| { |
| "alpaca_en": { |
| "file_name": "alpaca_data_en_52k.json", |
| "file_sha1": "607f94a7f581341e59685aef32f531095232cf23" |
| }, |
| "alpaca_zh": { |
| "file_name": "alpaca_data_zh_51k.json", |
| "file_sha1": "0016a4df88f523aad8dc004ada7575896824a0dc" |
| }, |
| "alpaca_gpt4_en": { |
| "file_name": "alpaca_gpt4_data_en.json", |
| "file_sha1": "647f4ad447bd993e4b6b6223d1be15208bab694a" |
| }, |
| "alpaca_gpt4_zh": { |
| "file_name": "alpaca_gpt4_data_zh.json", |
| "file_sha1": "3eaa3bda364ccdd59925d7448a698256c31ef845" |
| }, |
| "self_cognition": { |
| "file_name": "self_cognition.json", |
| "file_sha1": "6287a730ada924fc5d9eadc6d8f865e01b7a6f67" |
| }, |
| "oaast_sft": { |
| "file_name": "oaast_sft.json", |
| "file_sha1": "7baf5d43e67a91f9bbdf4e400dbe033b87e9757e", |
| "columns": { |
| "prompt": "instruction", |
| "query": "input", |
| "response": "output", |
| "history": "history" |
| } |
| }, |
| "oaast_sft_zh": { |
| "file_name": "oaast_sft_zh.json", |
| "file_sha1": "a6a91f18f80f37b10ded9cf633fb50c033bf7b9f", |
| "columns": { |
| "prompt": "instruction", |
| "query": "input", |
| "response": "output", |
| "history": "history" |
| } |
| }, |
| "lima": { |
| "file_name": "lima.json", |
| "file_sha1": "9db59f6b7007dc4b17529fc63379b9cd61640f37", |
| "columns": { |
| "prompt": "instruction", |
| "query": "input", |
| "response": "output", |
| "history": "history" |
| } |
| }, |
| "glaive_toolcall": { |
| "file_name": "glaive_toolcall_10k.json", |
| "file_sha1": "a6917b85d209df98d31fdecb253c79ebc440f6f3", |
| "formatting": "sharegpt", |
| "columns": { |
| "messages": "conversations", |
| "tools": "tools" |
| } |
| }, |
| "example": { |
| "script_url": "example_dataset", |
| "columns": { |
| "prompt": "instruction", |
| "query": "input", |
| "response": "output", |
| "history": "history" |
| } |
| }, |
| "guanaco": { |
| "hf_hub_url": "JosephusCheung/GuanacoDataset", |
| "ms_hub_url": "AI-ModelScope/GuanacoDataset" |
| }, |
| "belle_2m": { |
| "hf_hub_url": "BelleGroup/train_2M_CN", |
| "ms_hub_url": "AI-ModelScope/train_2M_CN" |
| }, |
| "belle_1m": { |
| "hf_hub_url": "BelleGroup/train_1M_CN", |
| "ms_hub_url": "AI-ModelScope/train_1M_CN" |
| }, |
| "belle_0.5m": { |
| "hf_hub_url": "BelleGroup/train_0.5M_CN", |
| "ms_hub_url": "AI-ModelScope/train_0.5M_CN" |
| }, |
| "belle_dialog": { |
| "hf_hub_url": "BelleGroup/generated_chat_0.4M", |
| "ms_hub_url": "AI-ModelScope/generated_chat_0.4M" |
| }, |
| "belle_math": { |
| "hf_hub_url": "BelleGroup/school_math_0.25M", |
| "ms_hub_url": "AI-ModelScope/school_math_0.25M" |
| }, |
| "belle_multiturn": { |
| "script_url": "belle_multiturn", |
| "formatting": "sharegpt" |
| }, |
| "ultra_chat": { |
| "script_url": "ultra_chat", |
| "formatting": "sharegpt" |
| }, |
| "open_platypus": { |
| "hf_hub_url": "garage-bAInd/Open-Platypus", |
| "ms_hub_url": "AI-ModelScope/Open-Platypus" |
| }, |
| "codealpaca": { |
| "hf_hub_url": "sahil2801/CodeAlpaca-20k", |
| "ms_hub_url": "AI-ModelScope/CodeAlpaca-20k" |
| }, |
| "alpaca_cot": { |
| "hf_hub_url": "QingyiSi/Alpaca-CoT", |
| "ms_hub_url": "AI-ModelScope/Alpaca-CoT" |
| }, |
| "openorca": { |
| "hf_hub_url": "Open-Orca/OpenOrca", |
| "ms_hub_url": "AI-ModelScope/OpenOrca", |
| "columns": { |
| "prompt": "question", |
| "response": "response", |
| "system": "system_prompt" |
| } |
| }, |
| "mathinstruct": { |
| "hf_hub_url": "TIGER-Lab/MathInstruct", |
| "ms_hub_url": "AI-ModelScope/MathInstruct", |
| "columns": { |
| "prompt": "instruction", |
| "response": "output" |
| } |
| }, |
| "firefly": { |
| "hf_hub_url": "YeungNLP/firefly-train-1.1M", |
| "columns": { |
| "prompt": "input", |
| "response": "target" |
| } |
| }, |
| "webqa": { |
| "hf_hub_url": "suolyer/webqa", |
| "ms_hub_url": "AI-ModelScope/webqa", |
| "columns": { |
| "prompt": "input", |
| "response": "output" |
| } |
| }, |
| "webnovel": { |
| "hf_hub_url": "zxbsmk/webnovel_cn", |
| "ms_hub_url": "AI-ModelScope/webnovel_cn" |
| }, |
| "nectar_sft": { |
| "hf_hub_url": "mlinmg/SFT-Nectar" |
| }, |
| "deepctrl": { |
| "ms_hub_url": "deepctrl/deepctrl-sft-data" |
| }, |
| "adgen": { |
| "hf_hub_url": "HasturOfficial/adgen", |
| "ms_hub_url": "AI-ModelScope/adgen", |
| "columns": { |
| "prompt": "content", |
| "response": "summary" |
| } |
| }, |
| "sharegpt_hyper": { |
| "hf_hub_url": "totally-not-an-llm/sharegpt-hyperfiltered-3k", |
| "formatting": "sharegpt" |
| }, |
| "sharegpt4": { |
| "hf_hub_url": "shibing624/sharegpt_gpt4", |
| "ms_hub_url": "AI-ModelScope/sharegpt_gpt4", |
| "formatting": "sharegpt" |
| }, |
| "ultrachat_200k": { |
| "hf_hub_url": "HuggingFaceH4/ultrachat_200k", |
| "ms_hub_url": "AI-ModelScope/ultrachat_200k", |
| "columns": { |
| "messages": "messages" |
| }, |
| "tags": { |
| "role_tag": "role", |
| "content_tag": "content", |
| "user_tag": "human", |
| "assistant_tag": "assistant" |
| }, |
| "formatting": "sharegpt" |
| }, |
| "agent_instruct": { |
| "hf_hub_url": "THUDM/AgentInstruct", |
| "ms_hub_url": "ZhipuAI/AgentInstruct", |
| "formatting": "sharegpt" |
| }, |
| "lmsys_chat": { |
| "hf_hub_url": "lmsys/lmsys-chat-1m", |
| "ms_hub_url": "AI-ModelScope/lmsys-chat-1m", |
| "columns": { |
| "messages": "conversation" |
| }, |
| "tags": { |
| "role_tag": "role", |
| "content_tag": "content", |
| "user_tag": "human", |
| "assistant_tag": "assistant" |
| }, |
| "formatting": "sharegpt" |
| }, |
| "evol_instruct": { |
| "hf_hub_url": "WizardLM/WizardLM_evol_instruct_V2_196k", |
| "formatting": "sharegpt" |
| }, |
| "hh_rlhf_en": { |
| "script_url": "hh_rlhf_en", |
| "columns": { |
| "prompt": "instruction", |
| "response": "output", |
| "history": "history" |
| }, |
| "ranking": true |
| }, |
| "oaast_rm": { |
| "file_name": "oaast_rm.json", |
| "file_sha1": "622d420e9b70003b210618253bd3d9d2891d86cb", |
| "columns": { |
| "prompt": "instruction", |
| "query": "input", |
| "response": "output", |
| "history": "history" |
| }, |
| "ranking": true |
| }, |
| "oaast_rm_zh": { |
| "file_name": "oaast_rm_zh.json", |
| "file_sha1": "1065af1f3784dd61be5e79713a35f427b713a232", |
| "columns": { |
| "prompt": "instruction", |
| "query": "input", |
| "response": "output", |
| "history": "history" |
| }, |
| "ranking": true |
| }, |
| "comparison_gpt4_en": { |
| "file_name": "comparison_gpt4_data_en.json", |
| "file_sha1": "96fa18313544e22444fe20eead7754b17da452ae", |
| "ranking": true |
| }, |
| "comparison_gpt4_zh": { |
| "file_name": "comparison_gpt4_data_zh.json", |
| "file_sha1": "515b18ed497199131ddcc1af950345c11dc5c7fd", |
| "ranking": true |
| }, |
| "nectar_rm": { |
| "hf_hub_url": "mlinmg/RLAIF-Nectar", |
| "ranking": true |
| }, |
| "wiki_demo": { |
| "file_name": "wiki_demo.txt", |
| "file_sha1": "e70375e28eda542a90c68213640cc371898ce181", |
| "columns": { |
| "prompt": "text" |
| } |
| }, |
| "c4_demo": { |
| "file_name": "c4_demo.json", |
| "file_sha1": "a5a0c86759732f9a5238e447fecd74f28a66cca8", |
| "columns": { |
| "prompt": "text" |
| } |
| }, |
| "refinedweb": { |
| "hf_hub_url": "tiiuae/falcon-refinedweb", |
| "columns": { |
| "prompt": "content" |
| } |
| }, |
| "redpajama_v2": { |
| "hf_hub_url": "togethercomputer/RedPajama-Data-V2", |
| "columns": { |
| "prompt": "raw_content" |
| }, |
| "subset": "default" |
| }, |
| "wikipedia_en": { |
| "hf_hub_url": "olm/olm-wikipedia-20221220", |
| "columns": { |
| "prompt": "text" |
| } |
| }, |
| "wikipedia_zh": { |
| "hf_hub_url": "pleisto/wikipedia-cn-20230720-filtered", |
| "ms_hub_url": "AI-ModelScope/wikipedia-cn-20230720-filtered", |
| "columns": { |
| "prompt": "completion" |
| } |
| }, |
| "pile": { |
| "hf_hub_url": "EleutherAI/pile", |
| "columns": { |
| "prompt": "text" |
| }, |
| "subset": "all" |
| }, |
| "skypile": { |
| "hf_hub_url": "Skywork/SkyPile-150B", |
| "columns": { |
| "prompt": "text" |
| } |
| }, |
| "the_stack": { |
| "hf_hub_url": "bigcode/the-stack", |
| "ms_hub_url": "AI-ModelScope/the-stack", |
| "columns": { |
| "prompt": "content" |
| } |
| }, |
| "starcoder_python": { |
| "hf_hub_url": "bigcode/starcoderdata", |
| "ms_hub_url": "AI-ModelScope/starcoderdata", |
| "columns": { |
| "prompt": "content" |
| }, |
| "folder": "python" |
| } |
| } |
|
|
