{"adoption": {"forks": 295, "observed_at": "2026-08-28T04:05:32.158147+00:00", "stars": 1756}, "canonical_url": "https://ross.abutalabs.com/products/chinese-medical-dialogue-data", "card": {"archived": false, "artifact_type": "dataset", "description": "Chinese medical dialogue data 中文医疗对话数据集", "domain": ["healthcare", "large-language-models", "machine-learning"], "enriched": true, "function": ["machine-learning", "llm-training", "nlp"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["Toyhom/Chinese-medical-dialogue-data"], "name": "Toyhom/Chinese-medical-dialogue-data", "platform": ["python"], "pushed_at": "2023-08-18T05:34:28+00:00", "repo": "Toyhom/Chinese-medical-dialogue-data", "stars": 1756, "tags": ["chinese-nlp", "medical-qa", "dialogue-dataset", "fine-tuning-data", "chatglm", "question-answering", "csv-dataset", "medical-chatbot", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["find a Chinese medical dialogue dataset for NLP research", "fine-tune ChatGLM-6B on medical QA data", "train a Chinese medical chatbot", "get a doctor-patient question-answer corpus in Chinese", "instruction-tuning data for a medical LLM assistant", "benchmark LoRA or P-Tuning on domain-specific Chinese text"], "what_it_is": "A Chinese medical dialogue dataset containing 792,099 patient-doctor question-answer pairs organized into six departments: internal medicine, surgery, pediatrics, oncology, obstetrics/gynecology, and andrology. The data ships as CSV files (department, title, question, answer) and includes instruction-tuning format examples prepared for fine-tuning models such as ChatGLM-6B.", "when_to_avoid": ["You need English or multilingual medical dialogue data", "You require clinically verified or expert-reviewed medical answers, since content originates from online consultation replies", "You need an application or API for medical QA rather than raw training data", "Your project needs actively maintained or updated data"], "when_to_choose": ["You need large-scale Chinese medical QA pairs for LLM fine-tuning or evaluation", "You want ready-made instruction/input/output JSON for ChatGLM-style training", "You want a permissively licensed (MIT) dataset covering six medical departments", "You are reproducing or comparing LoRA / P-Tuning V2 results on medical dialogue"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/chinese-medical-dialogue-data", "repo": "Toyhom/Chinese-medical-dialogue-data", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:27:50.978614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5030c5671d295a7ea87c828dfd24062ca094ed8b7091d7e177cb9017769d1dd2", "fetched_at": "2026-08-28T04:05:32.158147+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:27:50.978614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5030c5671d295a7ea87c828dfd24062ca094ed8b7091d7e177cb9017769d1dd2", "fetched_at": "2026-08-28T04:05:32.158147+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:27:50.978614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5030c5671d295a7ea87c828dfd24062ca094ed8b7091d7e177cb9017769d1dd2", "fetched_at": "2026-08-28T04:05:32.158147+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:27:50.978614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5030c5671d295a7ea87c828dfd24062ca094ed8b7091d7e177cb9017769d1dd2", "fetched_at": "2026-08-28T04:05:32.158147+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:27:50.978614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5030c5671d295a7ea87c828dfd24062ca094ed8b7091d7e177cb9017769d1dd2", "fetched_at": "2026-08-28T04:05:32.158147+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:27:50.978614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5030c5671d295a7ea87c828dfd24062ca094ed8b7091d7e177cb9017769d1dd2", "fetched_at": "2026-08-28T04:05:32.158147+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:32.158147+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:27:50.978614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5030c5671d295a7ea87c828dfd24062ca094ed8b7091d7e177cb9017769d1dd2", "fetched_at": "2026-08-28T04:05:32.158147+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:27:50.978614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5030c5671d295a7ea87c828dfd24062ca094ed8b7091d7e177cb9017769d1dd2", "fetched_at": "2026-08-28T04:05:32.158147+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:27:50.978614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5030c5671d295a7ea87c828dfd24062ca094ed8b7091d7e177cb9017769d1dd2", "fetched_at": "2026-08-28T04:05:32.158147+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:27:50.978614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5030c5671d295a7ea87c828dfd24062ca094ed8b7091d7e177cb9017769d1dd2", "fetched_at": "2026-08-28T04:05:32.158147+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2459, "days_push": 1111, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}