LLaMA-Factory-Mirror/data/dataset_info.json

{
  "alpaca_en": {
    "file_name": "alpaca_data_en_52k.json"
  },
  "alpaca_zh": {
    "file_name": "alpaca_data_zh_51k.json"
  },
  "alpaca_gpt4_en": {
    "file_name": "alpaca_gpt4_data_en.json"
  },
  "alpaca_gpt4_zh": {
    "file_name": "alpaca_gpt4_data_zh.json"
  },
  "identity": {
    "file_name": "identity.json"
  },
  "oaast_sft_zh": {
    "file_name": "oaast_sft_zh.json",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    }
  },
  "lima": {
    "file_name": "lima.json",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    }
  },
  "kto-mix-test": {
    "file_name": "kto-mix-test.json",
    "file_sha1": "91b59f657007dc4b17529fc643v9b9cd6d640fha",
    "columns": {
      "prompt": "instruction",
      "response": "output",
      "tag": "tag"
    }
  },
  "glaive_toolcall": {
    "file_name": "glaive_toolcall_10k.json",
    "formatting": "sharegpt",
    "columns": {
      "messages": "conversations",
      "tools": "tools"
    }
  },
  "mllm_demo": {
    "file_name": "mllm_demo.json",
    "formatting": "sharegpt",
    "columns": {
      "messages": "messages",
      "images": "images"
    },
    "tags": {
      "role_tag": "role",
      "content_tag": "content",
      "user_tag": "user",
      "assistant_tag": "assistant"
    }
  },
  "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"
    }
  },
  "slimorca": {
    "hf_hub_url": "Open-Orca/SlimOrca",
    "formatting": "sharegpt"
  },
  "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"
    }
  },
  "wikiqa": {
    "hf_hub_url": "wiki_qa",
    "columns": {
      "prompt": "question",
      "response": "answer"
    }
  },
  "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": "AstraMindAI/SFT-Nectar",
    "ms_hub_url": "AI-ModelScope/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",
    "formatting": "sharegpt",
    "columns": {
      "messages": "messages"
    },
    "tags": {
      "role_tag": "role",
      "content_tag": "content",
      "user_tag": "user",
      "assistant_tag": "assistant"
    }
  },
  "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",
    "formatting": "sharegpt",
    "columns": {
      "messages": "conversation"
    },
    "tags": {
      "role_tag": "role",
      "content_tag": "content",
      "user_tag": "human",
      "assistant_tag": "assistant"
    }
  },
  "evol_instruct": {
    "hf_hub_url": "WizardLM/WizardLM_evol_instruct_V2_196k",
    "ms_hub_url": "AI-ModelScope/WizardLM_evol_instruct_V2_196k",
    "formatting": "sharegpt"
  },
  "glaive_toolcall_100k": {
    "hf_hub_url": "hiyouga/glaive-function-calling-v2-sharegpt",
    "formatting": "sharegpt",
    "columns": {
      "messages": "conversations",
      "tools": "tools"
    }
  },
  "cosmopedia": {
    "hf_hub_url": "HuggingFaceTB/cosmopedia",
    "columns": {
      "prompt": "prompt",
      "response": "text"
    }
  },
  "llava_150k_en": {
    "hf_hub_url": "BUAADreamer/llava-en-zh-300k",
    "subset": "en",
    "formatting": "sharegpt",
    "columns": {
      "messages": "messages",
      "images": "images"
    },
    "tags": {
      "role_tag": "role",
      "content_tag": "content",
      "user_tag": "user",
      "assistant_tag": "assistant"
    }
  },
  "llava_150k_zh": {
    "hf_hub_url": "BUAADreamer/llava-en-zh-300k",
    "subset": "zh",
    "formatting": "sharegpt",
    "columns": {
      "messages": "messages",
      "images": "images"
    },
    "tags": {
      "role_tag": "role",
      "content_tag": "content",
      "user_tag": "user",
      "assistant_tag": "assistant"
    }
  },
  "oasst_de": {
    "hf_hub_url": "mayflowergmbh/oasst_de"
  },
  "dolly_15k_de": {
    "hf_hub_url": "mayflowergmbh/dolly-15k_de"
  },
  "alpaca-gpt4_de": {
    "hf_hub_url": "mayflowergmbh/alpaca-gpt4_de"
  },
  "openschnabeltier_de": {
    "hf_hub_url": "mayflowergmbh/openschnabeltier_de"
  },
  "evol_instruct_de": {
    "hf_hub_url": "mayflowergmbh/evol-instruct_de"
  },
  "dolphin_de": {
    "hf_hub_url": "mayflowergmbh/dolphin_de"
  },
  "booksum_de": {
    "hf_hub_url": "mayflowergmbh/booksum_de"
  },
  "airoboros_de": {
    "hf_hub_url": "mayflowergmbh/airoboros-3.0_de"
  },
  "ultrachat_de": {
    "hf_hub_url": "mayflowergmbh/ultra-chat_de"
  },
  "hh_rlhf_en": {
    "script_url": "hh_rlhf_en",
    "columns": {
      "prompt": "instruction",
      "response": "output",
      "history": "history"
    },
    "ranking": true
  },
  "oaast_rm_zh": {
    "file_name": "oaast_rm_zh.json",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    },
    "ranking": true
  },
  "comparison_gpt4_en": {
    "file_name": "comparison_gpt4_data_en.json",
    "ranking": true
  },
  "comparison_gpt4_zh": {
    "file_name": "comparison_gpt4_data_zh.json",
    "ranking": true
  },
  "orca_rlhf": {
    "file_name": "orca_rlhf.json",
    "ranking": true,
    "columns": {
      "prompt": "question",
      "response": "answer",
      "system": "system"
    }
  },
  "nectar_rm": {
    "hf_hub_url": "AstraMindAI/RLAIF-Nectar",
    "ms_hub_url": "AI-ModelScope/RLAIF-Nectar",
    "ranking": true
  },
  "dpo_mix_en": {
    "hf_hub_url": "hiyouga/DPO-En-Zh-20k",
    "subset": "en",
    "ranking": true,
    "columns": {
      "prompt": "prompt",
      "response": "answer",
      "system": "system",
      "history": "history"
    }
  },
  "dpo_mix_zh": {
    "hf_hub_url": "hiyouga/DPO-En-Zh-20k",
    "subset": "zh",
    "ranking": true,
    "columns": {
      "prompt": "prompt",
      "response": "answer",
      "system": "system",
      "history": "history"
    }
  },
  "orca_dpo_de": {
    "hf_hub_url": "mayflowergmbh/intel_orca_dpo_pairs_de",
    "ranking": true
  },
  "wiki_demo": {
    "file_name": "wiki_demo.txt",
    "columns": {
      "prompt": "text"
    }
  },
  "c4_demo": {
    "file_name": "c4_demo.json",
    "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",
    "ms_hub_url": "AI-ModelScope/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": "monology/pile-uncopyrighted",
    "ms_hub_url": "AI-ModelScope/pile",
    "columns": {
      "prompt": "text"
    }
  },
  "skypile": {
    "hf_hub_url": "Skywork/SkyPile-150B",
    "ms_hub_url": "AI-ModelScope/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"
  }
}