# SCIR-HI/Med-ChatGLM

Repo for Chinese Medical ChatGLM 基于中文医学知识的ChatGLM指令微调

Repository: https://github.com/SCIR-HI/Med-ChatGLM
Canonical: https://ross.abutalabs.com/products/med-chatglm
Language: Python
License: Apache-2.0
License Family: permissive
Topics: chinese, medical, medqa, nlp
Last push: 2023-05-19T09:17:15+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 89
- inputs: {"age_days": 1251, "days_push": 1202, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1037, forks 161 (observed 2026-08-28T04:03:19.413662+00:00)

## What it is
An open-source project providing a Chinese medical instruction-tuned version of ChatGLM-6B, built from a medical knowledge graph and GPT-3.5-generated instruction data. It includes training scripts, dataset construction references, and downloadable fine-tuned model weights.

## Use cases
- fine-tune ChatGLM on Chinese medical data
- build a Chinese medical QA chatbot
- generate instruction datasets from a medical knowledge graph
- improve LLM answers for medical questions in Chinese
- run inference with a medically tuned ChatGLM model

## When to choose
- you need a Chinese-language medical question-answering model based on ChatGLM-6B
- you want reference code and data formats for instruction-tuning ChatGLM on domain knowledge
- you have A100-class GPUs (32GB+ VRAM) for fine-tuning

## When to avoid
- you need a production-grade, clinically validated medical assistant
- you work primarily in English or other non-Chinese languages
- you cannot access large model weights or lack high-VRAM GPUs
- you want actively maintained fine-tuning code (the README recommends the official ChatGLM ptuning pipeline instead)

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-training, machine-learning, rag, chatbot
- domain: large-language-models, healthcare, artificial-intelligence
- platform: python
- tags: chatglm, medical-qa, chinese, instruction-tuning, fine-tuning, llm, natural-language-processing, gpu, linux

## Member repositories
- SCIR-HI/Med-ChatGLM (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:19.413662+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:04:21.188924+00:00, confidence not recorded.
  - readme: https://github.com/SCIR-HI/Med-ChatGLM (fetched 2026-08-28T04:03:19.413662+00:00, sha ace966d78ef5)
- Data as of 2026-08-30T08:39:29.467469+00:00.