data/dataset_info.json

{
  "mydata": {
    "file_name": "output.json",
    "file_sha1": "123456789abc"
  },
  "example": {
    "script_url": "example_dataset",
    "columns": {
      "prompt": "instruction",
      "query": "input",
      "response": "output",
      "history": "history"
    }
  },
  "guanaco": {
    "hf_hub_url": "JosephusCheung/GuanacoDataset"
  },
  "belle_0.5m": {
    "hf_hub_url": "BelleGroup/train_0.5M_CN"
  },
  "belle_1m": {
    "hf_hub_url": "BelleGroup/train_1M_CN"
  },
  "belle_2m": {
    "hf_hub_url": "BelleGroup/train_2M_CN"
  },
  "belle_dialog": {
    "hf_hub_url": "BelleGroup/generated_chat_0.4M"
  },
  "belle_math": {
    "hf_hub_url": "BelleGroup/school_math_0.25M"
  },
  "belle_multiturn": {
    "script_url": "belle_multiturn",
    "columns": {
      "prompt": "instruction",
      "query": "",
      "response": "output",
      "history": "history"
    }
  },
  "codealpaca": {
    "hf_hub_url": "sahil2801/CodeAlpaca-20k"
  },
  "alpaca_cot": {
    "hf_hub_url": "QingyiSi/Alpaca-CoT"
  },
  "firefly": {
    "hf_hub_url": "YeungNLP/firefly-train-1.1M",
    "columns": {
      "prompt": "input",
      "query": "",
      "response": "target",
      "history": ""
    }
  },
  "mathinstruct": {
    "hf_hub_url": "TIGER-Lab/MathInstruct",
    "columns": {
      "prompt": "instruction",
      "query": "",
      "response": "output",
      "history": ""
    }
  },
  "webqa": {
    "hf_hub_url": "suolyer/webqa",
    "columns": {
      "prompt": "input",
      "query": "",
      "response": "output",
      "history": ""
    }
  },
  "ultra_chat": {
    "script_url": "ultra_chat",
    "columns": {
      "prompt": "instruction",
      "query": "",
      "response": "output",
      "history": "history"
    }
  },
  "novel_tokens512_50k": {
    "hf_hub_url": "zxbsmk/webnovel_cn"
  },
  "adgen": {
    "hf_hub_url": "HasturOfficial/adgen",
    "columns": {
      "prompt": "content",
      "query": "",
      "response": "summary",
      "history": ""
    }
  },
  "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
  },
  "hh_rlhf_en": {
    "script_url": "hh_rlhf_en",
    "columns": {
      "prompt": "instruction",
      "query": "",
      "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
  },
  "wiki_demo": {
    "file_name": "wiki_demo.txt",
    "file_sha1": "b2288edb05b233e5b35250fd4b308a5fa21fa66d",
    "columns": {
      "prompt": "text",
      "query": "",
      "response": "",
      "history": ""
    }
  },
  "refinedweb": {
    "hf_hub_url": "tiiuae/falcon-refinedweb",
    "columns": {
      "prompt": "content",
      "query": "",
      "response": "",
      "history": ""
    }
  },
  "wikipedia_en": {
    "hf_hub_url": "olm/olm-wikipedia-20221220",
    "columns": {
      "prompt": "text",
      "query": "",
      "response": "",
      "history": ""
    }
  },
  "wikipedia_zh": {
    "hf_hub_url": "pleisto/wikipedia-cn-20230720-filtered",
    "columns": {
      "prompt": "completion",
      "query": "",
      "response": "",
      "history": ""
    }
  },
  "the_stack": {
    "hf_hub_url": "bigcode/the-stack",
    "columns": {
      "prompt": "content",
      "query": "",
      "response": "",
      "history": ""
    }
  },
  "starcoder": {
    "hf_hub_url": "bigcode/starcoderdata",
    "columns": {
      "prompt": "content",
      "query": "",
      "response": "",
      "history": ""
    }
  }
}