DAMO-ConvAI
DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.
File Explorer
Download Latest Version (.zip)Showing a partial file list β download the zip above to see everything.
- static.yml
- fr.json
- id_to_passage.json
- vi.json
- inference_generation.py
- inference_rerank.py
- inference_retrieval.py
- outputStandardFileBaseline.json
- README.md
- requirements.txt
- run.sh
- train_generation.py
- train_rerank.py
- train_retrieval.py
- __init__.py
- add_agenda.py
- add_alarm.py
- add_meeting.py
- add_reminder.py
- add_scene.py
- api.py
- appointment_registration.py
- book_hotel.py
- calculator.py
- cancel_registration.py
- cancel_timed_switch.py
- check_token.py
- delete_account.py
- delete_agenda.py
- delete_alarm.py
- delete_meeting.py
- delete_reminder.py
- delete_scene.py
- dictionary.py
- document_qa.py
- emergency_knowledge.py
- forgot_password.py
- get_today.py
- get_user_token.py
- image_caption.py
- modify_agenda.py
- modify_alarm.py
- modify_meeting.py
- modify_password.py
- modify_registration.py
- modify_reminder.py
- modify_scene.py
- open_bank_account.py
- play_music.py
- query_agenda.py
- query_alarm.py
- query_balance.py
- query_health_data.py
- query_history_today.py
- query_meeting.py
- query_registration.py
- query_reminder.py
- query_scene.py
- query_stock.py
- record_health_data.py
- register_user.py
- search_engine.py
- send_email.py
- speech_recognition.py
- symptom_search.py
- timed_switch.py
- tool_search.py
- translate.py
- wiki.py
- all_apis.csv
- exceptions.json
- multi-agent.png
- three_ability.png
- Account.json
- Agenda.json
- Alarm.json
- Appointments.json
- Bank.json
- HealthData.json
- History.json
- Hotel.json
- ImageCaptioning.json
- Meeting.json
- QuestionAnswering.json
- Reminder.json
- Scenes.json
- SearchEngine.json
- SpeechRecognition.json
- Stock.json
- Symptom.json
- TimeSwitch.json
- Wiki.json
- AddAgenda-AddAlarm-GetUserToken-level-2-1.jsonl
- AddAgenda-AddMeeting-GetUserToken-level-2-2.jsonl
- AddAgenda-AddMeeting-GetUserToken-level-2-3.jsonl
- AddAgenda-AddMeeting-GetUserToken-level-2-4.jsonl
- AddAgenda-level-1-1.jsonl
- AddAgenda-level-1-2.jsonl
- AddAlarm-GetReminder-ModifyAgenda-GetUserToken-level-2-1.jsonl
- AddAlarm-level-1-1.jsonl
- AddMeeting-level-1-1.jsonl
- AddReminder-level-1-1.jsonl
- AddReminder-level-1-2.jsonl
- AddReminder-level-1-3.jsonl
- AppointmentRegistration-level-1-1.jsonl
- AppointmentRegistration-level-1-2.jsonl
- AppointmentRegistration-level-1-3.jsonl
- BookHotel-level-1-1.jsonl
- BookHotel-level-1-2.jsonl
- BookHotel-level-1-3.jsonl
- BookHotel-level-1-4.jsonl
- BookHotel-level-1-5.jsonl
- Calculator-level-1-1.jsonl
- Calculator-level-1-2.jsonl
- Calculator-level-1-3.jsonl
- Calculator-QueryHistoryToday-level-2-1.jsonl
- Calculator-QueryHistoryToday-level-2-2.jsonl
- CancelRegistration-level-1-1.jsonl
- CancelRegistration-level-1-2.jsonl
- CancelRegistration-level-1-3.jsonl
- CancelRegistration-RecordHealthData-level-2-1.jsonl
- CancelRegistration-RecordHealthData-level-2-2.jsonl
- CancelRegistration-RecordHealthData-level-2-3.jsonl
- CancelRegistration-RecordHealthData-level-2-4.jsonl
- CancelRegistration-RecordHealthData-level-2-5.jsonl
- CancelRegistration-RecordHealthData-QueryRegistration-level-2-1.jsonl
- CancelRegistration-RecordHealthData-QueryRegistration-level-2-2.jsonl
- CancelTimedSwitch-level-1-1.jsonl
- CancelTimedSwitch-level-1-2.jsonl
- CancelTimedSwitch-level-1-3.jsonl
- CancelTimedSwitch-level-1-4.jsonl
- CancelTimedSwitch-level-1-5.jsonl
- DeleteAccount-level-1-1.jsonl
- DeleteAccount-level-1-2.jsonl
- DeleteAccount-level-1-3.jsonl
- DeleteAccount-ModifyPassword-GetUserToken-level-2-1.jsonl
- DeleteAccount-ModifyPassword-GetUserToken-level-2-2.jsonl
- DeleteAccount-ModifyPassword-GetUserToken-level-2-3.jsonl
- DeleteAccount-ModifyPassword-GetUserToken-level-2-4.jsonl
- DeleteAccount-ModifyPassword-GetUserToken-level-2-5.jsonl
- DeleteAccount-RegisterUser-ForgotPassword-GetUserToken-level-2-1.jsonl
- DeleteAccount-RegisterUser-ForgotPassword-GetUserToken-level-2-2.jsonl
- .gitignore
- API-Bank-arxiv-version.pdf
- api_call_extraction.py
- demo.py
- evaluator.py
- evaluator_by_json.py
- LICENSE
- README.md
- intro.jpeg
- overview.jpeg
- README.md
- run_web_agent_site_env.py
- run_web_agent_text_env.py
- lucene_searcher.py
- __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
- __init__.py
- setup.py
- __init__.py
- base.py
- fastchat_agent.py
- openai_lm_agent.py
- fastchat.json
- openai.json
- alfworld.json
- webshop.json
- alfred.pddl
- alfred.twl2
- alfworld_3prompts.json
- process_format.py
- base_config.yaml
- gamefile_id.txt
- test_indices.json
- test_indices_500.json
- train_indices.json
- __init__.py
- alfworld_env.py
- base.py
- webshop_env.py
- alfworld_icl.json
- alfworld_thought_icl.json
- webshop_icl.json
- webshop_thought_icl.json
- alfworld_inst.txt
- alfworld_thought_inst.txt
- webshop_inst.txt
- webshop_thought_inst.txt
- __init__.py
- templates.py
- __init__.py
- alfworld.py
- base.py
- webshop.py
- __init__.py
- datatypes.py
- main.py
- requirements.txt
- __init__.py
- apply_delta.py
- apply_lora.py
- compression.py
- convert_fp16.py
- llama_condense_monkey_patch.py
- make_delta.py
- model_adapter.py
- model_chatglm.py
- model_codet5p.py
- model_exllama.py
- model_falcon.py
- model_registry.py
- model_xfastertransformer.py
- monkey_patch_non_inplace.py
- rwkv_model.py
- upload_hub.py
- __init__.py
- awq.py
- exllama.py
- gptq.py
- xfastertransformer.py
- api_protocol.py
- openai_api_protocol.py
- nginx.conf
- README.md
- count_unique_users.py
- filter_bad_conv.py
- merge_field.py
- sample.py
- upload_hf_dataset.py
- approve_all.py
- compute_stats.py
- filter_bad_conv.py
- final_post_processing.py
- instructions.md
- merge_oai_tag.py
- process_all.sh
- sample.py
- upload_hf_dataset.py
- basic_stats.py
- clean_battle_data.py
- clean_chat_data.py
- elo_analysis.py
- inspect_conv.py
- intersect_conv_file.py
- leaderboard_csv_to_html.py
- monitor.py
- summarize_cluster.py
- tag_openai_moderation.py
- topic_clustering.py
- __init__.py
- api_provider.py
- base_model_worker.py
- cli.py
- controller.py
- gradio_block_arena_anony.py
- gradio_block_arena_named.py
- gradio_web_server.py
- gradio_web_server_multi.py
- huggingface_api.py
- huggingface_api_worker.py
- inference.py
- launch_all_serve.py
- model_worker.py
- multi_model_worker.py
- openai_api_server.py
- register_worker.py
- shutdown_serve.py
- test_message.py
- test_throughput.py
- vllm_worker.py
- dpo_trainer.py
- llama2_flash_attn_monkey_patch.py
- llama_flash_attn_monkey_patch.py
- llama_xformers_attn_monkey_patch.py
- ppo_trainer.py
- train.py
- train_baichuan.py
- train_dpo.py
- train_dpo_mistral.py
- train_flant5.py
- train_lora.py
- train_lora_t5.py
- train_mem.py
- train_mistral.py
- train_ppo.py
- train_xformers.py
- __init__.py
- constants.py
- conversation.py
- utils.py
- .gitignore
- README.md
- requirements.txt
- setup.sh
- preprocessing.py
- prm.py
- dataset_info.json
- docker-compose.yml
- Dockerfile
- docker-compose.yml
- Dockerfile
- docker-compose.yml
- Dockerfile
- ceval.py
- ceval.zip
- mapping.json
- cmmlu.py
- cmmlu.zip
- mapping.json
- mapping.json
- mmlu.py
- mmlu.zip
- fsdp_config.yaml
- ds_z0_config.json
- ds_z2_config.json
- ds_z2_offload_config.json
- ds_z3_config.json
- ds_z3_offload_config.json
- qwen2_full_sft.yaml
- llama3_full_sft.yaml
- llama3_lora_sft.yaml
- train.sh
- llama3_full_sft.yaml
- expand.sh
- llama3_freeze_sft.yaml
- llama3_lora_sft.yaml
- llama3_full_sft.yaml
- init.sh
- llama3_lora_sft.yaml
- llama3_vllm.yaml
- mistral_vllm.yaml
- llama3_gptq.yaml
- llama3_lora_sft.yaml
- qwen2vl_lora_sft.yaml
- llama3_alfshop_rl.yaml
- llama3_sotopia_pi_rl.yaml
- mistral_sotopia_pi_rl.yaml
- llama3_full_sft.yaml
- qwen2vl_full_sft.yaml
- 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
- qwen2vl_lora_dpo.yaml
- qwen2vl_lora_sft.yaml
- llama3_lora_sft_aqlm.yaml
- llama3_lora_sft_awq.yaml
- llama3_lora_sft_gptq.yaml
- llama3_lora_sft_otfq.yaml
- README.md
- cal_flops.py
- cal_lr.py
- cal_mfu.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
- __init__.py
- app.py
- chat.py
- common.py
- protocol.py
- __init__.py
- base_engine.py
- chat_model.py
- hf_engine.py
- vllm_engine.py
- __init__.py
- feedback.py
- pairwise.py
- pretrain.py
- processor_utils.py
- supervised.py
- unsupervised.py
- __init__.py
- aligner.py
- collator.py
- data_utils.py
- formatter.py
- loader.py
- mm_plugin.py
- parser.py
- preprocess.py
- template.py
- tool_utils.py
- __init__.py
- evaluator.py
- template.py
- __init__.py
- constants.py
- env.py
- logging.py
- misc.py
- packages.py
- ploting.py
- __init__.py
- data_args.py
- evaluation_args.py
- finetuning_args.py
- generating_args.py
- model_args.py
- parser.py
- __init__.py
- attention.py
- checkpointing.py
- embedding.py
- liger_kernel.py
- longlora.py
- misc.py
- mod.py
- moe.py
- packing.py
- quantization.py
- rope.py
- unsloth.py
- valuehead.py
- visual.py
- __init__.py
- adapter.py
- loader.py
- patcher.py
- __init__.py
- trainer.py
- workflow.py
- __init__.py
- trainer.py
- workflow.py
- __init__.py
- ppo_utils.py
- trainer.py
- workflow.py
- __init__.py
- trainer.py
- workflow.py
- __init__.py
- metric.py
- trainer.py
- workflow.py
- __init__.py
- metric.py
- test_loss.py
- trainer.py
- workflow.py
- __init__.py
- callbacks.py
- test_utils.py
- trainer_utils.py
- tuner.py
- __init__.py
- chatbot.py
- data.py
- eval.py
- export.py
- infer.py
- top.py
- train.py
- __init__.py
- chatter.py
- common.py
- css.py
- engine.py
- interface.py
- locales.py
- manager.py
- runner.py
- utils.py
- __init__.py
- cli.py
- launcher.py
- api.py
- train.py
- webui.py
- test_feedback.py
- test_pairwise.py
- test_processor_utils.py
- test_supervised.py
- test_unsupervised.py
- test_collator.py
- test_formatter.py
- test_mm_plugin.py
- test_template.py
- test_chat.py
- test_train.py
- test_eval_template.py
- test_attention.py
- test_checkpointing.py
- test_packing.py
- test_base.py
- test_freeze.py
- test_full.py
- test_lora.py
- test_pissa.py
- .dockerignore
- .env.local
- .gitattributes
- .gitignore
- CITATION.cff
- LICENSE
- Makefile
- MANIFEST.in
- pyproject.toml
- README.md
- requirements.txt
- setup.py
- accordion.tsx
- badge.tsx
- button.tsx
- card.tsx
- checkbox.tsx
- command.tsx
- data-table-faceted-filter.tsx
- dialog.tsx
- dropdown-menu.tsx
- input.tsx
- menubar.tsx
- popover.tsx
- separator.tsx
- table.tsx
- tabs.tsx
- _app.tsx
- _meta.json
- agents.md
- benchmark.md
- environments.md
- examples.mdx
- generation.md
- hyperparameters.md
- index.mdx
- scripts.md
- simulation_modes.md
- troubleshooting.md
- xml.md
- favicon.ico
- favicon.png
- favicon.svg
- next.svg
- vercel.svg
- globals.css
- .nojekyll
- bun.lockb
- components.json
- next-env.d.ts
- next.config.js
- package.json
- postcss.config.mjs
- tailwind.config.ts
- theme.config.jsx
- tsconfig.json
- benchmark_evaluator.py
- evaluate_existing_episode.py
- experiment_eval.py
- fix_missing_episodes.py
- fix_missing_episodes_with_tag.py
- generate_scenarios.py
- generate_script.py
- generate_specific_envs.py
- minimalist_demo.py
- title.png
- empty.css
- Page.html
- heruko_db.png
- heruko_env_config.png
- otree_hub.png
- prolific_release.png
- release_link.png
- __init__.py
- PaymentInfo.html
- Procfile
- __init__.py
- PaymentInfo.html
- Procfile
- example_data.json
- __init__.py
- SotopiaEval.html
- SotopiaEvalInstruction.html
- example_data.json
- __init__.py
- SotopiaEval.html
- SotopiaEvalInstruction.html
- agreement.py
- Procfile
- README.md
- requirements.txt
- settings.py
- 1.1-setup.ipynb
- 1.2-browse-data.ipynb
- figure_plots.ipynb
- redis_serialization.ipynb
- redis_stats.ipynb
- upload_human_annotation_csv_to_db.ipynb
- evaluate_finetuned_full.sh
- evaluate_finetuned_MF.sh
- fix_missing_episodes_with_tag.sh
- run_all.sh
- run_interaction.sh
- run_script_full.sh
- __init__.py
- base_agent.py
- generate_agent_background.py
- llm_agent.py
- redis_agent.py
- __init__.py
- benchmark.py
- __init__.py
- install.py
- menu.py
- published_datasets.json
- __init__.py
- _pixel.py
- __init__.py
- app.py
- __init__.py
- aggregate_annotations.py
- annotators.py
- auto_expires_mixin.py
- env_agent_combo_storage.py
- handshake.py
- logs.py
- persistent_profile.py
- serialization.py
- session_transaction.py
- waiting_room.py
- __init__.py
- evaluators.py
- parallel.py
- __init__.py
- generate.py
- langchain_callback_handler.py
- llama2.py
- sync.py
- __init__.py
- message_classes.py
- messenger.py
- __init__.py
- base.py
- xml_renderer.py
- __init__.py
- base_sampler.py
- constraint_based_sampler.py
- uniform_sampler.py
- __init__.py
- server.py
- utils.py
- chat_server.py
- fastapi_server.py
- generate.gin
- server.gin
- __init__.py
- gin_utils.py
- rerun_missing_episodes_in_batch.gin
- rerun_missing_episodes_with_tag.gin
- run_async_server_in_batch.gin
- run_async_server_in_batch_script.gin
- server.py
- __init__.py
- app.py
- flags.py
- __init__.py
- __init__.py
- __init__.py
- __init__.pyi
- __init__.py
- __init__.pyi
- api.pyi
- __init__.pyi
- env.pyi
- __init__.pyi
- __init__.py
- model.pyi
- __init__.pyi
- __init__.pyi
- _resampling.pyi
- _result_classes.pyi
- __init__.pyi
- __init__.pyi
- __init__.pyi
- __init__.pyi
- test_install.py
- test_database.py
- test_serialization.py
- test_background.json
- test_evaluators.py
- test_get_bio.py
- test_parallel.py
- test_generation.py
- test_xml_renderer.py
- test_sampler.py
- .gitignore
- .pre-commit-config.yaml
- CODE_OF_CONDUCT.md
- libssl1.1_1.1.1f-1ubuntu2.23_amd64.deb
- LICENSE
- README.md
- requirements.txt
- architecture.png
- README.md
- README.md
- system_prompt_template.md
- system_prompt_template_alt.md
- tools.json
- user_query_template_linux.md
- user_query_template_windows.md
- data.jsonl
- 20250108_prompt_rewrite_template.md
- 20250802_algo_coding_template.md
- 20250802_algo_coding_template.rewrited.jsonl
- 20250803_math_template.md
- 20250803_math_template.rewrited.jsonl
- 20250918_math_think_template.md
- 20250918_math_think_template.rewrited.jsonl
- 20250919_code_think_template.md
- 20250919_code_think_template.rewrited.jsonl
- Dockerfile.torch2100
- Dockerfile.torch251.sglang
- Dockerfile.torch251.vllm
- Dockerfile.torch260.sglang
- Dockerfile.torch260.vllm
- Dockerfile.torch280
- Dockerfile.torch291
- style.css
- demo.js
- swe9b_evolution.png
- teaser.png
- trace_overview.png
- trajectories.png
- trajectories_paper.png
- index.html
- deepspeed_zero.yaml
- deepspeed_zero2.yaml
- deepspeed_zero2_cpuoffload.yaml
- deepspeed_zero3.yaml
- deepspeed_zero3_cpuoffload.yaml
- train_coding_v1.sh
- train_coding_v1.yaml
- train_math_v1.sh
- train_math_v1.yaml
- train_swe_v1.sh
- train_swe_v1.yaml
- train_coding_v1.sh
- train_coding_v1.yaml
- train_math_v1.sh
- train_math_v1.yaml
- train_swe_v1.sh
- train_swe_v1.yaml
- train_swe_v4.yaml
- train_swe_v8.yaml
- convert_model.sh
- env_setup.sh
- run_pipeline.sh
- sleep_container.sh
- start_agentic_pipeline.py
- start_agentic_rollout_pipeline.py
- ds_zero2.json
- ds_zero3.json
- ds_zero3_cpuoffload.json
- README.md
- __init__.py
- lora_layer.py
- utils.py
- __init__.py
- config_auto.py
- modeling_auto.py
- __init__.py
- convert_utils.py
- dist_converter.py
- model_converter.py
- post_converter.py
- template.py
- __init__.py
- modeling_deepseek_v3.py
- __init__.py
- __init__.py
- configuration_llama.py
- modeling_llama.py
- __init__.py
- __init__.py
- __init__.py
- __init__.py
- config_qwen2_5_vl.py
- modeling_qwen2_5_vl.py
- __init__.py
- __init__.py
- config_qwen2_vl.py
- modeling_qwen2_vl.py
- __init__.py
- __init__.py
- config_qwen3_5.py
- modeling_qwen3_5.py
- __init__.py
- __init__.py
- __init__.py
- config_qwen3_next.py
- modeling_qwen3_next.py
- __init__.py
- config_qwen3_omni.py
- modeling_qwen3_omni.py
- __init__.py
- config_qwen3_vl.py
- modeling_qwen3_vl.py
- rope_utils.py
- transformer_block.py
- __init__.py
- __init__.py
- __init__.py
- model_config.py
- model_factory.py
- model_utils.py
- __init__.py
- context_parallel.py
- encoder_sequence_parallel.py
- vocab_parallel.py
- __init__.py
- cpu.py
- cuda.py
- npu.py
- platform.py
- rocm.py
- unknown.py
- __init__.py
- dpo_config.py
- dpo_trainer.py
- trainer.py
- utils.py
- __init__.py
- checkpointing.py
- constants.py
- initialize.py
- patcher.py
- training_args.py
- utils.py
- convert.py
- Makefile
- pyproject.toml
- README.md
- requirements.txt
- __init__.py
- base_config.py
- data_args.py
- generating_args.py
- model_args.py
- training_args.py
- worker_config.py
- __init__.py
- chat_template.py
- collator.py
- data_distributor.py
- dataset.py
- global_dataset.py
- loader.py
- sampler.py
- __init__.py
- cluster.py
- model_update_group.py
- worker.py
- __init__.py
- decorator.py
- driver_utils.py
- generate_scheduler.py
- initialize.py
- log_monitor.py
- protocol.py
- resource_manager.py
- reward_scheduler.py
- rollout_mock_mixin.py
- rollout_scheduler.py
- router.py
- storage.py
- user_defined_rollout_loop.py
- __init__.py
- deepspeed_strategy.py
- diffusion_strategy.py
- factory.py
- fsdp2_strategy.py
- hf_strategy.py
- megatron_strategy.py
- mock_strategy.py
- sglang_strategy.py
- strategy.py
- vllm_strategy.py
- __init__.py
- __init__.py
- func_providers.py
- model_providers.py
- trl_patches.py
- __init__.py
- agent_native_env_manager.py
- base_env_manager.py
- encoding_dsv32.py
- mcp_swe_env_manager.py
- step_concat_env_manager.py
- step_env_manager.py
- tir_env_manager.py
- token_mask_utils.py
- traj_env_manager.py
- traj_env_manager_swe.py
- __init__.py
- base_llm_proxy.py
- openai_proxy.py
- policy_proxy.py
- proxy_utils.py
- random_proxy.py
- fail_to_pass.py
- __init__.py
- action_parser.py
- mcp_tool.py
- python_code_tool.py
- registration.py
- speedup.py
- tool_env_wrapper.py
- __init__.py
- agentic_actor_pg_worker.py
- agentic_actor_worker.py
- agentic_config.py
- agentic_pipeline.py
- agentic_rollout_pipeline.py
- environment_worker.py
- utils.py
- __init__.py
- wan_module.py
- __init__.py
- actor_worker.py
- euler.py
- face_tools.py
- reward_fl_config.py
- reward_fl_pipeline.py
- wan_video_vae.py
- __init__.py
- __init__.py
- distill_config.py
- distill_pipeline.py
- distill_vlm_pipeline.py
- distill_worker.py
- logits_transfer_group.py
- various_divergence.py
- __init__.py
- actor_worker.py
- dpo_config.py
- dpo_pipeline.py
- __init__.py
- code_sandbox_reward_worker.py
- crossthinkqa_rule_reward_worker.py
- detection_reward_worker.py
- general_val_rule_reward_worker.py
- ifeval_rule_reward_worker.py
- llm_judge_reward_worker.py
- math_rule_reward_worker.py
- multiple_choice_boxed_rule_reward_worker.py
- remote_reward_system_worker.py
- __init__.py
- actor_pg_worker.py
- actor_worker.py
- rlvr_config.py
- rlvr_pipeline.py
- rlvr_rollout_pipeline.py
- rlvr_vlm_pipeline.py
- utils.py
- sft_config.py
- sft_pipeline.py
- sft_worker.py
- __init__.py
- base_pipeline.py
- base_worker.py
- __init__.py
- cpu.py
- cuda.py
- npu.py
- platform.py
- rocm.py
- unknown.py
- __init__.py
- model_update.py
- offload_states.py
- offload_states_patch.py
- __init__.py
- model_update.py
- qwen3_moe_patch.py
- tiled_mlp.py
- __init__.py
- model_update.py
- offload_states_patch.py
- optimizer.py
- tensor_parallel.py
- __init__.py
- engine.py
- __init__.py
- engine.py
- __init__.py
- engine.py
- __init__.py
- engine.py
- __init__.py
- fp8.py
- __init__.py
- ray_distributed_executor.py
- __init__.py
- ray_distributed_executor.py
- __init__.py
- ray_distributed_executor.py
- __init__.py
- ray_distributed_executor.py
- __init__.py
- ray_distributed_executor.py
- __init__.py
- ray_distributed_executor.py
- __init__.py
- ray_distributed_executor.py
- __init__.py
- async_llm.py
- async_llm_engine.py
- fp8.py
- patch_transformers.py
- ray_distributed_executor.py
- vllm_utils.py
- worker.py
- __init__.py
- __init__.py
- collective.py
- pg_utils.py
- __init__.py
- all_to_all.py
- autograd_gather.py
- globals.py
- hf_flash_attention_patch.py
- monkey_patch.py
- rmpad_ulysses.py
- ulysses_attention.py
- vlm_cp_patch.py
- __init__.py
- evaluator.py
- execute_utils.py
- extract_utils.py
- pass_k_utils.py
- testing_util.py
- __init__.py
- metrics_manager.py
- __init__.py
- asyncio_decorator.py
- checkpoint_manager.py
- config_utils.py
- constants.py
- context_managers.py
- cuda_ipc_utils.py
- deepseekv32_tool_parser.py
- deepspeed_utils.py
- dynamic_batching.py
- env_action_limiter.py
- fp8.py
- fsdp_utils.py
- functionals.py
- glm_tool_parser.py
- hash_utils.py
- import_utils.py
- kimi_tool_parser.py
- kl_controller.py
- logging.py
- minimax_tool_parser.py
- network_utils.py
- offload_nccl.py
- offload_states.py
- packages.py
- prompt.py
- qwen3coder_tool_parser.py
- random_utils.py
- ray_utils.py
- send_recv_utils.py
- sequence_packing.py
- str_utils.py
- taskgroups.py
- tracking.py
- train_infer_corrections.py
- upload_utils.py
- worker_state.py
- __init__.py
- training_4b.md
- training_4b.md
- training_4b.md
- training_9b.md
- README.md
- README.md
- README.md
- README.md
- agentic-rl-harness.md
- ANALYSIS_PLAYBOOK.md
- .gitignore
- LICENSE
- Makefile
- MANIFEST.in
- pyproject.toml
- README.md
- README_zh.md
- requirements_common.txt
- requirements_em_local_debug.txt
- requirements_torch2100_vllm.txt
- requirements_torch260_diffsynth.txt
- requirements_torch260_sglang.txt
- requirements_torch260_vllm.txt
- requirements_torch280_sglang.txt
- requirements_torch280_vllm.txt
- requirements_vision.txt
- setup.py
- flowbench.png
- session_level.sh
- turn_level.sh
- session_metric_display.py
- session_simulate.py
- turn_inference.py
- turn_metric_display.py
- eval_utils.py
- key.json
- llm.py
- request_openai.py
- utils.py
- README.md
- requirements.txt
- 2024_trace_evaluation.jsonl
- intro.pdf
- intro.png
- trace_test_constraint_type.pdf
- trace_test_constraint_type.png
- dataset_info.json
- trace.json
- ds_z0_config.json
- ds_z2_config.json
- ds_z2_offload_config.json
- ds_z3_config.json
- ds_z3_offload_config.json
- .DS_Store
- qwen2_lora_iopo.yaml
- __init__.py
- app.py
- chat.py
- common.py
- protocol.py
- __init__.py
- base_engine.py
- chat_model.py
- hf_engine.py
- vllm_engine.py
- __init__.py
- feedback.py
- pairwise.py
- pretrain.py
- processor_utils.py
- supervised.py
- unsupervised.py
- .DS_Store
- __init__.py
- aligner.py
- collator.py
- data_utils.py
- formatter.py
- loader.py
- parser.py
- preprocess.py
- template.py
- tool_utils.py
- __init__.py
- evaluator.py
- template.py
- __init__.py
- constants.py
- env.py
- logging.py
- misc.py
- packages.py
- ploting.py
- __init__.py
- data_args.py
- evaluation_args.py
- finetuning_args.py
- generating_args.py
- model_args.py
- parser.py
- __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
- .DS_Store
- __init__.py
- adapter.py
- loader.py
- patcher.py
- __init__.py
- trainer.py
- workflow.py
- .DS_Store
- __init__.py
- trainer.py
- workflow.py
- __init__.py
- trainer.py
- workflow.py
- __init__.py
- ppo_utils.py
- trainer.py
- workflow.py
- __init__.py
- trainer.py
- workflow.py
- __init__.py
- metric.py
- trainer.py
- workflow.py
- __init__.py
- metric.py
- trainer.py
- workflow.py
- .DS_Store
- __init__.py
- callbacks.py
- test_utils.py
- trainer_utils.py
- tuner.py
- __init__.py
- chatbot.py
- data.py
- eval.py
- export.py
- infer.py
- top.py
- train.py
- __init__.py
- chatter.py
- common.py
- css.py
- engine.py
- interface.py
- locales.py
- manager.py
- runner.py
- utils.py
- .DS_Store
- __init__.py
- cli.py
- launcher.py
- .DS_Store
- api.py
- train.py
- webui.py
- .DS_Store
- Makefile
- requirements.txt
- setup.py
- README.md
- logo.png
- main_fig.jpg
- claude35sonnet.yaml
- claude3haiku.yaml
- geminipro.yaml
- glm4.yaml
- gpt4.yaml
- gpt4o.yaml
- qwen2.yaml
- loong.jsonl
- args.py
- config.py
- generate.py
- metric.py
- prompt.py
- token_length.py
- util.py
- run.sh
- step1_load_data.py
- step2_model_generate.py
- step3_model_evaluate.py
- step4_cal_metric.py
- test.sh
- vllm_example.sh
- .gitignore
- LICENSE
- README.md
- requirements.txt
- __init__.py
- BasicArguments.py
- ModelArguments.py
- llama_generation
- decorator.py
- parse_args.py
- __init__.py
- BasicProcessor.py
- TokenizeProcessor.py
- data_reader.py
- gsm8k_test.json
- gsm8k_train.json
- tokenizer_utils.py
- gen_math_greedy.py
- get_gsm8k_res.py
- run_gen_math_greedy_vllm_1.sh
- ds_config_zero3.json
- README.md
- __init__.py
- compute_accuracy.py
- data_loader.py
- prompt_utils.py
- run_choice.py
- run_open.py
- run_open_sc.py
- utils.py
- README.md
- .gitignore
- __init__.py
- mammoth-mistral.png
- mammoth_github.png
- README.md
- requirements.txt
- run.sh
- run_llama2_mft.sh
- run_llama2_sft.sh
- run_mistral_mft.sh
- run_mistral_sft.sh
- train.py
- utils.py
- README.md
- README.md
- metamath.svg
- eval_gsm8k.py
- eval_math.py
- LICENSE
- README.MD
- requirements.txt
- run_llama_mft.sh
- run_mistral_mft.sh
- train_math.py
- util.py
- __init__.py
- mask_policy_utils.py
- modeling_llama.py
- modeling_mistral.py
- alpaca_eval.sh
- .gitignore
- conversation.py
- convert_fsdp_to_hf.py
- convert_hf_to_fsdp.py
- dataset.py
- eval_generate.py
- io_utils.py
- preprocess_data.py
- profile_loading.py
- README.md
- requirements.txt
- train.py
- utils.py
- AlpacaEval_Figue1.png
- LICENSE
- README.md
- __init__.py
- basic_outputter.py
- __init__.py
- trainer_436.py
- __init__.py
- run_llama2_7b_gsm8k_mft.sh
- run_llama2_7b_gsm8k_rft100_mft.sh
- run_llama2_7b_gsm8k_rftu33_mft.sh
- run_llama2_7b_gsm8k_sft.sh
- run_llama2_7b_math_mft.sh
- __init__.py
- main.py
- main_res.png
- overview.png
- README.md
- requirements.txt
- multi_gpu_4gpu.yaml
- api_utils.py
- collect_responses.py
- copy_coco_images_into_MMRole.py
- MMRole_data_process.py
- process_MMRole.sh
- process_PCogAlignBench.sh
- MM_pretrain.json
- TextOnly_pretrain.json
- download_related_dataset.sh
- process_laion.py
- process_LLaVANeXT.py
- process_N24News.py
- process_WikiWeb2M_s1.py
- process_WikiWeb2M_s2.py
- README.md
- reformat_pretrain_data.py
- api_utils.py
- metric_MMRole.py
- metric_PCogAlign.py
- api_utils.py
- MMRole_Eval.py
- PCogAlign_Eval.py
- fsdp1.yaml
- fsdp2.yaml
- multi_gpu.yaml
- single_gpu.yaml
- zero1.yaml
- zero2.yaml
- zero3.yaml
- __init__.py
- best_of_n_sampler.py
- dataset_formatting.py
- profiling.py
- vllm_client.py
- __init__.py
- activation_offloading.py
- auxiliary_modules.py
- modeling_base.py
- modeling_sd_base.py
- modeling_value_head.py
- sd_utils.py
- utils.py
- __init__.py
- format_rewards.py
- other_rewards.py
- __init__.py
- dpo.py
- env.py
- grpo.py
- kto.py
- rloo.py
- sft.py
- utils.py
- vllm_serve.py
- lm_model_card.md
- __init__.py
- alignprop_config.py
- alignprop_trainer.py
- bco_config.py
- bco_trainer.py
- callbacks.py
- cpo_config.py
- cpo_trainer.py
- ddpo_config.py
- ddpo_trainer.py
- dpo_config.py
- dpo_trainer.py
- gkd_config.py
- gkd_trainer.py
- grpo_config.py
- grpo_trainer.py
- iterative_sft_config.py
- iterative_sft_trainer.py
- judges.py
- kto_config.py
- kto_trainer.py
- model_config.py
- nash_md_config.py
- nash_md_trainer.py
- online_dpo_config.py
- online_dpo_trainer.py
- orpo_config.py
- orpo_trainer.py
- ppo_config.py
- ppo_trainer.py
- prm_config.py
- prm_trainer.py
- reward_config.py
- reward_trainer.py
- rloo_config.py
- rloo_trainer.py
- sft_config.py
- sft_trainer.py
- utils.py
- xpo_config.py
- xpo_trainer.py
- __init__.py
- cli.py
- core.py
- data_utils.py
- import_utils.py
- mergekit_utils.py
- py.typed
- generate_MMLA_diversity_MMRole.py
- generate_MMLA_diversity_PCogAlign.py
- grpo_trainer.py
- grpo_vlm_MMRole.py
- grpo_vlm_PCogAlign.py
- modeling_qwen2_5_vl_InverseModel.py
- modeling_qwen2_5_vl_PolicyModel.py
- pretrain.py
- pretrain.sh
- prompt_templates.py
- README.md
- requirements.txt
- run_MMRole_RL.sh
- run_PCogAlign_RL.sh
- sft_trainer.py
- sft_vlm_MMRole.py
- sft_vlm_PCogAlign.py
- logo.png
- inference.py
- train.py
- __init__.py
- cosyvoice.py
- frontend.py
- model.py
- __init__.py
- dataset.py
- processor.py
- adp.py
- blocks.py
- dit.py
- dit_v2.py
- sampling.py
- stable_diffusion.py
- stable_diffusion_test.py
- transformer.py
- transformer_use_mask.py
- decoder.py
- flow.py
- flow_gradtts.py
- flow_matching.py
- flow_matching_dit.py
- length_regulator.py
- f0_predictor.py
- generator.py
- llm.py
- __init__.py
- activation.py
- attention.py
- convolution.py
- decoder.py
- decoder_layer.py
- embedding.py
- encoder.py
- encoder_layer.py
- label_smoothing_loss.py
- positionwise_feed_forward.py
- subsampling.py
- __init__.py
- block_mask_util.py
- class_utils.py
- common.py
- executor.py
- file_utils.py
- frontend_utils.py
- mask.py
- scheduler.py
- train_utils.py
- __init__.py
- vocab_16K.yaml
- vocab_6K.yaml
- llava_her_llama.py
- llava_her_qwen.py
- llava_llama.py
- llava_mistral.py
- llava_mpt.py
- llava_qwen.py
- builder.py
- clip_encoder.py
- builder.py
- builder.py
- speech_encoder.py
- builder.py
- generation.py
- speech_generator.py
- builder.py
- generation.py
- speech_generator.py
- builder.py
- speech_projector.py
- builder.py
- clip_encoder.py
- builder.py
- __init__.py
- apply_delta.py
- builder.py
- consolidate.py
- llava_arch.py
- llava_her_arch.py
- make_delta.py
- utils.py
- extreme_ironing.jpg
- waterview.jpg
- __init__.py
- cli.py
- controller.py
- gradio_web_server.py
- model_worker.py
- register_worker.py
- sglang_worker.py
- test_message.py
- llama_flash_attn_monkey_patch.py
- llama_xformers_attn_monkey_patch.py
- llava_trainer.py
- train.py
- train_mem.py
- train_xformers.py
- __init__.py
- constants.py
- conversation.py
- flow_inference.py
- mm_utils.py
- utils.py
- zero2.json
- zero3.json
- zero3_offload.json
- inference.py
- omnicharacter_stage1_qwen2.5.sh
- omnicharacter_stage2_qwen2.5.sh
- pyproject.toml
- README.md
- requirements.txt
- en_0.webm
- en_1.webm
- en_10.webm
- en_11.webm
- en_12.webm
- en_13.webm
- en_14.webm
- en_15.webm
- en_16.webm
- en_17.webm
- en_18.webm
- en_19.webm
- en_2.webm
- en_3.webm
- en_4.webm
- en_5.webm
- en_6.webm
- en_7.webm
- en_8.webm
- en_9.webm
- zh_0.webm
- zh_1.webm
- zh_10.webm
- zh_11.webm
- zh_12.webm
- zh_13.webm
- zh_14.webm
- zh_18.webm
- zh_19.webm
- zh_2.webm
- zh_3.webm
- zh_4.webm
- zh_5.webm
- zh_6.webm
- zh_7.webm
- zh_8.webm
- zh_9.webm
- emotion_temp.wav
- example.png
- framework.png
- librispeech_temp.wav
- logo.png
- question.wav
- temp.wav
- inference.py
- train.py
- __init__.py
- cosyvoice.py
- frontend.py
- model.py
- __init__.py
- dataset.py
- processor.py
- adp.py
- blocks.py
- dit.py
- dit_v2.py
- sampling.py
- stable_diffusion.py
- stable_diffusion_test.py
- transformer.py
- transformer_use_mask.py
- decoder.py
- flow.py
- flow_gradtts.py
- flow_matching.py
- flow_matching_dit.py
- length_regulator.py
- f0_predictor.py
- generator.py
- llm.py
- __init__.py
- activation.py
- attention.py
- convolution.py
- decoder.py
- decoder_layer.py
- embedding.py
- encoder.py
- encoder_layer.py
- label_smoothing_loss.py
- positionwise_feed_forward.py
- subsampling.py
- __init__.py
- block_mask_util.py
- class_utils.py
- common.py
- executor.py
- file_utils.py
- frontend_utils.py
- mask.py
- scheduler.py
- train_utils.py
- __init__.py
- aishell2_eval.jsonl
- asr_eval.py
- et2s_eval.py
- librispeech_eval.jsonl
- omni_eval.py
- openomni_emotion_val.json
- ov_ossey_eval.py
- t2s_eval.py
- wenetspeech_eval.json
- cvbench_eval.py
- eval_gpt_review.py
- eval_gpt_review_bench.py
- eval_gpt_review_visual.py
- eval_pope.py
- eval_science_qa.py
- eval_science_qa_gpt4.py
- eval_science_qa_gpt4_requery.py
- eval_textvqa.py
- generate_webpage_data_from_table.py
- m4c_evaluator.py
- mm_vet_eval.py
- mminst_eval.py
- mmvp_eval.py
- model_qa.py
- model_vqa_blink.py
- model_vqa_cvbench.py
- model_vqa_gqa.py
- model_vqa_loader.py
- model_vqa_mia.py
- model_vqa_mmbench.py
- model_vqa_mminst.py
- model_vqa_mminst2.py
- model_vqa_mmvp.py
- model_vqa_science.py
- model_vqa_test.py
- model_vqa_textvqa.py
- model_vqa_vqa2.py
- omni_eval.py
- ov_odssey_eval.py
- qa_baseline_gpt35.py
- run_llava.py
- summarize_gpt_review.py
- llava_her_llama.py
- llava_her_qwen.py
- llava_llama.py
- llava_mistral.py
- llava_mpt.py
- llava_qwen.py
- builder.py
- clip_encoder.py
- builder.py
- builder.py
- speech_encoder.py
- builder.py
- generation.py
- speech_generator.py
- builder.py
- generation.py
- speech_generator.py
- builder.py
- speech_projector.py
- builder.py
- clip_encoder.py
- builder.py
- __init__.py
- apply_delta.py
- builder.py
- consolidate.py
- llava_arch.py
- llava_her_arch.py
- make_delta.py
- utils.py
- extreme_ironing.jpg
- waterview.jpg
- __init__.py
- cli.py
- controller.py
- gradio_web_server.py
- model_worker.py
- register_worker.py
- sglang_worker.py
- test_message.py
- llama_flash_attn_monkey_patch.py
- llama_xformers_attn_monkey_patch.py
- llava_trainer.py
- train.py
- train_mem.py
- train_xformers.py
- __init__.py
- constants.py
- conversation.py
- flow_inference.py
- mm_utils.py
- utils.py
- gqa.sh
- mmbench.sh
- mmbench_cn.sh
- mme.sh
- seed.sh
- sqa.sh
- textvqa.sh
- finetune.sh
- pretrain.sh
- finetune.sh
- pretrain.sh
- asr_finetune.sh
- image2text_finetune.sh
- image2text_pretrain.sh
- speech2text_pretrain.sh
- text2speech_dpo.sh
- text2speech_pretrain.sh
- text2speech_pretrain_ctc.sh
- asr_finetune.sh
- image2text_finetune.sh
- image2text_pretrain.sh
- speech2text_pretrain.sh
- text2speech_dpo.sh
- text2speech_pretrain.sh
- text2speech_pretrain_6k.sh
- text2speech_pretrain_ctc.sh
- clear.sh
- convert_gqa_for_eval.py
- convert_mmbench_for_submission.py
- convert_mmvet_for_eval.py
- convert_seed_for_submission.py
- convert_sqa_to_llava.py
- convert_sqa_to_llava_base_prompt.py
- convert_vizwiz_for_submission.py
- convert_vqav2_for_submission.py
- zero2.json
- zero3.json
- zero3_offload.json
- run_inference_2.sh
- __init__.py
- base.py
- gpt.py
- gpt_int.py
- __init__.py
- coco_eval.py
- llavabench.py
- mathvista_eval.py
- misc.py
- mmvet_eval.py
- multiple_choice.py
- OCRBench.py
- vqa_eval.py
- yes_or_no.py
- __init__.py
- file.py
- log.py
- misc.py
- vlm.py
- __init__.py
- custom_prompt.py
- dataset.py
- dataset_config.py
- matching_util.py
- mp_util.py
- __init__.py
- base.py
- openomni_llama.py
- openomni_qwen.py
- __init__.py
- config.py
- inference.py
- run.py
- .gitignore
- demo.py
- inference.py
- README.md
- requirements.txt
- dp_config.yaml
- infer_and_eval_main_generate.py
- infer_and_eval_main_reward.py
- infer_and_eval_main_score.py
- infer_func_now.py
- metrics2.py
- reward_model.py
- run_infer_main_dist.sh
- dp_config.yaml
- infer_and_eval_main_generate.py
- infer_and_eval_main_reward.py
- infer_and_eval_main_score.py
- infer_func_now.py
- metrics2.py
- run_infer_main_dist.sh
- automatic_hh.jpg
- automatic_summarize.jpg
- gpt4.jpg
- human.jpg
- pipeline.jpg
- step_1_process.py
- step_2_gen_train_data.py
- step_3_gen_test_data.py
- step_1_process.py
- step_2_gen_train_data.py
- step_3_gen_test_data.py
- __init__.py
- config.py
- data_manager.py
- metrics_hh.py
- metrics_summarize.py
- process_manager.py
- reward_model.py
- ds_config.yaml
- ds_config2.yaml
- main.py
- train3_summarize.sh
- train_hh.sh
- train_summarize.sh
- README.md
- requirements.txt
- README.md
- multi_gpu_42splitgpu.yaml
- multi_gpu_4gpu.yaml
- CoEvolve_RL.py
- CoEvolve_SFT.py
- grpo_config.py
- grpo_trainer.py
- README.md
- run_co_evolve.sh
- collect_evaluated_policy_generations.py
- REMID_estimation.py
- REMID_thought_collection.py
- run.sh
- policy_test.py
- emi_utils.py
- README.md
- requirements.txt
- templates.py
- benchmark.svg
- logo.png
- wechat.jpg
- wechat_npu.jpg
- dataset_info.json
- README.md
- README_zh.md
- wiki_demo.txt
- docker-compose.yml
- Dockerfile
- docker-compose.yml
- Dockerfile
- docker-compose.yml
- Dockerfile
- ceval.py
- ceval.zip
- mapping.json
- cmmlu.py
- cmmlu.zip
- mapping.json
- mapping.json
- mmlu.py
- mmlu.zip
- fsdp_config.yaml
- llama3_vllm.yaml
- sft.yaml
- ds_z0_config.json
- ds_z2_config.json
- ds_z2_offload_config.json
- ds_z3_config.json
- ds_z3_offload_config.json
- qwen2_full_sft.yaml
- llama3_full_sft.yaml
- llama3_lora_sft.yaml
- train.sh
- llama3_full_sft.yaml
- expand.sh
- llama3_freeze_sft.yaml
- llama3_lora_sft.yaml
- llama3_full_sft.yaml
- init.sh
- llama3_lora_sft.yaml
- llama3.yaml
- llama3_lora_sft.yaml
- llama3_vllm.yaml
- llava1_5.yaml
- qwen2_vl.yaml
- llama3_gptq.yaml
- llama3_lora_sft.yaml
- qwen2vl_lora_sft.yaml
- dpo.yaml
- dpo_m.yaml
- positive_sft.yaml
- sft.yaml
- 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
- qwen2vl_lora_dpo.yaml
- qwen2vl_lora_sft.yaml
- llama3_lora_sft_aqlm.yaml
- llama3_lora_sft_awq.yaml
- llama3_lora_sft_gptq.yaml
- llama3_lora_sft_otfq.yaml
- README.md
- README_zh.md
- cal_flops.py
- cal_lr.py
- cal_mfu.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
- __init__.py
- app.py
- chat.py
- common.py
- protocol.py
- __init__.py
- base_engine.py
- chat_model.py
- hf_engine.py
- vllm_engine.py
- __init__.py
- feedback.py
- pairwise.py
- pretrain.py
- processor_utils.py
- supervised.py
- unsupervised.py
- __init__.py
- aligner.py
- collator.py
- data_utils.py
- formatter.py
- loader.py
- mm_plugin.py
- parser.py
- preprocess.py
- template.py
- tool_utils.py
- __init__.py
- evaluator.py
- template.py
- __init__.py
- constants.py
- env.py
- logging.py
- misc.py
- packages.py
- ploting.py
- __init__.py
- data_args.py
- evaluation_args.py
- finetuning_args.py
- generating_args.py
- model_args.py
- parser.py
- __init__.py
- attention.py
- checkpointing.py
- embedding.py
- liger_kernel.py
- longlora.py
- misc.py
- mod.py
- moe.py
- packing.py
- quantization.py
- rope.py
- unsloth.py
- valuehead.py
- visual.py
- __init__.py
- adapter.py
- loader.py
- patcher.py
- __init__.py
- trainer.py
- workflow.py
- __init__.py
- trainer.py
- workflow.py
- __init__.py
- ppo_utils.py
- trainer.py
- workflow.py
- __init__.py
- trainer.py
- workflow.py
- __init__.py
- metric.py
- trainer.py
- workflow.py
- __init__.py
- metric.py
- trainer.py
- workflow.py
- __init__.py
- callbacks.py
- test_utils.py
- trainer_utils.py
- tuner.py
- __init__.py
- chatbot.py
- data.py
- eval.py
- export.py
- infer.py
- top.py
- train.py
- __init__.py
- chatter.py
- common.py
- css.py
- engine.py
- interface.py
- locales.py
- manager.py
- runner.py
- utils.py
- __init__.py
- cli.py
- launcher.py
- api.py
- train.py
- webui.py
- test_feedback.py
- test_pairwise.py
- test_processor_utils.py
- test_supervised.py
- test_unsupervised.py
- test_collator.py
- test_formatter.py
- test_mm_plugin.py
- test_template.py
- test_chat.py
- test_train.py
- test_eval_template.py
- test_attention.py
- test_checkpointing.py
- test_packing.py
- test_base.py
- test_freeze.py
- test_full.py
- test_lora.py
- test_pissa.py
- .dockerignore
- .env.local
- .gitattributes
- .gitignore
- CITATION.cff
- inference.sh
- LICENSE
- Makefile
- MANIFEST.in
- pyproject.toml
- README.md
- README_zh.md
- requirements.txt
- setup.py
- train.sh
- accordion.tsx
- badge.tsx
- button.tsx
- card.tsx
- checkbox.tsx
- command.tsx
- data-table-faceted-filter.tsx
- dialog.tsx
- dropdown-menu.tsx
- input.tsx
- menubar.tsx
- popover.tsx
- separator.tsx
- table.tsx
- tabs.tsx
- _app.tsx
- _meta.json
- agents.md
- benchmark.md
- environments.md
- examples.mdx
- generation.md
- hyperparameters.md
- index.mdx
- scripts.md
- simulation_modes.md
- troubleshooting.md
- xml.md
- favicon.ico
- favicon.png
- favicon.svg
- next.svg
- vercel.svg
- globals.css
- .nojekyll
- bun.lockb
- components.json
- next-env.d.ts
- next.config.js
- package.json
- postcss.config.mjs
- tailwind.config.ts
- theme.config.jsx
- tsconfig.json
- data_filtering_negative.py
- data_filtering_positive.py
- data_filtering_negative.py
- data_filtering_positive.py
- auto_tail.py
- locate.py
- prompt_reverse_engineering.py
- sft_data.py
- benchmark_evaluator.py
- evaluate_existing_episode.py
- experiment_eval.py
- fix_missing_episodes.py
- fix_missing_episodes_with_tag.py
- generate_scenarios.py
- generate_script.py
- generate_specific_envs.py
- minimalist_demo.py
- title.png
- empty.css
- Page.html
- heruko_db.png
- heruko_env_config.png
- otree_hub.png
- prolific_release.png
- release_link.png
- __init__.py
- PaymentInfo.html
- Procfile
- __init__.py
- PaymentInfo.html
- Procfile
- example_data.json
- __init__.py
- SotopiaEval.html
- SotopiaEvalInstruction.html
- example_data.json
- __init__.py
- SotopiaEval.html
- SotopiaEvalInstruction.html
- agreement.py
- Procfile
- README.md
- requirements.txt
- settings.py
- 1.1-setup.ipynb
- 1.2-browse-data.ipynb
- figure_plots.ipynb
- redis_serialization.ipynb
- redis_stats.ipynb
- upload_human_annotation_csv_to_db.ipynb
- evaluate_finetuned_full.sh
- evaluate_finetuned_MF.sh
- fix_missing_episodes_with_tag.sh
- run_all.sh
- run_interaction.sh
- run_script_full.sh
- __init__.py
- base_agent.py
- generate_agent_background.py
- llm_agent.py
- redis_agent.py
- __init__.py
- benchmark.py
- data.json
- __init__.py
- install.py
- menu.py
- published_datasets.json
- __init__.py
- _pixel.py
- __init__.py
- app.py
- __init__.py
- aggregate_annotations.py
- annotators.py
- auto_expires_mixin.py
- env_agent_combo_storage.py
- handshake.py
- logs.py
- persistent_profile.py
- serialization.py
- session_transaction.py
- waiting_room.py
- __init__.py
- evaluators.py
- parallel.py
- __init__.py
- generate.py
- langchain_callback_handler.py
- llama2.py
- sync.py
- __init__.py
- message_classes.py
- messenger.py
- __init__.py
- base.py
- xml_renderer.py
- __init__.py
- base_sampler.py
- constraint_based_sampler.py
- uniform_sampler.py
- __init__.py
- py.typed
- server.py
- utils.py
- chat_server.py
- fastapi_server.py
- generate.gin
- server.gin
- __init__.py
- gin_utils.py
- rerun_missing_episodes_in_batch.gin
- rerun_missing_episodes_with_tag.gin
- run_async_server_in_batch.gin
- run_async_server_in_batch_script.gin
- server.py
- __init__.py
- app.py
- flags.py
- __init__.py
- __init__.py
- __init__.py
- __init__.pyi
- __init__.py
- __init__.pyi
- api.pyi
- __init__.pyi
- env.pyi
- __init__.pyi
- __init__.py
- model.pyi
- __init__.pyi
- __init__.pyi
- _resampling.pyi
- _result_classes.pyi
- __init__.pyi
- __init__.pyi
- __init__.pyi
- __init__.pyi
- test_install.py
- test_database.py
- test_serialization.py
- test_background.json
- test_evaluators.py
- test_get_bio.py
- test_parallel.py
- test_generation.py
- test_xml_renderer.py
- test_sampler.py
- .gitignore
- .pre-commit-config.yaml
- CODE_OF_CONDUCT.md
- del_tag.py
- LICENSE
- look_dialogue.py
- look_tags.py
- poetry.lock
- pyproject.toml
- README.md
- case.png
- libssl1.1_1.1.1f-1ubuntu2.23_amd64.deb
- README.md
- requirements.txt
- benchmark.png
- intro.png
- experts_task.py
- inference-WideDeep.py
- README.md
- run_widedeep.sh
- .DS_Store
- .gitignore
- LICENSE
- README.md
# Installation Guide
1. Get the code
git clone https://github.com/AlibabaResearch/DAMO-ConvAI
Downloads the entire project code from GitHub to your computer.
cd DAMO-ConvAI
Moves into the project folder you just downloaded.
2. Docker
Easy RecommendedPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
β οΈ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.
docker compose -f EPO/LLaMA-Factory/docker/docker-cuda/docker-compose.yml up -d --build
Runs the command against the services defined in the compose file.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
3. Python
EasyPrerequisites
β οΈ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.
pip install -r EPO/Alfshop/eval_agent/requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
jupyter notebook
Launches Jupyter in your browser so you can open and run the notebook (.ipynb) files.
If it runs without errors and prints output in the terminal, it worked.
4. Make
MediumPrerequisites
- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
cd EPO/LLaMA-Factory
This project's files live in a subfolder, so move into it first.
make
Compiles the code based on the generated build configuration to produce an executable.
If it finishes without errors, it worked. Try running the generated executable directly.
// repository documentation
Was this content helpful?
(0 ratings)
