LLaMA-Factory-Mirror/data/dataset_info.json

{
  "alpaca_en": {
    "file_name": "alpaca_data_en_52k.json",
    "file_sha1": "607f94a7f581341e59685aef32f531095232cf23",
    "stage": "sft"
  },
  "alpaca_zh": {
    "file_name": "alpaca_data_zh_51k.json",
    "file_sha1": "e655af3db557a4197f7b0cf92e1986b08fae6311",
    "stage": "sft"
  },
  "alpaca_gpt4_en": {
    "file_name": "alpaca_gpt4_data_en.json",
    "file_sha1": "647f4ad447bd993e4b6b6223d1be15208bab694a",
    "stage": "sft"
  },
  "alpaca_gpt4_zh": {
    "file_name": "alpaca_gpt4_data_zh.json",
    "file_sha1": "3eaa3bda364ccdd59925d7448a698256c31ef845",
    "stage": "sft"
  },
  "self_cognition": {
    "file_name": "self_cognition.json",
    "file_sha1": "6287a730ada924fc5d9eadc6d8f865e01b7a6f67",
    "stage": "sft"
  },
  "oaast_sft": {
    "file_name": "oaast_sft.json",
    "file_sha1": "7baf5d43e67a91f9bbdf4e400dbe033b87e9757e",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    },
    "stage": "sft"
  },
  "oaast_sft_zh": {
    "file_name": "oaast_sft_zh.json",
    "file_sha1": "a6a91f18f80f37b10ded9cf633fb50c033bf7b9f",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    },
    "stage": "sft"
  },
  "sharegpt_zh": {
    "file_name": "sharegpt_zh_27k.json",
    "file_sha1": "baf766bcf3d61f1b783728c14ce695af57a86e6e",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    },
    "stage": "sft"
  },
  "lima": {
    "file_name": "lima.json",
    "file_sha1": "9db59f6b7007dc4b17529fc63379b9cd61640f37",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    },
    "stage": "sft"
  },
  "example": {
    "script_url": "example_dataset",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    },
    "stage": "sft"
  },
  "guanaco": {
    "hf_hub_url": "JosephusCheung/GuanacoDataset",
    "stage": "sft"
  },
  "belle_0.5m": {
    "hf_hub_url": "BelleGroup/train_0.5M_CN",
    "stage": "sft"
  },
  "belle_1m": {
    "hf_hub_url": "BelleGroup/train_1M_CN",
    "stage": "sft"
  },
  "belle_2m": {
    "hf_hub_url": "BelleGroup/train_2M_CN",
    "stage": "sft"
  },
  "belle_dialog": {
    "hf_hub_url": "BelleGroup/generated_chat_0.4M",
    "stage": "sft"
  },
  "belle_math": {
    "hf_hub_url": "BelleGroup/school_math_0.25M",
    "stage": "sft"
  },
  "belle_multiturn": {
    "script_url": "belle_multiturn",
    "columns": {
      "prompt": "instruction",
      "query": "",
      "response": "output",
      "history": "history"
    },
    "stage": "sft"
  },
  "firefly": {
    "hf_hub_url": "YeungNLP/firefly-train-1.1M",
    "columns": {
      "prompt": "input",
      "query": "",
      "response": "target",
      "history": ""
    },
    "stage": "sft"
  },
  "codealpaca": {
    "hf_hub_url": "sahil2801/CodeAlpaca-20k",
    "stage": "sft"
  },
  "alpaca_cot": {
    "hf_hub_url": "QingyiSi/Alpaca-CoT",
    "stage": "sft"
  },
  "webqa": {
    "hf_hub_url": "suolyer/webqa",
    "columns": {
      "prompt": "input",
      "query": "",
      "response": "output",
      "history": ""
    },
    "stage": "sft"
  },
  "ultra_chat": {
    "script_url": "ultra_chat",
    "columns": {
      "prompt": "instruction",
      "query": "",
      "response": "output",
      "history": "history"
    },
    "stage": "sft"
  },
  "novel_tokens512_50k": {
    "hf_hub_url": "zxbsmk/webnovel_cn",
    "stage": "sft"
  },
  "ad_gen": {
    "hf_hub_url": "HasturOfficial/adgen",
    "columns": {
      "prompt": "content",
      "query": "",
      "response": "summary",
      "history": ""
    },
    "stage": "sft"
  },
  "comparison_gpt4_en": {
    "file_name": "comparison_gpt4_data_en.json",
    "file_sha1": "96fa18313544e22444fe20eead7754b17da452ae",
    "stage": "rm"
  },
  "comparison_gpt4_zh": {
    "file_name": "comparison_gpt4_data_zh.json",
    "file_sha1": "515b18ed497199131ddcc1af950345c11dc5c7fd",
    "stage": "rm"
  },
  "hh_rlhf_en": {
    "script_url": "hh_rlhf_en",
    "columns": {
      "prompt": "instruction",
      "query": "",
      "response": "output",
      "history": "history"
    },
    "stage": "rm"
  },
  "oaast_rm": {
    "file_name": "oaast_rm.json",
    "file_sha1": "622d420e9b70003b210618253bd3d9d2891d86cb",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    },
    "stage": "rm"
  },
  "oaast_rm_zh": {
    "file_name": "oaast_rm_zh.json",
    "file_sha1": "1065af1f3784dd61be5e79713a35f427b713a232",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    },
    "stage": "rm"
  },
  "wiki_demo": {
    "file_name": "wiki_demo.txt",
    "file_sha1": "b2288edb05b233e5b35250fd4b308a5fa21fa66d",
    "columns": {
      "prompt": "text",
      "query": "",
      "response": "",
      "history": ""
    },
    "stage": "pt"
  },
  "refinedweb": {
    "hf_hub_url": "tiiuae/falcon-refinedweb",
    "columns": {
      "prompt": "content",
      "query": "",
      "response": "",
      "history": ""
    },
    "stage": "pt"
  },
  "starcoder": {
    "hf_hub_url": "bigcode/starcoderdata",
    "columns": {
      "prompt": "content",
      "query": "",
      "response": "",
      "history": ""
    },
    "stage": "pt"
  },
  "wikipedia_en": {
    "hf_hub_url": "olm/olm-wikipedia-20221220",
    "columns": {
      "prompt": "text",
      "query": "",
      "response": "",
      "history": ""
    },
    "stage": "pt"
  },
  "wikipedia_zh": {
    "hf_hub_url": "pleisto/wikipedia-cn-20230720-filtered",
    "columns": {
      "prompt": "completion",
      "query": "",
      "response": "",
      "history": ""
    },
    "stage": "pt"
  }
}