SkillRL
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
파일 탐색기
- __init__.cpython-312.pyc
- __init__.cpython-313.pyc
- base.cpython-312.pyc
- base.cpython-313.pyc
- env_manager.cpython-312.pyc
- env_manager.cpython-313.pyc
- __init__.cpython-312.pyc
- envs.cpython-312.pyc
- projection.cpython-312.pyc
- __init__.cpython-312.pyc
- __init__.cpython-312.pyc
- __init__.py
- base_agent.py
- text_dagger_agent.py
- text_dqn_agent.py
- vision_dagger_agent.py
- rewards.json
- __init__.py
- base.py
- mrcnn.py
- mrcnn_astar.py
- oracle.py
- oracle_astar.py
- __init__.py
- coco_eval.py
- coco_utils.py
- engine.py
- group_by_aspect_ratio.py
- mrcnn.py
- train.py
- transforms.py
- utils.py
- __init__.cpython-312.pyc
- alfred_tw_env.cpython-312.pyc
- __init__.py
- alfred_hybrid.py
- alfred_thor_env.py
- alfred_tw_env.py
- __init__.py
- evaluate_dagger.py
- evaluate_dqn.py
- evaluate_vision_dagger.py
- __init__.py
- handcoded_expert.py
- handcoded_expert_thor.py
- handcoded_expert_tw.py
- __init__.py
- generic.py
- layers.py
- memory.py
- model.py
- segment_tree.py
- __init__.py
- misc.py
- __init__.py
- README.md
- alfred.pddl
- alfred.twl2
- README.md
- __init__.py
- reward.py
- tasks.py
- thor_env.py
- __init__.py
- agent_base.py
- deterministic_planner_agent.py
- plan_agent.py
- semantic_map_planner_agent.py
- problem_0_0.pddl
- PutTask_domain.pddl
- expressions.c
- expressions.h
- ff.h
- inst_easy.c
- inst_easy.h
- inst_final.c
- inst_final.h
- inst_hard.c
- inst_hard.h
- inst_pre.c
- inst_pre.h
- lex-fct_pddl.l
- lex-ops_pddl.l
- main.c
- makefile
- memory.c
- memory.h
- output.c
- output.h
- parse.c
- parse.h
- README.md
- relax.c
- relax.h
- run_sample.sh
- scan-fct_pddl.y
- scan-ops_pddl.y
- search.c
- search.h
- __init__.py
- game_state_base.py
- planned_game_state.py
- task_game_state.py
- task_game_state_full_knowledge.py
- __init__.py
- graph_obj.py
- FloorPlan1-layout.npy
- FloorPlan1-objects.json
- FloorPlan1-openable.json
- FloorPlan10-layout.npy
- FloorPlan10-objects.json
- FloorPlan10-openable.json
- FloorPlan11-layout.npy
- FloorPlan11-objects.json
- FloorPlan11-openable.json
- FloorPlan12-layout.npy
- FloorPlan12-objects.json
- FloorPlan12-openable.json
- FloorPlan13-layout.npy
- FloorPlan13-objects.json
- FloorPlan13-openable.json
- FloorPlan14-layout.npy
- FloorPlan14-objects.json
- FloorPlan14-openable.json
- FloorPlan15-layout.npy
- FloorPlan15-objects.json
- FloorPlan15-openable.json
- FloorPlan16-layout.npy
- FloorPlan16-objects.json
- FloorPlan16-openable.json
- FloorPlan17-layout.npy
- FloorPlan17-objects.json
- FloorPlan17-openable.json
- FloorPlan18-layout.npy
- FloorPlan18-objects.json
- FloorPlan18-openable.json
- FloorPlan19-layout.npy
- FloorPlan19-objects.json
- FloorPlan19-openable.json
- FloorPlan2-layout.npy
- FloorPlan2-objects.json
- FloorPlan2-openable.json
- FloorPlan20-layout.npy
- FloorPlan20-objects.json
- FloorPlan20-openable.json
- FloorPlan201-layout.npy
- FloorPlan201-objects.json
- FloorPlan201-openable.json
- FloorPlan202-layout.npy
- FloorPlan202-objects.json
- FloorPlan202-openable.json
- FloorPlan203-layout.npy
- FloorPlan203-objects.json
- FloorPlan203-openable.json
- FloorPlan204-layout.npy
- FloorPlan204-objects.json
- FloorPlan204-openable.json
- FloorPlan205-layout.npy
- FloorPlan205-objects.json
- FloorPlan205-openable.json
- FloorPlan206-layout.npy
- FloorPlan206-objects.json
- FloorPlan206-openable.json
- FloorPlan207-layout.npy
- FloorPlan207-objects.json
- FloorPlan207-openable.json
- FloorPlan208-layout.npy
- FloorPlan208-objects.json
- FloorPlan208-openable.json
- FloorPlan209-layout.npy
- FloorPlan209-objects.json
- FloorPlan209-openable.json
- FloorPlan21-layout.npy
- FloorPlan21-objects.json
- FloorPlan21-openable.json
- FloorPlan210-layout.npy
- FloorPlan210-objects.json
- FloorPlan210-openable.json
- FloorPlan211-layout.npy
- FloorPlan211-objects.json
- FloorPlan211-openable.json
- FloorPlan212-layout.npy
- FloorPlan212-objects.json
- FloorPlan212-openable.json
- FloorPlan213-layout.npy
- FloorPlan213-objects.json
- FloorPlan213-openable.json
- FloorPlan214-layout.npy
- FloorPlan214-objects.json
- FloorPlan214-openable.json
- FloorPlan215-layout.npy
- FloorPlan215-objects.json
- FloorPlan215-openable.json
- FloorPlan216-layout.npy
- FloorPlan216-objects.json
- FloorPlan216-openable.json
- FloorPlan217-layout.npy
- FloorPlan217-objects.json
- FloorPlan217-openable.json
- FloorPlan218-layout.npy
- FloorPlan218-objects.json
- FloorPlan218-openable.json
- FloorPlan219-layout.npy
- FloorPlan219-objects.json
- FloorPlan219-openable.json
- FloorPlan22-layout.npy
- FloorPlan22-objects.json
- FloorPlan22-openable.json
- FloorPlan220-layout.npy
- FloorPlan220-objects.json
- FloorPlan220-openable.json
- FloorPlan221-layout.npy
- FloorPlan221-objects.json
- FloorPlan221-openable.json
- FloorPlan222-layout.npy
- FloorPlan222-objects.json
- FloorPlan222-openable.json
- FloorPlan223-layout.npy
- FloorPlan223-objects.json
- FloorPlan223-openable.json
- FloorPlan224-layout.npy
- FloorPlan224-objects.json
- FloorPlan224-openable.json
- FloorPlan225-layout.npy
- FloorPlan225-objects.json
- FloorPlan225-openable.json
- FloorPlan226-layout.npy
- FloorPlan226-objects.json
- FloorPlan226-openable.json
- FloorPlan227-layout.npy
- FloorPlan227-objects.json
- FloorPlan227-openable.json
- FloorPlan228-layout.npy
- FloorPlan228-objects.json
- FloorPlan228-openable.json
- FloorPlan229-layout.npy
- FloorPlan229-objects.json
- FloorPlan229-openable.json
- FloorPlan23-layout.npy
- FloorPlan23-objects.json
- FloorPlan23-openable.json
- FloorPlan230-layout.npy
- FloorPlan230-objects.json
- FloorPlan230-openable.json
- FloorPlan24-layout.npy
- FloorPlan24-objects.json
- FloorPlan24-openable.json
- FloorPlan25-layout.npy
- FloorPlan25-objects.json
- FloorPlan25-openable.json
- FloorPlan26-layout.npy
- FloorPlan26-objects.json
- FloorPlan26-openable.json
- FloorPlan27-layout.npy
- FloorPlan27-objects.json
- FloorPlan27-openable.json
- FloorPlan28-layout.npy
- FloorPlan28-objects.json
- FloorPlan28-openable.json
- FloorPlan29-layout.npy
- FloorPlan29-objects.json
- FloorPlan29-openable.json
- FloorPlan3-layout.npy
- FloorPlan3-objects.json
- FloorPlan3-openable.json
- FloorPlan30-layout.npy
- FloorPlan30-objects.json
- FloorPlan30-openable.json
- FloorPlan301-layout.npy
- FloorPlan301-objects.json
- FloorPlan301-openable.json
- FloorPlan302-layout.npy
- FloorPlan302-objects.json
- FloorPlan302-openable.json
- FloorPlan303-layout.npy
- FloorPlan303-objects.json
- FloorPlan303-openable.json
- FloorPlan304-layout.npy
- FloorPlan304-objects.json
- FloorPlan304-openable.json
- FloorPlan305-layout.npy
- FloorPlan305-objects.json
- FloorPlan305-openable.json
- FloorPlan306-layout.npy
- FloorPlan306-objects.json
- FloorPlan306-openable.json
- FloorPlan307-layout.npy
- FloorPlan307-objects.json
- FloorPlan307-openable.json
- FloorPlan308-layout.npy
- FloorPlan308-objects.json
- FloorPlan308-openable.json
- FloorPlan309-layout.npy
- FloorPlan309-objects.json
- FloorPlan309-openable.json
- FloorPlan310-layout.npy
- FloorPlan310-objects.json
- FloorPlan310-openable.json
- FloorPlan311-layout.npy
- FloorPlan311-objects.json
- FloorPlan311-openable.json
- FloorPlan312-layout.npy
- FloorPlan312-objects.json
- FloorPlan312-openable.json
- FloorPlan313-layout.npy
- FloorPlan313-objects.json
- FloorPlan313-openable.json
- FloorPlan314-layout.npy
- FloorPlan314-objects.json
- FloorPlan314-openable.json
- FloorPlan315-layout.npy
- FloorPlan315-objects.json
- FloorPlan315-openable.json
- FloorPlan316-layout.npy
- FloorPlan316-objects.json
- FloorPlan316-openable.json
- FloorPlan317-layout.npy
- FloorPlan317-objects.json
- FloorPlan317-openable.json
- FloorPlan318-layout.npy
- FloorPlan318-objects.json
- FloorPlan318-openable.json
- FloorPlan319-layout.npy
- FloorPlan319-objects.json
- FloorPlan319-openable.json
- FloorPlan320-layout.npy
- FloorPlan320-objects.json
- FloorPlan320-openable.json
- FloorPlan321-layout.npy
- FloorPlan321-objects.json
- FloorPlan321-openable.json
- FloorPlan322-layout.npy
- FloorPlan322-objects.json
- FloorPlan322-openable.json
- FloorPlan323-layout.npy
- FloorPlan323-objects.json
- FloorPlan323-openable.json
- FloorPlan324-layout.npy
- FloorPlan324-objects.json
- FloorPlan324-openable.json
- FloorPlan325-layout.npy
- FloorPlan325-objects.json
- FloorPlan325-openable.json
- FloorPlan326-layout.npy
- FloorPlan326-objects.json
- FloorPlan326-openable.json
- FloorPlan327-layout.npy
- FloorPlan327-objects.json
- FloorPlan327-openable.json
- FloorPlan328-layout.npy
- FloorPlan328-objects.json
- FloorPlan328-openable.json
- FloorPlan329-layout.npy
- FloorPlan329-objects.json
- FloorPlan329-openable.json
- FloorPlan330-layout.npy
- FloorPlan330-objects.json
- FloorPlan330-openable.json
- FloorPlan4-layout.npy
- FloorPlan4-objects.json
- FloorPlan4-openable.json
- FloorPlan401-layout.npy
- FloorPlan401-objects.json
- FloorPlan401-openable.json
- FloorPlan402-layout.npy
- FloorPlan402-objects.json
- FloorPlan402-openable.json
- FloorPlan403-layout.npy
- FloorPlan403-objects.json
- FloorPlan403-openable.json
- FloorPlan404-layout.npy
- FloorPlan404-objects.json
- FloorPlan404-openable.json
- FloorPlan405-layout.npy
- FloorPlan405-objects.json
- FloorPlan405-openable.json
- FloorPlan406-layout.npy
- FloorPlan406-objects.json
- FloorPlan406-openable.json
- FloorPlan407-layout.npy
- FloorPlan407-objects.json
- FloorPlan407-openable.json
- FloorPlan408-layout.npy
- FloorPlan408-objects.json
- FloorPlan408-openable.json
- FloorPlan409-layout.npy
- FloorPlan409-objects.json
- FloorPlan409-openable.json
- FloorPlan410-layout.npy
- FloorPlan410-objects.json
- FloorPlan410-openable.json
- FloorPlan411-layout.npy
- FloorPlan411-objects.json
- FloorPlan411-openable.json
- FloorPlan412-layout.npy
- FloorPlan412-objects.json
- FloorPlan412-openable.json
- FloorPlan413-layout.npy
- FloorPlan413-objects.json
- FloorPlan413-openable.json
- FloorPlan414-layout.npy
- FloorPlan414-objects.json
- FloorPlan414-openable.json
- FloorPlan415-layout.npy
- FloorPlan415-objects.json
- FloorPlan415-openable.json
- FloorPlan416-layout.npy
- FloorPlan416-objects.json
- FloorPlan416-openable.json
- FloorPlan417-layout.npy
- FloorPlan417-objects.json
- FloorPlan417-openable.json
- FloorPlan418-layout.npy
- FloorPlan418-objects.json
- FloorPlan418-openable.json
- FloorPlan419-layout.npy
- FloorPlan419-objects.json
- FloorPlan419-openable.json
- FloorPlan420-layout.npy
- FloorPlan420-objects.json
- FloorPlan420-openable.json
- FloorPlan421-layout.npy
- FloorPlan421-objects.json
- FloorPlan421-openable.json
- FloorPlan422-layout.npy
- FloorPlan422-objects.json
- FloorPlan422-openable.json
- FloorPlan423-layout.npy
- FloorPlan423-objects.json
- FloorPlan423-openable.json
- FloorPlan424-layout.npy
- FloorPlan424-objects.json
- FloorPlan424-openable.json
- FloorPlan425-layout.npy
- FloorPlan425-objects.json
- FloorPlan425-openable.json
- FloorPlan426-layout.npy
- FloorPlan426-objects.json
- FloorPlan426-openable.json
- FloorPlan427-layout.npy
- FloorPlan427-objects.json
- FloorPlan427-openable.json
- FloorPlan428-layout.npy
- FloorPlan428-objects.json
- FloorPlan428-openable.json
- FloorPlan429-layout.npy
- FloorPlan429-objects.json
- FloorPlan429-openable.json
- FloorPlan430-layout.npy
- FloorPlan430-objects.json
- FloorPlan430-openable.json
- FloorPlan5-layout.npy
- FloorPlan5-objects.json
- FloorPlan5-openable.json
- FloorPlan6-layout.npy
- FloorPlan6-objects.json
- FloorPlan6-openable.json
- FloorPlan7-layout.npy
- FloorPlan7-objects.json
- FloorPlan7-openable.json
- FloorPlan8-layout.npy
- FloorPlan8-objects.json
- FloorPlan8-openable.json
- FloorPlan9-layout.npy
- FloorPlan9-objects.json
- FloorPlan9-openable.json
- precompute_layout_locations.py
- PutTaskExtended_domain.pddl
- __init__.py
- ff_planner_handler.py
- pddl.pdf
- generate_trajectories.py
- replay_checks.py
- __init__.py
- bb_util.py
- dataset_management_util.py
- game_util.py
- image_util.py
- py_util.py
- replay_json.py
- video_util.py
- __init__.py
- constants.py
- goal_library.py
- README.md
- __init__.py
- info.py
- utils.py
- config_thor.yaml
- config_tw.yaml
- __init__.py
- envs.py
- projection.py
- __init__.py
- envs.py
- projection.py
- Minecraft.ttf
- C2.png
- C3.png
- C4.png
- C5.png
- C6.png
- C7.png
- C8.png
- C9.png
- CA.png
- card.png
- CJ.png
- CK.png
- CQ.png
- CT.png
- D2.png
- D3.png
- D4.png
- D5.png
- D6.png
- D7.png
- D8.png
- D9.png
- DA.png
- DJ.png
- DK.png
- DQ.png
- DT.png
- H2.png
- H3.png
- H4.png
- H5.png
- H6.png
- H7.png
- H8.png
- H9.png
- HA.png
- HJ.png
- HK.png
- HQ.png
- HT.png
- pointgame_sample.png
- S2.png
- S3.png
- S4.png
- S5.png
- S6.png
- S7.png
- S8.png
- S9.png
- SA.png
- SJ.png
- SK.png
- SQ.png
- ST.png
- __init__.py
- blackjack.py
- ezpoints.py
- numberline.py
- points.py
- __init__.py
- .gitignore
- play_gymcards.ipynb
- play_gymcards_test_text_wrap.ipynb
- README.md
- setup.py
- text_wrapper.py
- __init__.py
- envs.py
- projection.py
- env.py
- utils.py
- __init__.py
- base_text_env.py
- README.md
- registration.py
- __init__.py
- core.py
- search.py
- __init__.py
- core.py
- error.py
- pyproject.toml
- README.md
- __init__.py
- envs.py
- projection.py
- __init__.py
- base.py
- env.py
- room_utils.py
- utils.py
- __init__.py
- envs.py
- projection.py
- bert.py
- modules.py
- rnn.py
- .gitignore
- agent.py
- env.py
- generate_search.py
- logger.py
- README.md
- requirements.txt
- test.py
- train_choice_il.py
- train_rl.py
- train_search_il.py
- convert_product_file_format.py
- lucene_searcher.py
- run_indexing.sh
- __init__.py
- app.py
- predict_help.py
- README.md
- webshop_lite.py
- annotate.py
- generate_attrs.py
- __init__.py
- engine.py
- goal.py
- normalize.py
- __init__.py
- chromedriver
- web_agent_site_env.py
- web_agent_text_env.py
- __init__.py
- models.py
- no-image-available.png
- style.css
- attributes_page.html
- description_page.html
- done_page.html
- features_page.html
- item_page.html
- results_page.html
- review_page.html
- search_page.html
- __init__.py
- app.py
- utils.py
- .gitignore
- conftest.py
- LICENSE.md
- README.md
- README_INSTALL_ARM-MAC.md
- requirements.txt
- requirements_arm.txt
- run_web_agent_text_env.py
- setup.sh
- setup_arm.sh
- __init__.py
- envs.py
- projection.py
- __init__.cpython-312.pyc
- __init__.cpython-313.pyc
- alfworld.cpython-312.pyc
- alfworld.cpython-313.pyc
- appworld.cpython-312.pyc
- appworld.cpython-313.pyc
- gym_cards.cpython-312.pyc
- gym_cards.cpython-313.pyc
- search.cpython-312.pyc
- search.cpython-313.pyc
- sokoban.cpython-312.pyc
- sokoban.cpython-313.pyc
- webshop.cpython-312.pyc
- webshop.cpython-313.pyc
- __init__.py
- alfworld.py
- appworld.py
- gym_cards.py
- search.py
- sokoban.py
- webshop.py
- __init__.py
- base.py
- env_manager.py
- README.md
- __init__.cpython-312.pyc
- __init__.cpython-313.pyc
- base.cpython-312.pyc
- base.cpython-313.pyc
- memory.cpython-312.pyc
- memory.cpython-313.pyc
- retrieval_memory.cpython-312.pyc
- retrieval_memory.cpython-313.pyc
- skill_updater.cpython-312.pyc
- skill_updater.cpython-313.pyc
- skills_only_memory.cpython-312.pyc
- skills_only_memory.cpython-313.pyc
- __init__.py
- base.py
- memory.py
- README.md
- retrieval_memory.py
- skill_updater.py
- skills_only_memory.py
- __init__.cpython-312.pyc
- rollout_loop.cpython-312.pyc
- utils.cpython-312.pyc
- __init__.py
- rollout_loop.py
- utils.py
- __init__.cpython-312.pyc
- episode.cpython-312.pyc
- __init__.py
- episode.py
- Apptainerfile.rocm
- Dockerfile.awsefa
- Dockerfile.ngc.vllm
- Dockerfile.ngc.vllm0.8
- Dockerfile.ngc.vllm0.8.sagemaker
- Dockerfile.rocm
- Dockerfile.sglang
- Dockerfile.vemlp.vllm.te
- Dockerfile.vllm.sglang.megatron
- runllm-widget.js
- logo.png
- checkpoint.rst
- dpo_extension.rst
- fsdp_extension.rst
- megatron_extension.rst
- placement.rst
- ppo_lora.rst
- rope.rst
- baseline.md
- dapo.md
- grpo.md
- ppo.md
- spin.md
- sppo.md
- amd_build_dockerfile_page.rst
- amd_vllm_page.rst
- data.rst
- single_controller.rst
- trainer.rst
- utils.rst
- ascend_quick_start.rst
- config.rst
- gsm8k_example.rst
- multi_modal_example.rst
- ppo_code_architecture.rst
- sandbox_fusion_example.rst
- faq.rst
- framework-comparison.png
- logo-verl-agent.png
- workflow.png
- device_tuning.rst
- perf_tuning.rst
- prepare_data.rst
- reward_function.rst
- multiturn.rst
- sandbox_fusion.rst
- search_tool_example.rst
- install.rst
- multinode.rst
- quickstart.rst
- ray_debug_tutorial.rst
- fsdp_workers.rst
- megatron_workers.rst
- ray_trainer.rst
- sglang_worker.rst
- conf.py
- hybrid_flow.rst
- index.rst
- Makefile
- README.md
- README_vllm0.7.md
- README_vllm0.8.md
- requirements-docs.txt
- single_controller.rst
- run_alfworld.sh
- run_webshop.sh
- prepare.cpython-312.pyc
- aime2024_multiturn_w_tool.py
- dapo_multiturn_w_tool.py
- full_hh_rlhf.py
- geo3k.py
- gsm8k.py
- gsm8k_multiturn_w_tool.py
- hellaswag.py
- math_dataset.py
- multiturn.py
- prepare.py
- preprocess_search_r1_dataset.py
- start_appworld_server.sh
- run_deepseek7b_mutli_node.sh
- run_deepseek_v2_lite_math.sh
- run_alfworld.sh
- run_sokoban.sh
- run_webshop.sh
- run_alfworld.sh
- run_alfworld_lora.sh
- run_blackjack.sh
- run_ezpoints.sh
- run_numberline.sh
- run_search.sh
- run_sokoban.sh
- run_sokoban_qwen3vl.sh
- run_webshop.sh
- run_webshop_lora.sh
- run_webshop_qwen3.sh
- run_alfworld.sh
- run_alfworld_skills.sh
- run_alfworld_skills_train_update.sh
- run_balckjack.sh
- run_search_skills.sh
- run_sokoban.sh
- run_webshop.sh
- run_webshop_skills.sh
- run_alfworld.sh
- run_alfworld.sh
- run_webshop.sh
- gpt4o_alfworld.py
- run_gpt4o_agent.sh
- tutorial.ipynb
- run_alfworld.sh
- run_webshop.sh
- retrieval_launch.sh
- retrieval_server.py
- searchr1_download.py
- run_deepseek_6b7.sh
- run_gemma_2b.sh
- run_gemma_7b.sh
- run_qwen_05_peft.sh
- run_qwen_05_sp2.sh
- run_qwen_05_sp2_liger.sh
- run_qwen_05_sp2.sh
- distill_alfworld.py
- distill_search.py
- distill_webshop.py
- skill_retrieval.py
- sharegpt_to_pairs.py
- validate_and_fix_webshop.py
- dedupe_repetitions.py
- parse_alfworld.py
- parse_search.py
- parse_webshop.py
- aggregate_skills.py
- generate_memory_alfworld.py
- generate_memory_search.py
- generate_memory_webshop.py
- README.md
- run_alfworld.sh
- run_search.sh
- run_webshop.sh
- ray_on_slurm.slurm
- ppo_trainer_split.yaml
- main_ppo_split.py
- README.md
- run_deepseek7b_llm.sh
- split_monkey_patch.py
- pipeline.png
- core_gigpo.cpython-312.pyc
- core_gigpo.py
- claude_style_skills.json
- generated_memories_alfworld_total.json
- prompt.txt
- claude_style_skills_search.json
- generated_memories_search.json
- claude_style_skills.json
- generated_memories_webshop_100.json
- generated_memories_webshop_101-200.json
- dapo_trainer.yaml
- dapo_ray_trainer.py
- main_dapo.py
- prepare_dapo_data.sh
- README.md
- run_dapo_early_qwen2.5_32b.sh
- run_dapo_qwen2.5_32b.sh
- run_dapo_wo_ds_qwen2.5_32b.sh
- test_dapo_7b.sh
- test_dapo_7b_math.sh
- test_dapo_7b_math_megatron.sh
- test_dapo_qwen3_30b_math.sh
- prime_trainer.yaml
- __init__.py
- main_prime.py
- prime_core_algos.py
- prime_dp_rm.py
- prime_fsdp_workers.py
- prime_ray_trainer.py
- run_prime_qwen.sh
- evaluation.yaml
- __init__.py
- gpqa.py
- livecodebench.py
- math.py
- __init__.py
- data_process.py
- main_eval.py
- README.md
- reward_score.py
- run_r1_distill_qwen.sh
- spin_trainer.yaml
- core_algos.py
- dp_actor.py
- fsdp_workers.py
- main_spin.py
- README.md
- run_spin.sh
- spin_trainer.py
- sppo_trainer.yaml
- __init__.py
- dp_actor.py
- main_sppo.py
- README.md
- run_qwen2.5-7b_rm.sh
- sppo_ray_trainer.py
- sppo_worker.py
- README.md
- converter_hf_to_mcore.py
- diagnose.py
- install_vllm_sglang_mcore.sh
- model_merger.py
- alfworld.py
- search.py
- webshop.py
- run_all.sh
- test_tensor_dict.py
- create_dataset.py
- test.parquet
- train.parquet
- config.json
- create_model_tokenizer.py
- generation_config.json
- model.safetensors
- tokenizer_config.json
- main_trainer.py
- README.md
- __init__.py
- task.py
- tokenizer.py
- __init__.py
- run_gen_qwen05.sh
- run_function_reward.sh
- run_model_reward.sh
- run_sft.sh
- test_sp_loss_match.py
- __init__.py
- check_custom_rwd_fn.py
- check_results.py
- run_dapo.sh
- run_gsm8k_fsdp_sgl_multiturn_sf_tool.sh
- run_gsm8k_fsdp_sgl_multiturn_w_tool.sh
- run_ppo_trainer_megatron.sh
- run_prime.sh
- run_r1_distill_qwen_aime24_eval.sh
- run_ray_trainer.sh
- run_ray_trainer_fire_sampling.sh
- run_ray_trainer_rmpad.sh
- run_spin.sh
- run_sppo.sh
- run_test.sh
- test_memory_buffers.py
- test_ops.py
- test_torch_functional.py
- test_linear_cross_entropy.py
- test_transformer.py
- test_transformers_ulysses.py
- run_qwen2_5_05b_grpo.sh
- run_qwen2_5_32b_grpo.sh
- run_qwen2_5_7b_grpo.sh
- main.py
- test_auto_padding.py
- test_check_worker_alive.py
- test_decorator.py
- test_fused_workers.py
- test_ray_local_envs.py
- test_ray_utils.py
- client.py
- README.md
- run.sh
- server.py
- test_colocated_workers.py
- test_colocated_workers_fused.py
- test_data_transfer.py
- test_driverfunc_to_worker.py
- test_high_level_scheduling_api.py
- test_rvdz.py
- test_worker_group_basics.py
- test_worker_group_torch.py
- test_sandbox_fusion.py
- test_sandbox.py
- check_license.py
- test_import.py
- test_decorator.py
- __init__.py
- test_metric_utils.py
- __init__.py
- test_fs.py
- test_import_utils.py
- test_model.py
- test_module.py
- test_timeout_decorator.py
- test_fsdp_ckpt.py
- test_multiturn_sft_dataset.py
- test_rl_dataset.py
- test_rm_dataset.py
- test_sft_dataset.py
- test_pipeline_parallel.py
- test_activation_offload.py
- test_flops_counter.py
- test_seqlen_balancing.py
- test_torch_functional.py
- sandbox_fusion_tool_config
- search_tool_config
- async_rollout_utils.py
- run_fsdp_vllm.py
- test_async_sglang_server.py
- test_hf_rollout.py
- test_sglang_async_rollout_search_tools.py
- test_sglang_async_rollout_sf_tools.py
- test_sglang_async_rollout_w_tools.py
- test_sglang_spmd.py
- test_vllm_hf_loader.py
- test_vllm_multi_turn.py
- test_vllm_spmd.py
- test_vllm_tool_calling.py
- utils_sglang.py
- __init__.py
- kill_github_tests.sh
- test_protocol.py
- __init__.cpython-312.pyc
- protocol.cpython-312.pyc
- __init__.cpython-312.pyc
- registry.cpython-312.pyc
- __init__.py
- llama_loader.py
- llama_loader_depracated.py
- llama_saver.py
- __init__.py
- parallel_attention.py
- parallel_decoder.py
- parallel_linear.py
- parallel_mlp.py
- parallel_rmsnorm.py
- __init__.py
- modeling_llama_megatron.py
- __init__.py
- __init__.py
- config_converter.py
- loader.py
- model_forward.py
- model_initializer.py
- patch_v012.py
- readme.md
- registry.py
- saver.py
- util.py
- weight_converter.py
- __init__.py
- qwen2_loader.py
- qwen2_loader_depracated.py
- qwen2_saver.py
- __init__.py
- parallel_attention.py
- parallel_decoder.py
- parallel_linear.py
- parallel_mlp.py
- parallel_rmsnorm.py
- __init__.py
- modeling_qwen2_megatron.py
- __init__.py
- __init__.cpython-312.pyc
- monkey_patch.cpython-312.pyc
- __init__.py
- kimi_vl.py
- llama.py
- monkey_patch.py
- qwen2.py
- qwen2_5_vl.py
- qwen2_vl.py
- qwen3_vl.py
- __init__.py
- README.md
- registry.py
- weight_loader_registry.py
- __init__.cpython-312.pyc
- __init__.cpython-312.pyc
- decorator.cpython-312.pyc
- worker.cpython-312.pyc
- worker_group.cpython-312.pyc
- __init__.py
- worker.py
- worker_group.py
- __init__.cpython-312.pyc
- ray.cpython-312.pyc
- __init__.py
- ray.py
- __init__.py
- decorator.py
- worker.py
- worker_group.py
- __init__.cpython-312.pyc
- base.cpython-312.pyc
- __init__.py
- base.py
- megatron.py
- __init__.py
- __init__.cpython-312.pyc
- __init__.py
- parallel_state.py
- __init__.cpython-312.pyc
- __init__.py
- arg_utils.py
- config.py
- dtensor_weight_loaders.py
- hf_weight_loader.py
- llm.py
- llm_engine_sp.py
- megatron_weight_loaders.py
- model_loader.py
- model_runner.py
- parallel_state.py
- spmd_gpu_executor.py
- tokenizer.py
- worker.py
- __init__.py
- arg_utils.py
- config.py
- dtensor_weight_loaders.py
- hf_weight_loader.py
- llm.py
- llm_engine_sp.py
- megatron_weight_loaders.py
- model_loader.py
- model_runner.py
- parallel_state.py
- spmd_gpu_executor.py
- tokenizer.py
- worker.py
- __init__.py
- __init__.py
- __init__.py
- search_r1_like_utils.py
- __init__.py
- base_tool.py
- gsm8k_tool.py
- sandbox_fusion_tools.py
- schemas.py
- search_tool.py
- __init__.cpython-312.pyc
- constants_ppo.cpython-312.pyc
- main_ppo.cpython-312.pyc
- evaluation.yaml
- generation.yaml
- ppo_megatron_trainer.yaml
- ppo_trainer.yaml
- sft_trainer.yaml
- __init__.cpython-312.pyc
- core_algos.cpython-312.pyc
- metric_utils.cpython-312.pyc
- ray_trainer.cpython-312.pyc
- reward.cpython-312.pyc
- __init__.py
- core_algos.py
- metric_utils.py
- ray_trainer.py
- reward.py
- __init__.py
- constants_ppo.py
- fsdp_sft_trainer.py
- main_eval.py
- main_generation.py
- main_ppo.py
- runtime_env.yaml
- __init__.cpython-312.pyc
- activation_offload.cpython-312.pyc
- device.cpython-312.pyc
- flops_counter.cpython-312.pyc
- fs.cpython-312.pyc
- fsdp_utils.cpython-312.pyc
- hdfs_io.cpython-312.pyc
- import_utils.cpython-312.pyc
- logging_utils.cpython-312.pyc
- model.cpython-312.pyc
- py_functional.cpython-312.pyc
- ray_utils.cpython-312.pyc
- seqlen_balancing.cpython-312.pyc
- tokenizer.cpython-312.pyc
- torch_dtypes.cpython-312.pyc
- torch_functional.cpython-312.pyc
- tracking.cpython-312.pyc
- transformers_compat.cpython-312.pyc
- ulysses.cpython-312.pyc
- vllm_utils.cpython-312.pyc
- __init__.cpython-312.pyc
- checkpoint_manager.cpython-312.pyc
- fsdp_checkpoint_manager.cpython-312.pyc
- __init__.py
- checkpoint_manager.py
- fsdp_checkpoint_manager.py
- megatron_checkpoint_manager.py
- __init__.cpython-312.pyc
- rl_dataset.cpython-312.pyc
- rm_dataset.cpython-312.pyc
- sft_dataset.cpython-312.pyc
- __init__.py
- multiturn_sft_dataset.py
- README.md
- rl_dataset.py
- rm_dataset.py
- sft_dataset.py
- vision_utils.py
- __init__.cpython-312.pyc
- performance.cpython-312.pyc
- __init__.py
- performance.py
- profile.py
- trajectory_tracker.py
- __init__.py
- torch_functional.py
- __init__.cpython-312.pyc
- aggregate_logger.cpython-312.pyc
- __init__.py
- aggregate_logger.py
- __init__.py
- memory.py
- optimizer.py
- pipeline_parallel.py
- sequence_parallel.py
- tensor_parallel.py
- __init__.cpython-312.pyc
- utils.cpython-312.pyc
- __init__.py
- utils.py
- __init__.py
- ray_backend.py
- __init__.cpython-312.pyc
- __init__.py
- testing_util.py
- utils.py
- __init__.py
- grader.py
- math_normalize.py
- __init__.py
- utils.py
- __init__.py
- geo3k.py
- gsm8k.py
- math.py
- math_batch.py
- math_dapo.py
- math_verify.py
- search_r1_like_qa_em.py
- __init__.py
- activation_offload.py
- config.py
- device.py
- distributed.py
- flops_counter.py
- fs.py
- fsdp_utils.py
- hdfs_io.py
- import_utils.py
- logging_utils.py
- megatron_utils.py
- memory_buffer.py
- model.py
- net_utils.py
- py_functional.py
- ray_utils.py
- seqlen_balancing.py
- tokenizer.py
- torch_dtypes.py
- torch_functional.py
- tracking.py
- transformers_compat.py
- ulysses.py
- vllm_utils.py
- version
- __init__.cpython-312.pyc
- fsdp_workers.cpython-312.pyc
- __init__.cpython-312.pyc
- base.cpython-312.pyc
- dp_actor.cpython-312.pyc
- __init__.py
- base.py
- dp_actor.py
- megatron_actor.py
- __init__.py
- base.py
- dp_critic.py
- megatron_critic.py
- __init__.py
- batch.py
- dapo.py
- naive.py
- prime.py
- __init__.py
- reward_model.py
- __init__.py
- base.py
- __init__.cpython-312.pyc
- async_server.cpython-312.pyc
- base.cpython-312.pyc
- hf_rollout.cpython-312.pyc
- __init__.cpython-312.pyc
- naive_rollout.cpython-312.pyc
- __init__.py
- naive_rollout.py
- __init__.py
- async_sglang_server.py
- sglang_rollout.py
- utils.py
- __init__.cpython-312.pyc
- vllm_rollout_spmd.cpython-312.pyc
- __init__.py
- fire_vllm_rollout.py
- vllm_async_server.py
- vllm_rollout.py
- vllm_rollout_spmd.py
- __init__.py
- async_server.py
- base.py
- hf_rollout.py
- schemas.py
- tokenizer.py
- __init__.cpython-312.pyc
- base.cpython-312.pyc
- fsdp_ulysses.cpython-312.pyc
- fsdp_vllm.cpython-312.pyc
- __init__.py
- base.py
- fsdp_sglang.py
- fsdp_ulysses.py
- fsdp_vllm.py
- megatron_sglang.py
- megatron_vllm.py
- __init__.py
- fsdp_workers.py
- megatron_workers.py
- __init__.py
- protocol.py
- LICENSE
- Notice.txt
- pyproject.toml
- README.md
- requirements.txt
- setup.py
# CDN으로 사용하기
jsDelivrjsDelivr는 공개 GitHub 리포지토리를 별도 설정 없이 CDN으로 즉시 서빙합니다. 버전과 파일을 고르면 웹페이지에 바로 붙일 수 있는 링크와 예시 코드가 만들어집니다.
명령어 용어집
이 문서에서 사용된 명령어를 모아봤습니다. 낯선 명령어가 있다면 펼쳐서 확인해보세요.
git clone
설명 보기 ▼
git clone
Clone an existing repository.
git clone {{remote_repository_location}} {{path/to/directory}}
Clone an existing repository into a new directory (the default directory is the repository name):
git clone --recursive {{remote_repository_location}}
Clone an existing repository and its submodules:
git clone {{[-n|--no-checkout]}} {{remote_repository_location}}
Clone only the `.git` directory of an existing repository:
pip install
설명 보기 ▼
pip install
Install Python packages.
pip install {{package1 package2 ...}}
Install one or more packages:
pip install {{package1 package2 ...}} {{[-U|--upgrade]}}
Upgrade all specified packages to the latest version, installing any that are not already present:
pip install {{package}}=={{version}}
Install a specific version of a package:
python
설명 보기 ▼
python
Python 언어 인터프리터.
더 많은 정보: <https://docs.python.org/using/cmdline.html>.
python
REPL(대화형 셸) 시작:
python {{path/to/file.py}}
특정 Python 파일 실행:
python -i {{path/to/file.py}}
특정 Python 파일 실행 후 REPL 시작:
python3
설명 보기 ▼
python3
이 명령은 `python`의 별칭입니다.
tldr python
자세한 내용은 원본 명령을 참고하세요:
