# Kent0n-Li/ChatDoctor

Repository: https://github.com/Kent0n-Li/ChatDoctor
Canonical: https://ross.abutalabs.com/products/chatdoctor
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-05-17T22:24:31+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 90
- inputs: {"age_days": 1261, "days_push": 838, "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 3631, forks 427 (observed 2026-08-28T04:08:12.046952+00:00)

## What it is
ChatDoctor is a medical chat model fine-tuned on LLaMA using real patient-doctor conversations, with training code, datasets (HealthCareMagic-100k, icliniq-10k), and model checkpoints. It is a research project demonstrating domain-specific LLM fine-tuning for medical dialogue.

## Use cases
- fine-tune an llm on medical conversations
- build a healthcare chatbot prototype
- download patient-doctor dialogue datasets for training
- research domain-specific llm fine-tuning
- experiment with medical question answering models

## When to choose
- you need real patient-doctor conversation datasets for research
- you want to study or reproduce medical LLM fine-tuning
- you need a starting point for domain-adapted chat models

## When to avoid
- you need a clinically reliable medical assistant - the authors warn against real clinical use
- you need a production-ready chatbot with support and guarantees
- you need up-to-date medical knowledge beyond the training data

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-training, chatbot, machine-learning, rag
- domain: healthcare, large-language-models, artificial-intelligence
- platform: python, cross-platform
- tags: medical-ai, llama-finetuning, healthcare-chatbot, fine-tuning, medical-dataset, research-model, natural-language-processing, gpu

## Member repositories
- Kent0n-Li/ChatDoctor (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:12.046952+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 2026-08-29T18:31:52.733630+00:00, confidence not recorded.
  - readme: https://github.com/Kent0n-Li/ChatDoctor (fetched 2026-08-28T04:08:12.046952+00:00, sha 69a453f29280)
- Data as of 2026-08-30T08:39:29.467469+00:00.