{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "medchatzh",
  "name": "MedChatZH",
  "summary": {
    "en": "License: conflict (NOASSERTION); Mdexa hosting: pending. the publisher's own statements contradict each other (permissive license vs restriction)",
    "zh": "许可证声明：冲突（NOASSERTION）；本站处理：待确认，暂只链接原出处。发布方自己的说法互相矛盾（宽松许可与限制并存）。"
  },
  "systems": [
    "traditional-medicine"
  ],
  "domains": [
    "tcm"
  ],
  "content_types": [
    "qa-dialogue"
  ],
  "content_description": {
    "en": "Traditional Chinese medicine book data and medical instruction dialogue data used to train Baichuan-7B for Chinese medical dialogue, stated to understand TCM questions.",
    "zh": "基于中医书籍数据和医疗指令对话数据的中文医疗对话数据，用于训练能够理解中医问题的模型。"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "100K<n<1M",
    "measures": []
  },
  "publisher": "tyang816",
  "year": {
    "value": 2024,
    "raw": "2024"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "NOASSERTION",
    "commercial_use": "conflict",
    "derivatives": "conflict",
    "redistribution": "conflict",
    "rationale": {
      "en": "the publisher's own statements contradict each other (permissive license vs restriction)",
      "zh": "发布方自己的说法互相矛盾（宽松许可与限制并存）"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Statement found in snapshot s04 (readme)",
          "zh": "在快照 s04（readme）中找到的声明"
        },
        "excerpt": "license: apache-2.0",
        "spdx": "Apache-2.0",
        "url": "https://huggingface.co/datasets/tyang816/MedChatZH",
        "verified_on": "2026-11-12",
        "snapshot_id": "s04",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "hf-card-text",
        "location_detail": {
          "en": "Statement found in snapshot s04 (readme)",
          "zh": "在快照 s04（readme）中找到的声明"
        },
        "excerpt": "**本项目模型与数据集及其衍生物仅用于研究目的，不得用于商业，以及其他会对社会带来危害的用途。**",
        "url": "https://huggingface.co/datasets/tyang816/MedChatZH",
        "verified_on": "2026-11-12",
        "snapshot_id": "s04",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "dataset-page",
        "location_detail": {
          "en": "Statement found in snapshot s05 (page)",
          "zh": "在快照 s05（page）中找到的声明"
        },
        "excerpt": "本项目模型与数据集及其衍生物仅用于研究目的，不得用于商业，以及其他会对社会带来危害的用途。",
        "url": "https://huggingface.co/datasets/tyang816/MedChatZH",
        "verified_on": "2026-11-12",
        "snapshot_id": "s05",
        "observed": "page",
        "captured_by": "pipeline"
      }
    ]
  },
  "license_status": "conflict",
  "hosting": "pending",
  "hosting_reason": {
    "en": "License conflict: the publisher's own statements contradict each other (permissive license vs restriction). Link only.",
    "zh": "许可证冲突：发布方自己的说法互相矛盾（宽松许可与限制并存）。只链接原出处。"
  },
  "signoff": null,
  "risk_flags": [],
  "provenance": {
    "source_description": null,
    "upstream": []
  },
  "known_issues": [
    {
      "en": "May produce factually incorrect answers on factual instructions.",
      "zh": "在涉及事实性的指令上可能会产生违背事实的错误回答。"
    },
    {
      "en": "Harmful instructions cannot be well identified, which produces harmful statements.",
      "zh": "对于具备危害性的指令无法很好的鉴别，由此会产生危害性言论。"
    },
    {
      "en": "Model capability in scenarios involving reasoning and code still needs improvement.",
      "zh": "在一些涉及推理、代码等场景下模型的能力仍有待提高。"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/tyang816/MedChatZH"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "references": []
  },
  "verification_level": "verified",
  "last_verified": "2026-11-14",
  "tags": [
    {
      "facet": "task_format",
      "value": "open-qa",
      "basis": "author-stated",
      "excerpt": "- question-answering",
      "snapshot_id": "s04"
    },
    {
      "facet": "intended_use",
      "value": "fine-tuning",
      "basis": "author-stated",
      "excerpt": "基于Baichuan-7B在中医书籍数据和医疗指令对话数据上训练",
      "snapshot_id": "s04"
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "基于Baichuan-7B在中医书籍数据和医疗指令对话数据上训练，使其具备较强的中文医疗对话能力，**能够理解中医问题**。",
      "snapshot_id": "s04"
    },
    {
      "facet": "source_type",
      "value": "classical-text",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "基于Baichuan-7B在中医书籍数据和医疗指令对话数据上训练",
      "snapshot_id": "s04"
    }
  ],
  "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": "tyang816/MedChatZH",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/tyang816/MedChatZH",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/tyang816/MedChatZH/resolve/c3ec8b78a39f103e8b608a44d092baea00485769/.gitattributes",
        "size_bytes": 2422,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "MedChatZH_mix_2M.json",
        "url": "https://huggingface.co/datasets/tyang816/MedChatZH/resolve/c3ec8b78a39f103e8b608a44d092baea00485769/MedChatZH_mix_2M.json",
        "size_bytes": 3005763853,
        "checksum": {
          "algorithm": "sha256",
          "value": "57ca99e4cd27c17ded246d3f1cf013f83d5124bc9fa8e66165aa9bb54a56a7c0"
        },
        "format": "json"
      },
      {
        "name": "MedChatZH_train.json",
        "url": "https://huggingface.co/datasets/tyang816/MedChatZH/resolve/c3ec8b78a39f103e8b608a44d092baea00485769/MedChatZH_train.json",
        "size_bytes": 866839707,
        "checksum": {
          "algorithm": "sha256",
          "value": "ba230c4124b2d9c4230ae15613afee66fd4ec12288e70b660275c23e20918f20"
        },
        "format": "json"
      },
      {
        "name": "MedChatZH_valid.json",
        "url": "https://huggingface.co/datasets/tyang816/MedChatZH/resolve/c3ec8b78a39f103e8b608a44d092baea00485769/MedChatZH_valid.json",
        "size_bytes": 562004,
        "checksum": null,
        "format": "json"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/tyang816/MedChatZH/resolve/c3ec8b78a39f103e8b608a44d092baea00485769/README.md",
        "size_bytes": 5799,
        "checksum": null,
        "format": "md"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download tyang816/MedChatZH --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": "c3ec8b78a39f103e8b608a44d092baea00485769",
      "last_modified": "2026-09-02T15:11:32.000Z"
    },
    "license_note": {
      "license_status": "conflict",
      "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：ShenNong_TCM_Dataset（ChatMed_TCM_Dataset） (https://mdexa.com/zh/datasets/shennong-tcm-dataset/)；LingLanMedBench Traditional Chinese Medicine Benchmark Dataset (https://mdexa.com/zh/datasets/linglan/)；HuatuoGPT2-SFT-GPT4-140K (https://mdexa.com/zh/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=%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": "ShenNong_TCM_Dataset（ChatMed_TCM_Dataset）",
        "url": "https://mdexa.com/zh/datasets/shennong-tcm-dataset/",
        "json": "https://mdexa.com/zh/datasets/shennong-tcm-dataset.json"
      },
      {
        "name": "LingLanMedBench Traditional Chinese Medicine Benchmark Dataset",
        "url": "https://mdexa.com/zh/datasets/linglan/",
        "json": "https://mdexa.com/zh/datasets/linglan.json"
      },
      {
        "name": "HuatuoGPT2-SFT-GPT4-140K",
        "url": "https://mdexa.com/zh/datasets/huatuogpt2-sft-gpt4-140k/",
        "json": "https://mdexa.com/zh/datasets/huatuogpt2-sft-gpt4-140k.json"
      }
    ]
  }
}