├── LICENSE ├── README.md ├── assets └── spa_rl_framework.png ├── config └── StepTool_ppo.json ├── envs └── webshop │ ├── setup.py │ └── src │ └── webshop │ ├── __init__.py │ ├── __pycache__ │ └── __init__.cpython-39.pyc │ ├── run_envs │ ├── run_web_agent_site_env.py │ └── run_web_agent_text_env.py │ ├── search_engine │ └── lucene_searcher.py │ ├── transfer │ ├── README.md │ ├── __init__.py │ ├── app.py │ ├── predict_help.py │ └── webshop_lite.py │ └── web_agent_site │ ├── __init__.py │ ├── __pycache__ │ ├── __init__.cpython-39.pyc │ └── utils.cpython-39.pyc │ ├── app.py │ ├── attributes │ ├── annotate.py │ └── generate_attrs.py │ ├── engine │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── engine.cpython-39.pyc │ │ ├── goal.cpython-39.pyc │ │ └── normalize.cpython-39.pyc │ ├── engine.py │ ├── goal.py │ └── normalize.py │ ├── envs │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── web_agent_site_env.cpython-39.pyc │ │ └── web_agent_text_env.cpython-39.pyc │ ├── chromedriver │ ├── web_agent_site_env.py │ └── web_agent_text_env.py │ ├── models │ ├── __init__.py │ └── models.py │ ├── static │ ├── images │ │ └── no-image-available.png │ └── style.css │ ├── templates │ ├── attributes_page.html │ ├── description_page.html │ ├── done_page.html │ ├── features_page.html │ ├── item_page.html │ ├── results_page.html │ ├── review_page.html │ └── search_page.html │ └── utils.py ├── eval ├── llama3_2_3b_eval_alfworld.sh ├── llama3_2_3b_eval_virtualhome.sh └── llama3_2_3b_eval_webshop.sh ├── eval_agent ├── __pycache__ │ └── main.cpython-39.pyc ├── agents │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── base.cpython-39.pyc │ │ ├── fastchat_agent.cpython-39.pyc │ │ └── openai_lm_agent.cpython-39.pyc │ ├── base.py │ ├── fastchat_agent.py │ └── openai_lm_agent.py ├── configs │ ├── model │ │ ├── fastchat.json │ │ ├── fastchat_explore.json │ │ └── openai.json │ └── task │ │ ├── alfworld.json │ │ ├── intercode_sql.json │ │ ├── virtualhome.json │ │ └── webshop.json ├── data │ └── webshop │ │ ├── test_indices.json │ │ ├── test_indices_500.json │ │ └── train_indices.json ├── envs │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── alfworld_env.cpython-39.pyc │ │ ├── base.cpython-39.pyc │ │ ├── intercode_sql_env.cpython-39.pyc │ │ ├── virtualhome_env.cpython-39.pyc │ │ └── webshop_env.cpython-39.pyc │ ├── alfworld_env.py │ ├── base.py │ ├── virtualhome_env.py │ └── webshop_env.py ├── main.py ├── main_vh.py ├── main_webshop.py ├── prompt │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ └── templates.cpython-39.pyc │ ├── icl_examples │ │ ├── alfworld_icl.json │ │ ├── intercode_sql_icl.json │ │ ├── virtualhome_icl.json │ │ └── webshop_icl.json │ ├── instructions │ │ ├── alfworld_inst.txt │ │ ├── intercode_sql_inst.txt │ │ ├── virtualhome_inst.txt │ │ └── webshop_inst.txt │ └── templates.py ├── requirements.txt ├── tasks │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── alfworld.cpython-39.pyc │ │ ├── base.cpython-39.pyc │ │ ├── intercode_sql.cpython-39.pyc │ │ └── webshop.cpython-39.pyc │ ├── alfworld.py │ ├── base.py │ ├── intercode_sql.py │ └── webshop.py └── utils │ ├── __init__.py │ ├── __pycache__ │ ├── __init__.cpython-39.pyc │ └── datatypes.cpython-39.pyc │ ├── datatypes.py │ └── replace_sciworld_score.py ├── exploration ├── alfworld │ ├── generate_response.py │ └── my_generate_response.sh ├── virtualhome │ ├── generate_response.py │ └── my_generate_response.sh └── webshop │ ├── generate_response_webshop.py │ └── my_generate_response_webshop.sh ├── fastchat ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ ├── __init__.cpython-39.pyc │ ├── constants.cpython-310.pyc │ ├── constants.cpython-39.pyc │ ├── conversation.cpython-310.pyc │ ├── conversation.cpython-39.pyc │ ├── utils.cpython-310.pyc │ └── utils.cpython-39.pyc ├── constants.py ├── conversation.py ├── llm_judge │ ├── README.md │ ├── clean_judgment.py │ ├── common.py │ ├── compute_agreement.py │ ├── download_mt_bench_pregenerated.py │ ├── gen_api_answer.py │ ├── gen_judgment.py │ ├── gen_model_answer.py │ ├── qa_browser.py │ └── show_result.py ├── model │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-310.pyc │ │ ├── __init__.cpython-39.pyc │ │ ├── compression.cpython-310.pyc │ │ ├── compression.cpython-39.pyc │ │ ├── llama_condense_monkey_patch.cpython-310.pyc │ │ ├── llama_condense_monkey_patch.cpython-39.pyc │ │ ├── model_adapter.cpython-310.pyc │ │ ├── model_adapter.cpython-39.pyc │ │ ├── model_chatglm.cpython-310.pyc │ │ ├── model_chatglm.cpython-39.pyc │ │ ├── model_codet5p.cpython-310.pyc │ │ ├── model_codet5p.cpython-39.pyc │ │ ├── model_exllama.cpython-310.pyc │ │ ├── model_exllama.cpython-39.pyc │ │ ├── model_falcon.cpython-310.pyc │ │ ├── model_falcon.cpython-39.pyc │ │ ├── model_xfastertransformer.cpython-310.pyc │ │ ├── model_xfastertransformer.cpython-39.pyc │ │ ├── monkey_patch_non_inplace.cpython-310.pyc │ │ └── monkey_patch_non_inplace.cpython-39.pyc │ ├── 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 ├── modules │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-310.pyc │ │ ├── __init__.cpython-39.pyc │ │ ├── awq.cpython-310.pyc │ │ ├── awq.cpython-39.pyc │ │ ├── exllama.cpython-310.pyc │ │ ├── exllama.cpython-39.pyc │ │ ├── gptq.cpython-310.pyc │ │ ├── gptq.cpython-39.pyc │ │ ├── xfastertransformer.cpython-310.pyc │ │ └── xfastertransformer.cpython-39.pyc │ ├── awq.py │ ├── exllama.py │ ├── gptq.py │ └── xfastertransformer.py ├── protocol │ ├── api_protocol.py │ └── openai_api_protocol.py ├── serve │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-310.pyc │ │ ├── __init__.cpython-39.pyc │ │ ├── base_model_worker.cpython-39.pyc │ │ ├── controller.cpython-310.pyc │ │ ├── controller.cpython-39.pyc │ │ ├── inference.cpython-39.pyc │ │ ├── model_worker.cpython-39.pyc │ │ ├── vllm_worker.cpython-310.pyc │ │ └── vllm_worker.cpython-39.pyc │ ├── api_provider.py │ ├── base_model_worker.py │ ├── cli.py │ ├── controller.py │ ├── gateway │ │ ├── README.md │ │ └── nginx.conf │ ├── 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 │ ├── monitor │ │ ├── basic_stats.py │ │ ├── clean_battle_data.py │ │ ├── clean_chat_data.py │ │ ├── dataset_release_scripts │ │ │ ├── arena_33k │ │ │ │ ├── count_unique_users.py │ │ │ │ ├── filter_bad_conv.py │ │ │ │ ├── merge_field.py │ │ │ │ ├── sample.py │ │ │ │ └── upload_hf_dataset.py │ │ │ └── lmsys_chat_1m │ │ │ │ ├── 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 │ │ ├── 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 │ ├── multi_model_worker.py │ ├── openai_api_server.py │ ├── register_worker.py │ ├── shutdown_serve.py │ ├── test_message.py │ ├── test_throughput.py │ └── vllm_worker.py ├── train │ ├── __pycache__ │ │ └── dpo_trainer.cpython-39.pyc │ ├── dpo_trainer.py │ ├── llama2_flash_attn_monkey_patch.py │ ├── llama_flash_attn_monkey_patch.py │ ├── llama_xformers_attn_monkey_patch.py │ ├── ppo_trainer.py │ ├── reward_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_reward.py │ └── train_xformers.py └── utils.py ├── ppo ├── merge.py ├── requirements.txt ├── step_ppo.py ├── step_ppotrainer.py └── train_ppo.sh ├── prm ├── data_org.py ├── inference_prm.py ├── rl_data_org.py └── train_our_progress_model.py ├── requirements.txt └── sft ├── alfworld_llama3b.sh ├── virtualhome_llama3b.sh └── webshop_llama3b.sh /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/README.md -------------------------------------------------------------------------------- /assets/spa_rl_framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/assets/spa_rl_framework.png -------------------------------------------------------------------------------- /config/StepTool_ppo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/config/StepTool_ppo.json -------------------------------------------------------------------------------- /envs/webshop/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/setup.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /envs/webshop/src/webshop/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /envs/webshop/src/webshop/run_envs/run_web_agent_site_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/run_envs/run_web_agent_site_env.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/run_envs/run_web_agent_text_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/run_envs/run_web_agent_text_env.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/search_engine/lucene_searcher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/search_engine/lucene_searcher.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/transfer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/transfer/README.md -------------------------------------------------------------------------------- /envs/webshop/src/webshop/transfer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /envs/webshop/src/webshop/transfer/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/transfer/app.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/transfer/predict_help.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/transfer/predict_help.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/transfer/webshop_lite.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/transfer/webshop_lite.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/__pycache__/utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/__pycache__/utils.cpython-39.pyc -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/app.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/attributes/annotate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/attributes/annotate.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/attributes/generate_attrs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/attributes/generate_attrs.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/engine/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/engine/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/engine/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/engine/__pycache__/engine.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/engine/__pycache__/engine.cpython-39.pyc -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/engine/__pycache__/goal.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/engine/__pycache__/goal.cpython-39.pyc -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/engine/__pycache__/normalize.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/engine/__pycache__/normalize.cpython-39.pyc -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/engine/engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/engine/engine.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/engine/goal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/engine/goal.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/engine/normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/engine/normalize.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/envs/__init__.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/envs/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/envs/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/envs/__pycache__/web_agent_site_env.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/envs/__pycache__/web_agent_site_env.cpython-39.pyc -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/envs/__pycache__/web_agent_text_env.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/envs/__pycache__/web_agent_text_env.cpython-39.pyc -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/envs/chromedriver: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/envs/chromedriver -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/envs/web_agent_site_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/envs/web_agent_site_env.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/envs/web_agent_text_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/envs/web_agent_text_env.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/models/__init__.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/models/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/models/models.py -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/static/images/no-image-available.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/static/images/no-image-available.png -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/static/style.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/static/style.css -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/templates/attributes_page.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/templates/attributes_page.html -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/templates/description_page.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/templates/description_page.html -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/templates/done_page.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/templates/done_page.html -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/templates/features_page.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/templates/features_page.html -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/templates/item_page.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/templates/item_page.html -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/templates/results_page.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/templates/results_page.html -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/templates/review_page.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/templates/review_page.html -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/templates/search_page.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/templates/search_page.html -------------------------------------------------------------------------------- /envs/webshop/src/webshop/web_agent_site/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/envs/webshop/src/webshop/web_agent_site/utils.py -------------------------------------------------------------------------------- /eval/llama3_2_3b_eval_alfworld.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval/llama3_2_3b_eval_alfworld.sh -------------------------------------------------------------------------------- /eval/llama3_2_3b_eval_virtualhome.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval/llama3_2_3b_eval_virtualhome.sh -------------------------------------------------------------------------------- /eval/llama3_2_3b_eval_webshop.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval/llama3_2_3b_eval_webshop.sh -------------------------------------------------------------------------------- /eval_agent/__pycache__/main.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/__pycache__/main.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/agents/__init__.py -------------------------------------------------------------------------------- /eval_agent/agents/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/agents/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/agents/__pycache__/base.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/agents/__pycache__/base.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/agents/__pycache__/fastchat_agent.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/agents/__pycache__/fastchat_agent.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/agents/__pycache__/openai_lm_agent.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/agents/__pycache__/openai_lm_agent.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/agents/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/agents/base.py -------------------------------------------------------------------------------- /eval_agent/agents/fastchat_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/agents/fastchat_agent.py -------------------------------------------------------------------------------- /eval_agent/agents/openai_lm_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/agents/openai_lm_agent.py -------------------------------------------------------------------------------- /eval_agent/configs/model/fastchat.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/configs/model/fastchat.json -------------------------------------------------------------------------------- /eval_agent/configs/model/fastchat_explore.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/configs/model/fastchat_explore.json -------------------------------------------------------------------------------- /eval_agent/configs/model/openai.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/configs/model/openai.json -------------------------------------------------------------------------------- /eval_agent/configs/task/alfworld.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/configs/task/alfworld.json -------------------------------------------------------------------------------- /eval_agent/configs/task/intercode_sql.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/configs/task/intercode_sql.json -------------------------------------------------------------------------------- /eval_agent/configs/task/virtualhome.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/configs/task/virtualhome.json -------------------------------------------------------------------------------- /eval_agent/configs/task/webshop.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/configs/task/webshop.json -------------------------------------------------------------------------------- /eval_agent/data/webshop/test_indices.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/data/webshop/test_indices.json -------------------------------------------------------------------------------- /eval_agent/data/webshop/test_indices_500.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/data/webshop/test_indices_500.json -------------------------------------------------------------------------------- /eval_agent/data/webshop/train_indices.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/data/webshop/train_indices.json -------------------------------------------------------------------------------- /eval_agent/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/__init__.py -------------------------------------------------------------------------------- /eval_agent/envs/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/envs/__pycache__/alfworld_env.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/__pycache__/alfworld_env.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/envs/__pycache__/base.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/__pycache__/base.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/envs/__pycache__/intercode_sql_env.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/__pycache__/intercode_sql_env.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/envs/__pycache__/virtualhome_env.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/__pycache__/virtualhome_env.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/envs/__pycache__/webshop_env.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/__pycache__/webshop_env.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/envs/alfworld_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/alfworld_env.py -------------------------------------------------------------------------------- /eval_agent/envs/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/base.py -------------------------------------------------------------------------------- /eval_agent/envs/virtualhome_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/virtualhome_env.py -------------------------------------------------------------------------------- /eval_agent/envs/webshop_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/envs/webshop_env.py -------------------------------------------------------------------------------- /eval_agent/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/main.py -------------------------------------------------------------------------------- /eval_agent/main_vh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/main_vh.py -------------------------------------------------------------------------------- /eval_agent/main_webshop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/main_webshop.py -------------------------------------------------------------------------------- /eval_agent/prompt/__init__.py: -------------------------------------------------------------------------------- 1 | from .templates import prompt_with_icl -------------------------------------------------------------------------------- /eval_agent/prompt/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/prompt/__pycache__/templates.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/__pycache__/templates.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/prompt/icl_examples/alfworld_icl.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/icl_examples/alfworld_icl.json -------------------------------------------------------------------------------- /eval_agent/prompt/icl_examples/intercode_sql_icl.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/icl_examples/intercode_sql_icl.json -------------------------------------------------------------------------------- /eval_agent/prompt/icl_examples/virtualhome_icl.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/icl_examples/virtualhome_icl.json -------------------------------------------------------------------------------- /eval_agent/prompt/icl_examples/webshop_icl.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/icl_examples/webshop_icl.json -------------------------------------------------------------------------------- /eval_agent/prompt/instructions/alfworld_inst.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/instructions/alfworld_inst.txt -------------------------------------------------------------------------------- /eval_agent/prompt/instructions/intercode_sql_inst.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/instructions/intercode_sql_inst.txt -------------------------------------------------------------------------------- /eval_agent/prompt/instructions/virtualhome_inst.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/instructions/virtualhome_inst.txt -------------------------------------------------------------------------------- /eval_agent/prompt/instructions/webshop_inst.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/instructions/webshop_inst.txt -------------------------------------------------------------------------------- /eval_agent/prompt/templates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/prompt/templates.py -------------------------------------------------------------------------------- /eval_agent/requirements.txt: -------------------------------------------------------------------------------- 1 | openai==0.28.1 2 | backoff 3 | colorama 4 | -------------------------------------------------------------------------------- /eval_agent/tasks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/tasks/__init__.py -------------------------------------------------------------------------------- /eval_agent/tasks/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/tasks/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/tasks/__pycache__/alfworld.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/tasks/__pycache__/alfworld.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/tasks/__pycache__/base.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/tasks/__pycache__/base.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/tasks/__pycache__/intercode_sql.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/tasks/__pycache__/intercode_sql.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/tasks/__pycache__/webshop.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/tasks/__pycache__/webshop.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/tasks/alfworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/tasks/alfworld.py -------------------------------------------------------------------------------- /eval_agent/tasks/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/tasks/base.py -------------------------------------------------------------------------------- /eval_agent/tasks/intercode_sql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/tasks/intercode_sql.py -------------------------------------------------------------------------------- /eval_agent/tasks/webshop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/tasks/webshop.py -------------------------------------------------------------------------------- /eval_agent/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/utils/__init__.py -------------------------------------------------------------------------------- /eval_agent/utils/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/utils/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/utils/__pycache__/datatypes.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/utils/__pycache__/datatypes.cpython-39.pyc -------------------------------------------------------------------------------- /eval_agent/utils/datatypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/utils/datatypes.py -------------------------------------------------------------------------------- /eval_agent/utils/replace_sciworld_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/eval_agent/utils/replace_sciworld_score.py -------------------------------------------------------------------------------- /exploration/alfworld/generate_response.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/exploration/alfworld/generate_response.py -------------------------------------------------------------------------------- /exploration/alfworld/my_generate_response.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/exploration/alfworld/my_generate_response.sh -------------------------------------------------------------------------------- /exploration/virtualhome/generate_response.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/exploration/virtualhome/generate_response.py -------------------------------------------------------------------------------- /exploration/virtualhome/my_generate_response.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/exploration/virtualhome/my_generate_response.sh -------------------------------------------------------------------------------- /exploration/webshop/generate_response_webshop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/exploration/webshop/generate_response_webshop.py -------------------------------------------------------------------------------- /exploration/webshop/my_generate_response_webshop.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/exploration/webshop/my_generate_response_webshop.sh -------------------------------------------------------------------------------- /fastchat/__init__.py: -------------------------------------------------------------------------------- 1 | __version__ = "0.2.34" 2 | -------------------------------------------------------------------------------- /fastchat/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/__pycache__/constants.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/__pycache__/constants.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/__pycache__/constants.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/__pycache__/constants.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/__pycache__/conversation.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/__pycache__/conversation.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/__pycache__/conversation.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/__pycache__/conversation.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/__pycache__/utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/__pycache__/utils.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/__pycache__/utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/__pycache__/utils.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/constants.py -------------------------------------------------------------------------------- /fastchat/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/conversation.py -------------------------------------------------------------------------------- /fastchat/llm_judge/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/llm_judge/README.md -------------------------------------------------------------------------------- /fastchat/llm_judge/clean_judgment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/llm_judge/clean_judgment.py -------------------------------------------------------------------------------- /fastchat/llm_judge/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/llm_judge/common.py -------------------------------------------------------------------------------- /fastchat/llm_judge/compute_agreement.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/llm_judge/compute_agreement.py -------------------------------------------------------------------------------- /fastchat/llm_judge/download_mt_bench_pregenerated.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/llm_judge/download_mt_bench_pregenerated.py -------------------------------------------------------------------------------- /fastchat/llm_judge/gen_api_answer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/llm_judge/gen_api_answer.py -------------------------------------------------------------------------------- /fastchat/llm_judge/gen_judgment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/llm_judge/gen_judgment.py -------------------------------------------------------------------------------- /fastchat/llm_judge/gen_model_answer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/llm_judge/gen_model_answer.py -------------------------------------------------------------------------------- /fastchat/llm_judge/qa_browser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/llm_judge/qa_browser.py -------------------------------------------------------------------------------- /fastchat/llm_judge/show_result.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/llm_judge/show_result.py -------------------------------------------------------------------------------- /fastchat/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__init__.py -------------------------------------------------------------------------------- /fastchat/model/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/compression.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/compression.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/compression.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/compression.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/llama_condense_monkey_patch.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/llama_condense_monkey_patch.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/llama_condense_monkey_patch.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/llama_condense_monkey_patch.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_adapter.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_adapter.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_adapter.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_adapter.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_chatglm.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_chatglm.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_chatglm.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_chatglm.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_codet5p.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_codet5p.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_codet5p.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_codet5p.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_exllama.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_exllama.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_exllama.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_exllama.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_falcon.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_falcon.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_falcon.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_falcon.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_xfastertransformer.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_xfastertransformer.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/model_xfastertransformer.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/model_xfastertransformer.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/monkey_patch_non_inplace.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/monkey_patch_non_inplace.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/model/__pycache__/monkey_patch_non_inplace.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/__pycache__/monkey_patch_non_inplace.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/model/apply_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/apply_delta.py -------------------------------------------------------------------------------- /fastchat/model/apply_lora.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/apply_lora.py -------------------------------------------------------------------------------- /fastchat/model/compression.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/compression.py -------------------------------------------------------------------------------- /fastchat/model/convert_fp16.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/convert_fp16.py -------------------------------------------------------------------------------- /fastchat/model/llama_condense_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/llama_condense_monkey_patch.py -------------------------------------------------------------------------------- /fastchat/model/make_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/make_delta.py -------------------------------------------------------------------------------- /fastchat/model/model_adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/model_adapter.py -------------------------------------------------------------------------------- /fastchat/model/model_chatglm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/model_chatglm.py -------------------------------------------------------------------------------- /fastchat/model/model_codet5p.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/model_codet5p.py -------------------------------------------------------------------------------- /fastchat/model/model_exllama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/model_exllama.py -------------------------------------------------------------------------------- /fastchat/model/model_falcon.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/model_falcon.py -------------------------------------------------------------------------------- /fastchat/model/model_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/model_registry.py -------------------------------------------------------------------------------- /fastchat/model/model_xfastertransformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/model_xfastertransformer.py -------------------------------------------------------------------------------- /fastchat/model/monkey_patch_non_inplace.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/monkey_patch_non_inplace.py -------------------------------------------------------------------------------- /fastchat/model/rwkv_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/rwkv_model.py -------------------------------------------------------------------------------- /fastchat/model/upload_hub.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/model/upload_hub.py -------------------------------------------------------------------------------- /fastchat/modules/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /fastchat/modules/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/modules/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/modules/__pycache__/awq.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/__pycache__/awq.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/modules/__pycache__/awq.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/__pycache__/awq.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/modules/__pycache__/exllama.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/__pycache__/exllama.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/modules/__pycache__/exllama.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/__pycache__/exllama.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/modules/__pycache__/gptq.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/__pycache__/gptq.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/modules/__pycache__/gptq.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/__pycache__/gptq.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/modules/__pycache__/xfastertransformer.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/__pycache__/xfastertransformer.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/modules/__pycache__/xfastertransformer.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/__pycache__/xfastertransformer.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/modules/awq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/awq.py -------------------------------------------------------------------------------- /fastchat/modules/exllama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/exllama.py -------------------------------------------------------------------------------- /fastchat/modules/gptq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/gptq.py -------------------------------------------------------------------------------- /fastchat/modules/xfastertransformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/modules/xfastertransformer.py -------------------------------------------------------------------------------- /fastchat/protocol/api_protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/protocol/api_protocol.py -------------------------------------------------------------------------------- /fastchat/protocol/openai_api_protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/protocol/openai_api_protocol.py -------------------------------------------------------------------------------- /fastchat/serve/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /fastchat/serve/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/serve/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/serve/__pycache__/base_model_worker.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/__pycache__/base_model_worker.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/serve/__pycache__/controller.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/__pycache__/controller.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/serve/__pycache__/controller.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/__pycache__/controller.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/serve/__pycache__/inference.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/__pycache__/inference.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/serve/__pycache__/model_worker.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/__pycache__/model_worker.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/serve/__pycache__/vllm_worker.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/__pycache__/vllm_worker.cpython-310.pyc -------------------------------------------------------------------------------- /fastchat/serve/__pycache__/vllm_worker.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/__pycache__/vllm_worker.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/serve/api_provider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/api_provider.py -------------------------------------------------------------------------------- /fastchat/serve/base_model_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/base_model_worker.py -------------------------------------------------------------------------------- /fastchat/serve/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/cli.py -------------------------------------------------------------------------------- /fastchat/serve/controller.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/controller.py -------------------------------------------------------------------------------- /fastchat/serve/gateway/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/gateway/README.md -------------------------------------------------------------------------------- /fastchat/serve/gateway/nginx.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/gateway/nginx.conf -------------------------------------------------------------------------------- /fastchat/serve/gradio_block_arena_anony.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/gradio_block_arena_anony.py -------------------------------------------------------------------------------- /fastchat/serve/gradio_block_arena_named.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/gradio_block_arena_named.py -------------------------------------------------------------------------------- /fastchat/serve/gradio_web_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/gradio_web_server.py -------------------------------------------------------------------------------- /fastchat/serve/gradio_web_server_multi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/gradio_web_server_multi.py -------------------------------------------------------------------------------- /fastchat/serve/huggingface_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/huggingface_api.py -------------------------------------------------------------------------------- /fastchat/serve/huggingface_api_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/huggingface_api_worker.py -------------------------------------------------------------------------------- /fastchat/serve/inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/inference.py -------------------------------------------------------------------------------- /fastchat/serve/launch_all_serve.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/launch_all_serve.py -------------------------------------------------------------------------------- /fastchat/serve/model_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/model_worker.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/basic_stats.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/basic_stats.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/clean_battle_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/clean_battle_data.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/clean_chat_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/clean_chat_data.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/arena_33k/count_unique_users.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/arena_33k/count_unique_users.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/arena_33k/filter_bad_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/arena_33k/filter_bad_conv.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/arena_33k/merge_field.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/arena_33k/merge_field.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/arena_33k/sample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/arena_33k/sample.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/arena_33k/upload_hf_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/arena_33k/upload_hf_dataset.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/approve_all.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/approve_all.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/compute_stats.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/compute_stats.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/filter_bad_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/filter_bad_conv.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/final_post_processing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/final_post_processing.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/instructions.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/instructions.md -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/merge_oai_tag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/merge_oai_tag.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/process_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/process_all.sh -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/sample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/sample.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/upload_hf_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/dataset_release_scripts/lmsys_chat_1m/upload_hf_dataset.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/elo_analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/elo_analysis.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/inspect_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/inspect_conv.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/intersect_conv_file.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/intersect_conv_file.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/leaderboard_csv_to_html.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/leaderboard_csv_to_html.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/monitor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/monitor.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/summarize_cluster.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/summarize_cluster.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/tag_openai_moderation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/tag_openai_moderation.py -------------------------------------------------------------------------------- /fastchat/serve/monitor/topic_clustering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/monitor/topic_clustering.py -------------------------------------------------------------------------------- /fastchat/serve/multi_model_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/multi_model_worker.py -------------------------------------------------------------------------------- /fastchat/serve/openai_api_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/openai_api_server.py -------------------------------------------------------------------------------- /fastchat/serve/register_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/register_worker.py -------------------------------------------------------------------------------- /fastchat/serve/shutdown_serve.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/shutdown_serve.py -------------------------------------------------------------------------------- /fastchat/serve/test_message.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/test_message.py -------------------------------------------------------------------------------- /fastchat/serve/test_throughput.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/test_throughput.py -------------------------------------------------------------------------------- /fastchat/serve/vllm_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/serve/vllm_worker.py -------------------------------------------------------------------------------- /fastchat/train/__pycache__/dpo_trainer.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/__pycache__/dpo_trainer.cpython-39.pyc -------------------------------------------------------------------------------- /fastchat/train/dpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/dpo_trainer.py -------------------------------------------------------------------------------- /fastchat/train/llama2_flash_attn_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/llama2_flash_attn_monkey_patch.py -------------------------------------------------------------------------------- /fastchat/train/llama_flash_attn_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/llama_flash_attn_monkey_patch.py -------------------------------------------------------------------------------- /fastchat/train/llama_xformers_attn_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/llama_xformers_attn_monkey_patch.py -------------------------------------------------------------------------------- /fastchat/train/ppo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/ppo_trainer.py -------------------------------------------------------------------------------- /fastchat/train/reward_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/reward_trainer.py -------------------------------------------------------------------------------- /fastchat/train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train.py -------------------------------------------------------------------------------- /fastchat/train/train_baichuan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_baichuan.py -------------------------------------------------------------------------------- /fastchat/train/train_dpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_dpo.py -------------------------------------------------------------------------------- /fastchat/train/train_dpo_mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_dpo_mistral.py -------------------------------------------------------------------------------- /fastchat/train/train_flant5.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_flant5.py -------------------------------------------------------------------------------- /fastchat/train/train_lora.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_lora.py -------------------------------------------------------------------------------- /fastchat/train/train_lora_t5.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_lora_t5.py -------------------------------------------------------------------------------- /fastchat/train/train_mem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_mem.py -------------------------------------------------------------------------------- /fastchat/train/train_mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_mistral.py -------------------------------------------------------------------------------- /fastchat/train/train_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_ppo.py -------------------------------------------------------------------------------- /fastchat/train/train_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_reward.py -------------------------------------------------------------------------------- /fastchat/train/train_xformers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/train/train_xformers.py -------------------------------------------------------------------------------- /fastchat/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/fastchat/utils.py -------------------------------------------------------------------------------- /ppo/merge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/ppo/merge.py -------------------------------------------------------------------------------- /ppo/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/ppo/requirements.txt -------------------------------------------------------------------------------- /ppo/step_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/ppo/step_ppo.py -------------------------------------------------------------------------------- /ppo/step_ppotrainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/ppo/step_ppotrainer.py -------------------------------------------------------------------------------- /ppo/train_ppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/ppo/train_ppo.sh -------------------------------------------------------------------------------- /prm/data_org.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/prm/data_org.py -------------------------------------------------------------------------------- /prm/inference_prm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/prm/inference_prm.py -------------------------------------------------------------------------------- /prm/rl_data_org.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/prm/rl_data_org.py -------------------------------------------------------------------------------- /prm/train_our_progress_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/prm/train_our_progress_model.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/requirements.txt -------------------------------------------------------------------------------- /sft/alfworld_llama3b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/sft/alfworld_llama3b.sh -------------------------------------------------------------------------------- /sft/virtualhome_llama3b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/sft/virtualhome_llama3b.sh -------------------------------------------------------------------------------- /sft/webshop_llama3b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/WangHanLinHenry/SPA-RL-Agent/HEAD/sft/webshop_llama3b.sh --------------------------------------------------------------------------------