├── .github ├── ISSUE_TEMPLATE │ ├── bug_report.yml │ ├── exp_record.yml │ ├── feature_request.yml │ └── writing_task.yml ├── pull_request_template.md └── workflows │ ├── mypy.yml │ ├── pre-commit.yml │ └── tests.yml ├── .gitignore ├── .pre-commit-config.yaml ├── LICENSE ├── README.md ├── assets ├── acl2024_teaser.png ├── sotopia-pi.png └── title.png ├── data_generate ├── README.md ├── env_files │ ├── used_env.json │ └── used_prompt.csv ├── generate_conversations.py ├── generate_inspirational_prompts.py ├── generate_new_envs.py ├── requirements.txt ├── sample_scenarios.py ├── scripts │ ├── eval_sft.sh │ ├── experiment_eval.py │ ├── generate_conv_sft.sh │ └── sotopia_conf │ │ ├── __init__.py │ │ ├── generation_utils_conf │ │ ├── generate.gin │ │ ├── generate_mistral_gpt-3.5-turbo.gin │ │ ├── generate_mistral_gpt-4.gin │ │ └── generate_mistral_mistral.gin │ │ ├── gin_utils.py │ │ ├── rerun_missing_episodes_in_batch.gin │ │ ├── run_async_server_in_batch.gin │ │ ├── server.py │ │ └── server_conf │ │ └── server.gin └── utils │ ├── __init__.py │ ├── convert_db_into_json.py │ ├── convert_json_to_gen_input.py │ ├── generate.py │ ├── get_env_from_redis.py │ └── sampling_utils.py ├── data_process ├── README.md └── utils │ ├── __init__.py │ ├── data_filtering.py │ ├── filter_args.yml │ ├── human_eval_episodes.py │ ├── interactive_filtering.py │ ├── prompt_reverse_engineering.py │ ├── redis_filtering.py │ ├── redis_transfer.py │ ├── redis_visualization.py │ └── run_filter_prompts.py ├── human_eval └── README.md ├── llm_deploy ├── README.md ├── deploy.sbatch ├── fastchat_deploy.sh ├── requirements.txt └── vllm_deploy.sh ├── llm_rl ├── README.md ├── README_zh.md ├── cli_inference-llama-2-13b.sh ├── deepspeed_config_s2.json ├── deepspeed_config_s3.json ├── finetune-llama-2-13b.sh ├── finetune-mistral-7b-dummy.sh ├── finetune-mistral-7b-full.sh ├── finetune-mistral-7b-lora.sh ├── finetune-mistral-7b-qlora.sh ├── preprocess │ ├── create_dummy.py │ ├── create_sft_data.py │ └── create_sft_data_from_chat.py ├── pyproject.toml ├── reward_model.sh ├── setup.py ├── src │ ├── api_demo.py │ ├── cli_demo.py │ ├── evaluate.py │ ├── export_model.py │ ├── llmtuner │ │ ├── __init__.py │ │ ├── api │ │ │ ├── __init__.py │ │ │ ├── app.py │ │ │ └── protocol.py │ │ ├── chat │ │ │ ├── __init__.py │ │ │ └── stream_chat.py │ │ ├── dsets │ │ │ ├── __init__.py │ │ │ ├── loader.py │ │ │ ├── preprocess.py │ │ │ └── utils.py │ │ ├── extras │ │ │ ├── __init__.py │ │ │ ├── callbacks.py │ │ │ ├── constants.py │ │ │ ├── logging.py │ │ │ ├── misc.py │ │ │ ├── patches │ │ │ │ ├── __init__.py │ │ │ │ └── llama_patch.py │ │ │ ├── ploting.py │ │ │ ├── save_and_load.py │ │ │ └── template.py │ │ ├── hparams │ │ │ ├── __init__.py │ │ │ ├── data_args.py │ │ │ ├── finetuning_args.py │ │ │ ├── general_args.py │ │ │ ├── generating_args.py │ │ │ └── model_args.py │ │ ├── tuner │ │ │ ├── __init__.py │ │ │ ├── core │ │ │ │ ├── __init__.py │ │ │ │ ├── adapter.py │ │ │ │ ├── loader.py │ │ │ │ ├── parser.py │ │ │ │ └── utils.py │ │ │ ├── dpo │ │ │ │ ├── __init__.py │ │ │ │ ├── collator.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── ppo │ │ │ │ ├── __init__.py │ │ │ │ ├── trainer.py │ │ │ │ ├── utils.py │ │ │ │ └── workflow.py │ │ │ ├── pt │ │ │ │ ├── __init__.py │ │ │ │ └── workflow.py │ │ │ ├── rm │ │ │ │ ├── __init__.py │ │ │ │ ├── collator.py │ │ │ │ ├── metric.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ ├── sft │ │ │ │ ├── __init__.py │ │ │ │ ├── custom_callback.py │ │ │ │ ├── metric.py │ │ │ │ ├── trainer.py │ │ │ │ └── workflow.py │ │ │ └── tune.py │ │ └── webui │ │ │ ├── __init__.py │ │ │ ├── chatter.py │ │ │ ├── common.py │ │ │ ├── components │ │ │ ├── __init__.py │ │ │ ├── chatbot.py │ │ │ ├── data.py │ │ │ ├── eval.py │ │ │ ├── export.py │ │ │ ├── infer.py │ │ │ ├── top.py │ │ │ └── train.py │ │ │ ├── css.py │ │ │ ├── engine.py │ │ │ ├── interface.py │ │ │ ├── locales.py │ │ │ ├── manager.py │ │ │ ├── runner.py │ │ │ └── utils.py │ ├── train_bash.py │ ├── train_web.py │ └── web_demo.py └── tests │ ├── cal_flops.py │ ├── llamafy_baichuan2.py │ ├── llamafy_qwen.py │ └── quantize.py ├── llm_self_train ├── README.md ├── check_episodes.py ├── config.yml ├── eval_score.py ├── monitor_and_submit.py ├── pipelines │ ├── __init__.py │ ├── archive_cloud_util.py │ ├── cloud_util.py │ ├── monitor_deploy_and_run_eval.py │ ├── monitor_eval_and_stop_deploy.py │ ├── monitor_utils.py │ ├── pull_data.py │ ├── run_train.py │ ├── submit_deploy.sh │ ├── submit_eval.sh │ └── submit_single_eval.sh ├── requirements.txt ├── resources │ ├── deploy_config.yml │ ├── env_ids.json │ ├── generate.gin │ └── train_args.yml ├── train.py ├── train.sbatch └── train.sh ├── plot_code ├── blue_openai.png ├── figure4.ipynb └── orange_openai.png ├── requirements.txt ├── setup.cfg ├── setup.py └── tests ├── dummyfile └── test_data_format.py /.github/ISSUE_TEMPLATE/bug_report.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/.github/ISSUE_TEMPLATE/bug_report.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/exp_record.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/.github/ISSUE_TEMPLATE/exp_record.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature_request.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/.github/ISSUE_TEMPLATE/feature_request.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/writing_task.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/.github/ISSUE_TEMPLATE/writing_task.yml -------------------------------------------------------------------------------- /.github/pull_request_template.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/.github/pull_request_template.md -------------------------------------------------------------------------------- /.github/workflows/mypy.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/.github/workflows/mypy.yml -------------------------------------------------------------------------------- /.github/workflows/pre-commit.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/.github/workflows/pre-commit.yml -------------------------------------------------------------------------------- /.github/workflows/tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/.github/workflows/tests.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/README.md -------------------------------------------------------------------------------- /assets/acl2024_teaser.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/assets/acl2024_teaser.png -------------------------------------------------------------------------------- /assets/sotopia-pi.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/assets/sotopia-pi.png -------------------------------------------------------------------------------- /assets/title.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/assets/title.png -------------------------------------------------------------------------------- /data_generate/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/README.md -------------------------------------------------------------------------------- /data_generate/env_files/used_env.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/env_files/used_env.json -------------------------------------------------------------------------------- /data_generate/env_files/used_prompt.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/env_files/used_prompt.csv -------------------------------------------------------------------------------- /data_generate/generate_conversations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/generate_conversations.py -------------------------------------------------------------------------------- /data_generate/generate_inspirational_prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/generate_inspirational_prompts.py -------------------------------------------------------------------------------- /data_generate/generate_new_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/generate_new_envs.py -------------------------------------------------------------------------------- /data_generate/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/requirements.txt -------------------------------------------------------------------------------- /data_generate/sample_scenarios.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/sample_scenarios.py -------------------------------------------------------------------------------- /data_generate/scripts/eval_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/eval_sft.sh -------------------------------------------------------------------------------- /data_generate/scripts/experiment_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/experiment_eval.py -------------------------------------------------------------------------------- /data_generate/scripts/generate_conv_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/generate_conv_sft.sh -------------------------------------------------------------------------------- /data_generate/scripts/sotopia_conf/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /data_generate/scripts/sotopia_conf/generation_utils_conf/generate.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/sotopia_conf/generation_utils_conf/generate.gin -------------------------------------------------------------------------------- /data_generate/scripts/sotopia_conf/generation_utils_conf/generate_mistral_gpt-3.5-turbo.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/sotopia_conf/generation_utils_conf/generate_mistral_gpt-3.5-turbo.gin -------------------------------------------------------------------------------- /data_generate/scripts/sotopia_conf/generation_utils_conf/generate_mistral_gpt-4.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/sotopia_conf/generation_utils_conf/generate_mistral_gpt-4.gin -------------------------------------------------------------------------------- /data_generate/scripts/sotopia_conf/generation_utils_conf/generate_mistral_mistral.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/sotopia_conf/generation_utils_conf/generate_mistral_mistral.gin -------------------------------------------------------------------------------- /data_generate/scripts/sotopia_conf/gin_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/sotopia_conf/gin_utils.py -------------------------------------------------------------------------------- /data_generate/scripts/sotopia_conf/rerun_missing_episodes_in_batch.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/sotopia_conf/rerun_missing_episodes_in_batch.gin -------------------------------------------------------------------------------- /data_generate/scripts/sotopia_conf/run_async_server_in_batch.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/sotopia_conf/run_async_server_in_batch.gin -------------------------------------------------------------------------------- /data_generate/scripts/sotopia_conf/server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/sotopia_conf/server.py -------------------------------------------------------------------------------- /data_generate/scripts/sotopia_conf/server_conf/server.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/scripts/sotopia_conf/server_conf/server.gin -------------------------------------------------------------------------------- /data_generate/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /data_generate/utils/convert_db_into_json.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/utils/convert_db_into_json.py -------------------------------------------------------------------------------- /data_generate/utils/convert_json_to_gen_input.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/utils/convert_json_to_gen_input.py -------------------------------------------------------------------------------- /data_generate/utils/generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/utils/generate.py -------------------------------------------------------------------------------- /data_generate/utils/get_env_from_redis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/utils/get_env_from_redis.py -------------------------------------------------------------------------------- /data_generate/utils/sampling_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_generate/utils/sampling_utils.py -------------------------------------------------------------------------------- /data_process/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_process/README.md -------------------------------------------------------------------------------- /data_process/utils/__init__.py: -------------------------------------------------------------------------------- 1 | import os 2 | -------------------------------------------------------------------------------- /data_process/utils/data_filtering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_process/utils/data_filtering.py -------------------------------------------------------------------------------- /data_process/utils/filter_args.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_process/utils/filter_args.yml -------------------------------------------------------------------------------- /data_process/utils/human_eval_episodes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_process/utils/human_eval_episodes.py -------------------------------------------------------------------------------- /data_process/utils/interactive_filtering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_process/utils/interactive_filtering.py -------------------------------------------------------------------------------- /data_process/utils/prompt_reverse_engineering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_process/utils/prompt_reverse_engineering.py -------------------------------------------------------------------------------- /data_process/utils/redis_filtering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_process/utils/redis_filtering.py -------------------------------------------------------------------------------- /data_process/utils/redis_transfer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_process/utils/redis_transfer.py -------------------------------------------------------------------------------- /data_process/utils/redis_visualization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_process/utils/redis_visualization.py -------------------------------------------------------------------------------- /data_process/utils/run_filter_prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/data_process/utils/run_filter_prompts.py -------------------------------------------------------------------------------- /human_eval/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/human_eval/README.md -------------------------------------------------------------------------------- /llm_deploy/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_deploy/README.md -------------------------------------------------------------------------------- /llm_deploy/deploy.sbatch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_deploy/deploy.sbatch -------------------------------------------------------------------------------- /llm_deploy/fastchat_deploy.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_deploy/fastchat_deploy.sh -------------------------------------------------------------------------------- /llm_deploy/requirements.txt: -------------------------------------------------------------------------------- 1 | vllm 2 | -------------------------------------------------------------------------------- /llm_deploy/vllm_deploy.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_deploy/vllm_deploy.sh -------------------------------------------------------------------------------- /llm_rl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/README.md -------------------------------------------------------------------------------- /llm_rl/README_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/README_zh.md -------------------------------------------------------------------------------- /llm_rl/cli_inference-llama-2-13b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/cli_inference-llama-2-13b.sh -------------------------------------------------------------------------------- /llm_rl/deepspeed_config_s2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/deepspeed_config_s2.json -------------------------------------------------------------------------------- /llm_rl/deepspeed_config_s3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/deepspeed_config_s3.json -------------------------------------------------------------------------------- /llm_rl/finetune-llama-2-13b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/finetune-llama-2-13b.sh -------------------------------------------------------------------------------- /llm_rl/finetune-mistral-7b-dummy.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/finetune-mistral-7b-dummy.sh -------------------------------------------------------------------------------- /llm_rl/finetune-mistral-7b-full.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/finetune-mistral-7b-full.sh -------------------------------------------------------------------------------- /llm_rl/finetune-mistral-7b-lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/finetune-mistral-7b-lora.sh -------------------------------------------------------------------------------- /llm_rl/finetune-mistral-7b-qlora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/finetune-mistral-7b-qlora.sh -------------------------------------------------------------------------------- /llm_rl/preprocess/create_dummy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/preprocess/create_dummy.py -------------------------------------------------------------------------------- /llm_rl/preprocess/create_sft_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/preprocess/create_sft_data.py -------------------------------------------------------------------------------- /llm_rl/preprocess/create_sft_data_from_chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/preprocess/create_sft_data_from_chat.py -------------------------------------------------------------------------------- /llm_rl/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/pyproject.toml -------------------------------------------------------------------------------- /llm_rl/reward_model.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/reward_model.sh -------------------------------------------------------------------------------- /llm_rl/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/setup.py -------------------------------------------------------------------------------- /llm_rl/src/api_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/api_demo.py -------------------------------------------------------------------------------- /llm_rl/src/cli_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/cli_demo.py -------------------------------------------------------------------------------- /llm_rl/src/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/evaluate.py -------------------------------------------------------------------------------- /llm_rl/src/export_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/export_model.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/api/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/api/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/api/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/api/app.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/api/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/api/protocol.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/chat/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/chat/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/chat/stream_chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/chat/stream_chat.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/dsets/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/dsets/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/dsets/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/dsets/loader.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/dsets/preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/dsets/preprocess.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/dsets/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/dsets/utils.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/extras/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/extras/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/extras/callbacks.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/extras/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/extras/constants.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/extras/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/extras/logging.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/extras/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/extras/misc.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/extras/patches/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/extras/patches/llama_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/extras/patches/llama_patch.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/extras/ploting.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/extras/ploting.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/extras/save_and_load.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/extras/save_and_load.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/extras/template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/extras/template.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/hparams/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/hparams/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/hparams/data_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/hparams/data_args.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/hparams/finetuning_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/hparams/finetuning_args.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/hparams/general_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/hparams/general_args.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/hparams/generating_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/hparams/generating_args.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/hparams/model_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/hparams/model_args.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/core/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/core/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/core/adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/core/adapter.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/core/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/core/loader.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/core/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/core/parser.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/core/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/core/utils.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/dpo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/dpo/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/dpo/collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/dpo/collator.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/dpo/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/dpo/trainer.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/dpo/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/dpo/workflow.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/ppo/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/ppo/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/ppo/trainer.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/ppo/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/ppo/utils.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/ppo/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/ppo/workflow.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/pt/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/pt/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/pt/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/pt/workflow.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/rm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/rm/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/rm/collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/rm/collator.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/rm/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/rm/metric.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/rm/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/rm/trainer.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/rm/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/rm/workflow.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/sft/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/sft/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/sft/custom_callback.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/sft/custom_callback.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/sft/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/sft/metric.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/sft/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/sft/trainer.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/sft/workflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/sft/workflow.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/tuner/tune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/tuner/tune.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/chatter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/chatter.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/common.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/components/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/components/__init__.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/components/chatbot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/components/chatbot.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/components/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/components/data.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/components/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/components/eval.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/components/export.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/components/export.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/components/infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/components/infer.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/components/top.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/components/top.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/components/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/components/train.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/css.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/css.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/engine.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/interface.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/interface.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/locales.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/locales.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/manager.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/runner.py -------------------------------------------------------------------------------- /llm_rl/src/llmtuner/webui/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/llmtuner/webui/utils.py -------------------------------------------------------------------------------- /llm_rl/src/train_bash.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/train_bash.py -------------------------------------------------------------------------------- /llm_rl/src/train_web.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/train_web.py -------------------------------------------------------------------------------- /llm_rl/src/web_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/src/web_demo.py -------------------------------------------------------------------------------- /llm_rl/tests/cal_flops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/tests/cal_flops.py -------------------------------------------------------------------------------- /llm_rl/tests/llamafy_baichuan2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/tests/llamafy_baichuan2.py -------------------------------------------------------------------------------- /llm_rl/tests/llamafy_qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/tests/llamafy_qwen.py -------------------------------------------------------------------------------- /llm_rl/tests/quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_rl/tests/quantize.py -------------------------------------------------------------------------------- /llm_self_train/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/README.md -------------------------------------------------------------------------------- /llm_self_train/check_episodes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/check_episodes.py -------------------------------------------------------------------------------- /llm_self_train/config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/config.yml -------------------------------------------------------------------------------- /llm_self_train/eval_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/eval_score.py -------------------------------------------------------------------------------- /llm_self_train/monitor_and_submit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/monitor_and_submit.py -------------------------------------------------------------------------------- /llm_self_train/pipelines/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/__init__.py -------------------------------------------------------------------------------- /llm_self_train/pipelines/archive_cloud_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/archive_cloud_util.py -------------------------------------------------------------------------------- /llm_self_train/pipelines/cloud_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/cloud_util.py -------------------------------------------------------------------------------- /llm_self_train/pipelines/monitor_deploy_and_run_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/monitor_deploy_and_run_eval.py -------------------------------------------------------------------------------- /llm_self_train/pipelines/monitor_eval_and_stop_deploy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/monitor_eval_and_stop_deploy.py -------------------------------------------------------------------------------- /llm_self_train/pipelines/monitor_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/monitor_utils.py -------------------------------------------------------------------------------- /llm_self_train/pipelines/pull_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/pull_data.py -------------------------------------------------------------------------------- /llm_self_train/pipelines/run_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/run_train.py -------------------------------------------------------------------------------- /llm_self_train/pipelines/submit_deploy.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/submit_deploy.sh -------------------------------------------------------------------------------- /llm_self_train/pipelines/submit_eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/submit_eval.sh -------------------------------------------------------------------------------- /llm_self_train/pipelines/submit_single_eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/pipelines/submit_single_eval.sh -------------------------------------------------------------------------------- /llm_self_train/requirements.txt: -------------------------------------------------------------------------------- 1 | tqdm 2 | requests 3 | google-cloud-storage 4 | transformers==4.36.0 5 | -------------------------------------------------------------------------------- /llm_self_train/resources/deploy_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/resources/deploy_config.yml -------------------------------------------------------------------------------- /llm_self_train/resources/env_ids.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/resources/env_ids.json -------------------------------------------------------------------------------- /llm_self_train/resources/generate.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/resources/generate.gin -------------------------------------------------------------------------------- /llm_self_train/resources/train_args.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/resources/train_args.yml -------------------------------------------------------------------------------- /llm_self_train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/train.py -------------------------------------------------------------------------------- /llm_self_train/train.sbatch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/train.sbatch -------------------------------------------------------------------------------- /llm_self_train/train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/llm_self_train/train.sh -------------------------------------------------------------------------------- /plot_code/blue_openai.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/plot_code/blue_openai.png -------------------------------------------------------------------------------- /plot_code/figure4.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/plot_code/figure4.ipynb -------------------------------------------------------------------------------- /plot_code/orange_openai.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/plot_code/orange_openai.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/setup.py -------------------------------------------------------------------------------- /tests/dummyfile: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/test_data_format.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sotopia-lab/sotopia-pi/HEAD/tests/test_data_format.py --------------------------------------------------------------------------------