{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "huatuogpt-sft-data-v1",
  "name": "HuatuoGPT-sft-data-v1",
  "summary": {
    "zh": "许可证声明：宽松（Apache-2.0）；本站处理：只链接原出处。许可证宽松，但有来源风险：来源未说明，无法判断来源版权；只链接原出处。",
    "en": "License: permissive (Apache-2.0); Mdexa hosting: link-only. License is permissive, but source risk: source not stated, so source copyright cannot be judged; link only."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "qa-dialogue"
  ],
  "content_description": {
    "en": "Medical consultation dialogue fine-tuning data",
    "zh": "医疗咨询对话微调数据"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "226,042行，333 MB",
    "measures": [
      {
        "value": 226042,
        "unit": "rows",
        "qualifier": "exact"
      },
      {
        "value": 333,
        "unit": "MB",
        "qualifier": "exact"
      }
    ]
  },
  "publisher": "FreedomIntelligence",
  "year": {
    "value": null,
    "raw": "未标明"
  },
  "expert_review": {
    "en": "Not stated",
    "zh": "未说明"
  },
  "license": {
    "legacy_status": "distributable",
    "spdx": "Apache-2.0",
    "commercial_use": "yes",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "Dataset card states Apache-2.0",
      "zh": "数据集卡为 Apache-2.0"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Hugging Face dataset card metadata: apache-2.0",
          "zh": "Hugging Face 数据集卡元数据：apache-2.0"
        },
        "excerpt": "license: apache-2.0",
        "spdx": "Apache-2.0",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT-sft-data-v1",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "zh": "许可证宽松，但有来源风险：来源未说明，无法判断来源版权；只链接原出处。",
    "en": "License is permissive, but source risk: source not stated, so source copyright cannot be judged; link only."
  },
  "signoff": null,
  "risk_flags": [
    "unknown-provenance"
  ],
  "provenance": {
    "source_description": {
      "en": "The card does not state the source",
      "zh": "卡片未写来源"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "README is empty; no source or construction description, so source copyright cannot be judged",
      "zh": "README 为空，无来源、构造方式说明，来源版权无法判断"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT-sft-data-v1"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": []
  },
  "verification_level": "verified",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "task_format",
      "value": "multi-turn-dialogue",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "Card: medical consultation dialogues.",
        "zh": "卡片内容描述为医疗咨询对话"
      }
    },
    {
      "facet": "data_format",
      "value": "json",
      "basis": "author-stated",
      "excerpt": "Formats: json",
      "snapshot_id": "s02"
    },
    {
      "facet": "official_split",
      "value": "no-split",
      "basis": "inferred",
      "inferred_from": "snapshot-structure",
      "note": {
        "en": "HF shows one split.",
        "zh": "HF 只有一个 split"
      }
    },
    {
      "facet": "intended_use",
      "value": "fine-tuning",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "SFT data.",
        "zh": "SFT 数据"
      }
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "zh": "综合医疗咨询对话，未限定专科",
        "en": "综合医疗咨询对话; not limited to a specialty"
      }
    }
  ],
  "changelog": [
    {
      "date": "2026-11-12",
      "change": {
        "en": "Card converted from an earlier manual catalog; no new facts added; reclassified under taxonomy v2.",
        "zh": "由早期人工整理的目录转换生成，未新增事实；按分类体系 v2 重新归类。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "License status split into license_status (what the license says) and hosting (what Mdexa does); the earlier conclusion is kept for traceability.",
        "zh": "把许可证状态拆成 license_status（许可证怎么写）与 hosting（本站怎么处理）；原结论保留以便追溯。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "Added verbatim license excerpts and snapshot ids from captured page snapshots; no conclusion changed.",
        "zh": "补入来自已抓取页面快照的许可证逐字摘录与快照编号；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 5 (1 stated by the authors with excerpts, 4 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 5 个（作者声明 1 个，附逐字摘录；据内容推断 4 个）；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Removed the stored size-tier tag; the tier is now computed from the size field when pages are built.",
        "zh": "移除存储的规模档位标签；档位改为生成页面时由 size 字段计算。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added specialty tags: multi-specialty(inferred).",
        "zh": "新增专科标签：multi-specialty(inferred)。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "huggingface",
    "repo_id": "FreedomIntelligence/HuatuoGPT-sft-data-v1",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/FreedomIntelligence/HuatuoGPT-sft-data-v1",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT-sft-data-v1/resolve/2f6c022606d7cbfa23651a231f0e5c9f3b603ad8/.gitattributes",
        "size_bytes": 2392,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "HuatuoGPT_sft_data_v1.jsonl",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT-sft-data-v1/resolve/2f6c022606d7cbfa23651a231f0e5c9f3b603ad8/HuatuoGPT_sft_data_v1.jsonl",
        "size_bytes": 333326040,
        "checksum": {
          "algorithm": "sha256",
          "value": "bfbaca0810171e8afb4b0c62163ccd0804aacb30a575c2590e6e0fd0679123c9"
        },
        "format": "jsonl"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT-sft-data-v1/resolve/2f6c022606d7cbfa23651a231f0e5c9f3b603ad8/README.md",
        "size_bytes": 28,
        "checksum": null,
        "format": "md"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download FreedomIntelligence/HuatuoGPT-sft-data-v1 --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": "2f6c022606d7cbfa23651a231f0e5c9f3b603ad8",
      "last_modified": "2023-06-01T11:05:15.000Z"
    },
    "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": "在本库继续查找。本条目是 109 条已处理并核实的记录之一（数据集、数据资源与开源模型）。查找其他条目：调用 `https://mcp.mdexa.com/v1/datasets?q=<关键词>`，或连接 MCP 服务 `https://mcp.mdexa.com/mcp`；每分钟 20 次以内无需密钥。每行返回不到 1 KB；空结果即\"数据库未收录\"。核对一份清单：一次批量核对（免费账号）即返回报告。说明：/agents.md。相似条目：Huatuo-Llama-Med-Chinese 知识库问答与文献数据 (https://mdexa.com/zh/datasets/huatuo-llama-med-chinese-data/)；BianQueCorpus（扁鹊健康大数据） (https://mdexa.com/zh/datasets/bianque-corpus/)；CMtMedQA (https://mdexa.com/zh/datasets/cmtmedqa/)。",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=%E7%BB%93%E5%90%88%E4%BA%B2%E5%92%8C%E5%8A%9B"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/zh/agents.md",
    "faq": "https://mdexa.com/zh/developers/faq/",
    "similar": [
      {
        "name": "Huatuo-Llama-Med-Chinese 知识库问答与文献数据",
        "url": "https://mdexa.com/zh/datasets/huatuo-llama-med-chinese-data/",
        "json": "https://mdexa.com/zh/datasets/huatuo-llama-med-chinese-data.json"
      },
      {
        "name": "BianQueCorpus（扁鹊健康大数据）",
        "url": "https://mdexa.com/zh/datasets/bianque-corpus/",
        "json": "https://mdexa.com/zh/datasets/bianque-corpus.json"
      },
      {
        "name": "CMtMedQA",
        "url": "https://mdexa.com/zh/datasets/cmtmedqa/",
        "json": "https://mdexa.com/zh/datasets/cmtmedqa.json"
      }
    ]
  }
}