# MediaBrain-SJTU/MING

明医 (MING)：中文医疗问诊大模型

Repository: https://github.com/MediaBrain-SJTU/MING
Canonical: https://ross.abutalabs.com/products/ming
Language: Python
License: Apache-2.0
License Family: permissive
Topics: medical, pytorch, transformers, llm, consultation, huggingface
Last push: 2025-05-23T09:29:13+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 23, release rhythm 35, longevity 88
- inputs: {"age_days": 1244, "days_push": 467, "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 1173, forks 145 (observed 2026-08-28T04:03:51.783469+00:00)

## What it is
MING (明医) is a Chinese medical consultation large language model fine-tuned on medical instruction data, with variants built on bloomz-7b and Qwen1.5 bases. The repository provides model weights, training code, and demos for medical QA and multi-turn intelligent consultation.

## Use cases
- build a chinese medical chatbot
- fine-tune an llm on medical instruction data
- answer medical questions with a domain-specific model
- run multi-turn patient consultation dialogues
- deploy a healthcare assistant model locally
- research medical llm alignment and evaluation

## When to choose
- you need a chinese-language medical consultation model
- you want open weights under a permissive Apache-2.0 license
- you are researching medical llm fine-tuning or multi-task medical learning

## When to avoid
- you need clinical-grade diagnostic accuracy or certified medical advice
- you need an english-language medical model
- you lack gpu resources for running 7B-scale models

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, llm-training, chatbot, machine-learning
- domain: healthcare, large-language-models, artificial-intelligence
- platform: python
- tags: medical-llm, chinese-language, instruction-tuning, huggingface, medical-consultation, natural-language-processing, gpu, linux

## Member repositories
- MediaBrain-SJTU/MING (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:51.783469+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 2026-08-30T06:28:20.892757+00:00, confidence not recorded.
  - readme: https://github.com/MediaBrain-SJTU/MING (fetched 2026-08-28T04:03:51.783469+00:00, sha 72cb95511c47)
- Data as of 2026-08-30T08:39:29.467469+00:00.