/cmmlu/mapping.json -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/mmlu/mapping.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/evaluation/mmlu/mapping.json -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/mmlu/mmlu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/evaluation/mmlu/mmlu.py -------------------------------------------------------------------------------- /LLaMA-Factory/evaluation/mmlu/mmlu.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/evaluation/mmlu/mmlu.zip -------------------------------------------------------------------------------- /LLaMA-Factory/examples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/README.md -------------------------------------------------------------------------------- /LLaMA-Factory/examples/README_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/README_zh.md -------------------------------------------------------------------------------- /LLaMA-Factory/examples/accelerate/fsdp_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/accelerate/fsdp_config.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/deepspeed/ds_z0_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/deepspeed/ds_z0_config.json -------------------------------------------------------------------------------- /LLaMA-Factory/examples/deepspeed/ds_z2_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/deepspeed/ds_z2_config.json -------------------------------------------------------------------------------- /LLaMA-Factory/examples/deepspeed/ds_z2_offload_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/deepspeed/ds_z2_offload_config.json -------------------------------------------------------------------------------- /LLaMA-Factory/examples/deepspeed/ds_z3_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/deepspeed/ds_z3_config.json -------------------------------------------------------------------------------- /LLaMA-Factory/examples/deepspeed/ds_z3_offload_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/deepspeed/ds_z3_offload_config.json -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/badam/llama3_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/extras/badam/llama3_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/fsdp_qlora/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/extras/fsdp_qlora/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/fsdp_qlora/train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/extras/fsdp_qlora/train.sh -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/galore/llama3_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/extras/galore/llama3_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/llama_pro/expand.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/extras/llama_pro/expand.sh -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/llama_pro/llama3_freeze_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/extras/llama_pro/llama3_freeze_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/loraplus/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/extras/loraplus/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/mod/llama3_full_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/extras/mod/llama3_full_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/extras/pissa/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/extras/pissa/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/inference/glm4.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/inference/glm4.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/inference/llama3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/inference/llama3.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/inference/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/inference/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/inference/llama3_vllm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/inference/llama3_vllm.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/inference/llava1_5.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/inference/llava1_5.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/merge_lora/llama3_gptq.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/merge_lora/llama3_gptq.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/merge_lora/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/merge_lora/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_full/llama3_full_orm_web.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_full/llama3_full_orm_web.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_full/llama3_full_policy_web.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_full/llama3_full_policy_web.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_full/llama3_full_predict.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_full/llama3_full_predict.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_full/llama3_full_sft_ds3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_full/llama3_full_sft_ds3.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_dpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_dpo.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_eval.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_eval.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_kto.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_kto.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_ppo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_ppo.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_predict.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_predict.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_pretrain.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_pretrain.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_reward.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_reward.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_sft_ds0.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_sft_ds0.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_lora_sft_ds3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_lora_sft_ds3.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llama3_preprocess.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llama3_preprocess.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_lora/llava1_5_lora_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_lora/llava1_5_lora_sft.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/examples/train_qlora/llama3_lora_sft_aqlm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/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/THUDM/WebRL/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/THUDM/WebRL/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/THUDM/WebRL/HEAD/LLaMA-Factory/examples/train_qlora/llama3_lora_sft_otfq.yaml -------------------------------------------------------------------------------- /LLaMA-Factory/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/pyproject.toml -------------------------------------------------------------------------------- /LLaMA-Factory/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/requirements.txt -------------------------------------------------------------------------------- /LLaMA-Factory/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/run.sh -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/cal_flops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/scripts/cal_flops.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/cal_lr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/scripts/cal_lr.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/cal_ppl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/scripts/cal_ppl.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/length_cdf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/scripts/length_cdf.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/llama_pro.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/scripts/llama_pro.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/llamafy_baichuan2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/scripts/llamafy_baichuan2.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/llamafy_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/scripts/llamafy_qwen.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/loftq_init.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/scripts/loftq_init.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/pissa_init.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/scripts/pissa_init.py -------------------------------------------------------------------------------- /LLaMA-Factory/scripts/test_toolcall.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/scripts/test_toolcall.py -------------------------------------------------------------------------------- /LLaMA-Factory/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/setup.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/api.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/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/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/api/app.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/api/chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/api/chat.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/api/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/api/common.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/api/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/api/protocol.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/chat/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/base_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/chat/base_engine.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/chat_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/chat/chat_model.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/hf_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/chat/hf_engine.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/chat/vllm_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/chat/vllm_engine.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/cli.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/aligner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/aligner.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/collator.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/data_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/formatter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/formatter.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/loader.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/parser.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/preprocess.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processors/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processors/feedback.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/processors/feedback.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processors/pairwise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/processors/pairwise.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processors/pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/processors/pretrain.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processors/processor_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/processors/processor_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processors/supervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/processors/supervised.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/processors/unsupervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/processors/unsupervised.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/data/template.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/data/tool_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/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/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/eval/evaluator.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/eval/template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/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/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/extras/constants.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/extras/env.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/extras/logging.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/extras/misc.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/packages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/extras/packages.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/extras/ploting.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/extras/ploting.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/hparams/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/data_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/hparams/data_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/evaluation_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/hparams/evaluation_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/finetuning_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/hparams/finetuning_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/generating_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/hparams/generating_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/model_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/hparams/model_args.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/hparams/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/hparams/parser.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/launcher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/launcher.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/adapter.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/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/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/attention.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/checkpointing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/checkpointing.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/embedding.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/longlora.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/longlora.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/misc.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/mod.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/mod.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/moe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/moe.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/packing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/packing.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/quantization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/quantization.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/rope.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/rope.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/unsloth.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/unsloth.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/valuehead.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/valuehead.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/model_utils/visual.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/model_utils/visual.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/model/patcher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/model/patcher.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/callbacks.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/dpo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/dpo/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/dpo/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/dpo/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/dpo/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/dpo/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/kto/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/kto/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/kto/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/kto/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/kto/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/kto/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/ppo/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/ppo/ppo_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/ppo/ppo_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/ppo/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/ppo/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/ppo/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/ppo/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/pt/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/pt/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/pt/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/pt/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/pt/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/pt/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/rm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/rm/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/rm/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/rm/metric.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/rm/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/rm/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/rm/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/rm/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/sft/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/sft/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/sft/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/sft/metric.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/sft/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/sft/trainer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/sft/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/sft/workflow.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/test_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/trainer_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/train/trainer_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/train/tuner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/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/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/chatter.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/common.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/components/__init__.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/chatbot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/components/chatbot.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/components/data.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/components/eval.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/export.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/components/export.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/components/infer.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/top.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/components/top.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/components/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/components/train.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/css.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/css.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/engine.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/interface.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/interface.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/locales.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/locales.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/manager.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/runner.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/llamafactory/webui/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/llamafactory/webui/utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/train.py -------------------------------------------------------------------------------- /LLaMA-Factory/src/webui.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/src/webui.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/processors/test_feedback.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/data/processors/test_feedback.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/processors/test_pairwise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/data/processors/test_pairwise.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/processors/test_processor_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/data/processors/test_processor_utils.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/processors/test_supervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/data/processors/test_supervised.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/processors/test_unsupervised.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/data/processors/test_unsupervised.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/test_collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/data/test_collator.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/test_formatter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/data/test_formatter.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/data/test_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/data/test_template.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/eval/test_eval_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/eval/test_eval_template.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/model_utils/test_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/model/model_utils/test_attention.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/model_utils/test_checkpointing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/model/model_utils/test_checkpointing.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/model_utils/test_packing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/model/model_utils/test_packing.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/test_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/model/test_base.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/test_freeze.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/model/test_freeze.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/test_full.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/model/test_full.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/test_lora.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/model/test_lora.py -------------------------------------------------------------------------------- /LLaMA-Factory/tests/model/test_pissa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/LLaMA-Factory/tests/model/test_pissa.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/README.md -------------------------------------------------------------------------------- /WebArena-Lite_info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/WebArena-Lite_info.json -------------------------------------------------------------------------------- /__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /assets/webrl.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/assets/webrl.png -------------------------------------------------------------------------------- /extras/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /extras/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /extras/__pycache__/constants.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/__pycache__/constants.cpython-310.pyc -------------------------------------------------------------------------------- /extras/__pycache__/env.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/__pycache__/env.cpython-310.pyc -------------------------------------------------------------------------------- /extras/__pycache__/logging.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/__pycache__/logging.cpython-310.pyc -------------------------------------------------------------------------------- /extras/__pycache__/misc.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/__pycache__/misc.cpython-310.pyc -------------------------------------------------------------------------------- /extras/__pycache__/packages.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/__pycache__/packages.cpython-310.pyc -------------------------------------------------------------------------------- /extras/__pycache__/ploting.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/__pycache__/ploting.cpython-310.pyc -------------------------------------------------------------------------------- /extras/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/constants.py -------------------------------------------------------------------------------- /extras/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/env.py -------------------------------------------------------------------------------- /extras/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/logging.py -------------------------------------------------------------------------------- /extras/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/misc.py -------------------------------------------------------------------------------- /extras/packages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/packages.py -------------------------------------------------------------------------------- /extras/ploting.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/extras/ploting.py -------------------------------------------------------------------------------- /hparams/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/__init__.py -------------------------------------------------------------------------------- /hparams/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /hparams/__pycache__/data_args.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/__pycache__/data_args.cpython-310.pyc -------------------------------------------------------------------------------- /hparams/__pycache__/evaluation_args.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/__pycache__/evaluation_args.cpython-310.pyc -------------------------------------------------------------------------------- /hparams/__pycache__/finetuning_args.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/__pycache__/finetuning_args.cpython-310.pyc -------------------------------------------------------------------------------- /hparams/__pycache__/generating_args.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/__pycache__/generating_args.cpython-310.pyc -------------------------------------------------------------------------------- /hparams/__pycache__/model_args.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/__pycache__/model_args.cpython-310.pyc -------------------------------------------------------------------------------- /hparams/__pycache__/parser.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/__pycache__/parser.cpython-310.pyc -------------------------------------------------------------------------------- /hparams/data_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/data_args.py -------------------------------------------------------------------------------- /hparams/evaluation_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/evaluation_args.py -------------------------------------------------------------------------------- /hparams/finetuning_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/finetuning_args.py -------------------------------------------------------------------------------- /hparams/generating_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/generating_args.py -------------------------------------------------------------------------------- /hparams/model_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/model_args.py -------------------------------------------------------------------------------- /hparams/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/hparams/parser.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/requirements.txt -------------------------------------------------------------------------------- /run_multinode.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/run_multinode.sh -------------------------------------------------------------------------------- /scripts/__pycache__/utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/scripts/__pycache__/utils.cpython-310.pyc -------------------------------------------------------------------------------- /scripts/config/accelerate_config/web_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/scripts/config/accelerate_config/web_config.yaml -------------------------------------------------------------------------------- /scripts/config/deepspeed_config/zero-3-offload.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/scripts/config/deepspeed_config/zero-3-offload.json -------------------------------------------------------------------------------- /scripts/config/main/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/scripts/config/main/default.yaml -------------------------------------------------------------------------------- /scripts/config/main/webrl.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/scripts/config/main/webrl.yaml -------------------------------------------------------------------------------- /scripts/gen_task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/scripts/gen_task.py -------------------------------------------------------------------------------- /scripts/process_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/scripts/process_data.py -------------------------------------------------------------------------------- /scripts/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/scripts/run.py -------------------------------------------------------------------------------- /scripts/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/scripts/utils.py -------------------------------------------------------------------------------- /scripts/webarena_lite_sft.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/scripts/webarena_lite_sft.pt -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/setup.py -------------------------------------------------------------------------------- /webrl.egg-info/PKG-INFO: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl.egg-info/PKG-INFO -------------------------------------------------------------------------------- /webrl.egg-info/SOURCES.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl.egg-info/SOURCES.txt -------------------------------------------------------------------------------- /webrl.egg-info/dependency_links.txt: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /webrl.egg-info/requires.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl.egg-info/requires.txt -------------------------------------------------------------------------------- /webrl.egg-info/top_level.txt: -------------------------------------------------------------------------------- 1 | extras 2 | hparams 3 | webrl 4 | -------------------------------------------------------------------------------- /webrl/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /webrl/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/__pycache__/misc.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/__pycache__/misc.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/algorithms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/__init__.py -------------------------------------------------------------------------------- /webrl/algorithms/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/algorithms/__pycache__/eval_loop.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/__pycache__/eval_loop.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/algorithms/__pycache__/offpolicy_train_loop.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/__pycache__/offpolicy_train_loop.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/algorithms/__pycache__/parallel_utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/__pycache__/parallel_utils.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/algorithms/__pycache__/worker_collect_loop.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/__pycache__/worker_collect_loop.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/algorithms/offpolicy_train_loop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/offpolicy_train_loop.py -------------------------------------------------------------------------------- /webrl/algorithms/webrl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/webrl/__init__.py -------------------------------------------------------------------------------- /webrl/algorithms/webrl/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/webrl/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/algorithms/webrl/__pycache__/trainer.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/webrl/__pycache__/trainer.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/algorithms/webrl/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/algorithms/webrl/trainer.py -------------------------------------------------------------------------------- /webrl/data/__init__.py: -------------------------------------------------------------------------------- 1 | from .utils import DummyDataset, ReplayBuffer -------------------------------------------------------------------------------- /webrl/data/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/data/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/data/__pycache__/utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/data/__pycache__/utils.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/data/htmls.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/data/htmls.json -------------------------------------------------------------------------------- /webrl/data/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/data/utils.py -------------------------------------------------------------------------------- /webrl/environment/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/environment/__init__.py -------------------------------------------------------------------------------- /webrl/environment/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/environment/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/environment/__pycache__/env_utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/environment/__pycache__/env_utils.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/environment/env_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/environment/env_utils.py -------------------------------------------------------------------------------- /webrl/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/misc.py -------------------------------------------------------------------------------- /webrl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/models/__init__.py -------------------------------------------------------------------------------- /webrl/models/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/models/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/models/__pycache__/critic.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/models/__pycache__/critic.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/models/__pycache__/llama_agent.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/models/__pycache__/llama_agent.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/models/__pycache__/model.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/models/__pycache__/model.cpython-310.pyc -------------------------------------------------------------------------------- /webrl/models/critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/models/critic.py -------------------------------------------------------------------------------- /webrl/models/llama_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/THUDM/WebRL/HEAD/webrl/models/llama_agent.py --------------------------------------------------------------------------------