{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "huatuogpt2-pretraining-instruction",
  "name": "HuatuoGPT2-Pretraining-Instruction",
  "summary": {
    "en": "License: permissive (Apache-2.0); Mdexa hosting: link-only. first-hand data-scope statement(s) allow commercial use and redistribution Risk flag(s): model-generated.",
    "zh": "许可证声明：宽松（Apache-2.0）；本站处理：只链接原出处。针对数据的声明允许商用和再分发。来源风险标记：model-generated。"
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine",
    "biomedical-literature"
  ],
  "content_types": [
    "qa-dialogue",
    "literature",
    "other"
  ],
  "content_description": {
    "en": "Pre-training instructions for HuatuoGPT-II, developed with a 5.2 million medical corpus using ChatGPT, to incorporate extensive medical knowledge and enable one-stage medical adaptation.",
    "zh": "HuatuoGPT-II 的预训练指令数据，使用 ChatGPT 基于 520 万医学语料构建，用于融入广泛医学知识并实现一阶段医学适配。"
  },
  "languages": [
    "zh",
    "en"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "5,286,308",
    "measures": []
  },
  "publisher": "FreedomIntelligence",
  "year": {
    "value": null,
    "raw": null
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "Apache-2.0",
    "commercial_use": "yes",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "first-hand data-scope statement(s) allow commercial use and redistribution",
      "zh": "针对数据的声明允许商用和再分发"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "license: apache-2.0",
        "spdx": "Apache-2.0",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      }
    ],
    "license_conditions": [
      "notice-required"
    ],
    "notes": {
      "en": "risk flag(s) model-generated: never eligible or hosted",
      "zh": "risk flag(s) model-generated: never eligible or hosted"
    }
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "en": "License permissive: first-hand data-scope statement(s) allow commercial use and redistribution. Risk flag(s): model-generated. Link only.",
    "zh": "许可证宽松：针对数据的声明允许商用和再分发。来源风险标记：model-generated。只链接原出处。"
  },
  "signoff": null,
  "risk_flags": [
    "model-generated"
  ],
  "provenance": {
    "source_description": null,
    "upstream": []
  },
  "known_issues": [],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "references": [
      "arXiv:2311.09774",
      "arXiv:2305.15075"
    ]
  },
  "verification_level": "verified",
  "last_verified": "2026-11-14",
  "tags": [
    {
      "facet": "task_format",
      "value": "open-qa",
      "basis": "author-stated",
      "excerpt": "  - question-answering",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "multi-turn-dialogue",
      "basis": "inferred",
      "inferred_from": "snapshot-structure",
      "excerpt": "    - name: conversations\n      list:\n        - name: from",
      "snapshot_id": "s01"
    },
    {
      "facet": "intended_use",
      "value": "pretraining",
      "basis": "author-stated",
      "excerpt": "Here are the pre-training instructions for HuatuoGPT-II",
      "snapshot_id": "s01"
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "This dataset is used to  incorporate extensive medical knowledge and enable a one-stage medical adaptation.",
      "snapshot_id": "s01"
    },
    {
      "facet": "source_type",
      "value": "literature",
      "basis": "inferred",
      "inferred_from": "snapshot-structure",
      "excerpt": "  - config_name: Meidcal_Literature_en",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "json",
      "basis": "inferred",
      "inferred_from": "snapshot-structure",
      "excerpt": "  - config_name: Meidcal_Encyclopedia_en\n    data_files: data/HuatuoGPT2_Pretrain_Meidcal_Encyclopedia_en.json",
      "snapshot_id": "s01"
    }
  ],
  "changelog": [
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added via the automated pipeline and passed all checks (gates, verbatim quotes, rule engine, two independent extractions).",
        "zh": "经自动流水线收录并通过全部校验（门禁、逐字引用、判定引擎、两轮独立抽取）。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "huggingface",
    "repo_id": "FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction/resolve/f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be/.gitattributes",
        "size_bytes": 2350,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction/resolve/f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be/README.md",
        "size_bytes": 2915,
        "checksum": null,
        "format": "md"
      },
      {
        "name": "data/HuatuoGPT2_Pretrain_Meidcal_Books_cn.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction/resolve/f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be/data/HuatuoGPT2_Pretrain_Meidcal_Books_cn.json",
        "size_bytes": 2580101850,
        "checksum": {
          "algorithm": "sha256",
          "value": "fb303b1c8e25ec59b76c37c73bb9a4774cd339c9fd431157d692eecbce5ab2a5"
        },
        "format": "json"
      },
      {
        "name": "data/HuatuoGPT2_Pretrain_Meidcal_Books_en.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction/resolve/f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be/data/HuatuoGPT2_Pretrain_Meidcal_Books_en.json",
        "size_bytes": 1130971934,
        "checksum": {
          "algorithm": "sha256",
          "value": "ba2cfee2ab167ea529193699ef84f214bfb6a1da9ba09843bbbd97e614ac6c8f"
        },
        "format": "json"
      },
      {
        "name": "data/HuatuoGPT2_Pretrain_Meidcal_Encyclopedia_cn.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction/resolve/f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be/data/HuatuoGPT2_Pretrain_Meidcal_Encyclopedia_cn.json",
        "size_bytes": 563408968,
        "checksum": {
          "algorithm": "sha256",
          "value": "b6bdf41bf3e3c09dd784255e75272b635b00eb1bc104203c250df01b51773c02"
        },
        "format": "json"
      },
      {
        "name": "data/HuatuoGPT2_Pretrain_Meidcal_Encyclopedia_en.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction/resolve/f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be/data/HuatuoGPT2_Pretrain_Meidcal_Encyclopedia_en.json",
        "size_bytes": 240476113,
        "checksum": {
          "algorithm": "sha256",
          "value": "cfd68e981216a6240b2884793b13138403d5aa6645b633147f48565c91445bef"
        },
        "format": "json"
      },
      {
        "name": "data/HuatuoGPT2_Pretrain_Meidcal_Literature_cn.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction/resolve/f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be/data/HuatuoGPT2_Pretrain_Meidcal_Literature_cn.json",
        "size_bytes": 256636916,
        "checksum": {
          "algorithm": "sha256",
          "value": "2fb3cef3617960ce74a83cd338a688c592a29751cb4566a646f118cdc50544db"
        },
        "format": "json"
      },
      {
        "name": "data/HuatuoGPT2_Pretrain_Meidcal_Literature_en.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction/resolve/f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be/data/HuatuoGPT2_Pretrain_Meidcal_Literature_en.json",
        "size_bytes": 1222009205,
        "checksum": {
          "algorithm": "sha256",
          "value": "f011f973f49ed66c1e5e2e22ea9029488577ed09804ddbe58e24a403ee7dea05"
        },
        "format": "json"
      },
      {
        "name": "data/HuatuoGPT2_Pretrain_Meidcal_Web_Corpus_cn.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction/resolve/f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be/data/HuatuoGPT2_Pretrain_Meidcal_Web_Corpus_cn.json",
        "size_bytes": 1172049612,
        "checksum": {
          "algorithm": "sha256",
          "value": "da80675b97a9e5bde890bb92d649b76d1400fedeabf763e5d5c49cb209f75fb2"
        },
        "format": "json"
      },
      {
        "name": "data/HuatuoGPT2_Pretrain_Meidcal_Web_Corpus_en.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction/resolve/f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be/data/HuatuoGPT2_Pretrain_Meidcal_Web_Corpus_en.json",
        "size_bytes": 651906570,
        "checksum": {
          "algorithm": "sha256",
          "value": "6842e627e51c15c8f73317b6cb0a4409abfb3458c10ab07dfdd33e8b556812f2"
        },
        "format": "json"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction --repo-type dataset",
        "evidence": {
          "excerpt": "You can use the hf download command from the terminal to directly download files from the Hub.",
          "doc": "hf-download",
          "url": "https://huggingface.co/docs/huggingface_hub/guides/download",
          "fetched_on": "2026-11-14"
        }
      }
    ],
    "registration": null,
    "version": {
      "commit": "f5da14b8a742233fc8f9627e5a8b5e9f4efeb8be",
      "last_modified": "2024-06-25T08:04:07.000Z"
    },
    "license_note": {
      "license_status": "permissive",
      "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely."
    },
    "gaps": []
  },
  "_links": {
    "text": "Continue in this database. This record is one of 109 processed and verified records (datasets, data resources and open models). To find others, call `https://mcp.mdexa.com/v1/datasets?q=<words>` or connect the MCP server at `https://mcp.mdexa.com/mcp`; no key is needed for 20 calls per minute. Rows are under 1 KB; an empty result means \"not listed\". For a list of items, one batch check (free account) returns a report. Guide: /agents.md. Similar records: Huatuo-Llama-Med-Chinese 知识库问答与文献数据 (https://mdexa.com/datasets/huatuo-llama-med-chinese-data/); Huatuo-26M (https://mdexa.com/datasets/huatuo-26m/); HuatuoGPT2-SFT-GPT4-140K (https://mdexa.com/datasets/huatuogpt2-sft-gpt4-140k/).",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=binding%20affinity"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/agents.md",
    "faq": "https://mdexa.com/developers/faq/",
    "similar": [
      {
        "name": "Huatuo-Llama-Med-Chinese 知识库问答与文献数据",
        "url": "https://mdexa.com/datasets/huatuo-llama-med-chinese-data/",
        "json": "https://mdexa.com/datasets/huatuo-llama-med-chinese-data.json"
      },
      {
        "name": "Huatuo-26M",
        "url": "https://mdexa.com/datasets/huatuo-26m/",
        "json": "https://mdexa.com/datasets/huatuo-26m.json"
      },
      {
        "name": "HuatuoGPT2-SFT-GPT4-140K",
        "url": "https://mdexa.com/datasets/huatuogpt2-sft-gpt4-140k/",
        "json": "https://mdexa.com/datasets/huatuogpt2-sft-gpt4-140k.json"
      }
    ]
  }
}