# LiuHC0428/LAW-GPT

中文法律对话语言模型

Repository: https://github.com/LiuHC0428/LAW-GPT
Canonical: https://ross.abutalabs.com/products/law-gpt
Language: Python
License Family: other
Last push: 2024-05-13T08:25:34+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 88
- inputs: {"age_days": 1242, "days_push": 842, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1194, forks 125 (observed 2026-08-28T04:03:56.702584+00:00)

## What it is
A Chinese-language legal conversational model (LawGPT_zh / 獬豸) fine-tuned from ChatGLM-6B with LoRA on legal Q&A datasets, including answers grounded in specific Chinese law articles. It ships training data, retrieval-augmented demos, and a CLI chat interface.

## Use cases
- answer legal questions in Chinese
- build a legal advice chatbot
- fine-tune ChatGLM-6B on legal data
- get answers citing relevant law articles
- download Chinese legal Q&A datasets
- run a legal assistant demo locally

## When to choose
- you need a Chinese legal-domain chat model with cited legal basis
- you want open legal Q&A training data for fine-tuning
- you have a GPU with 15GB+ VRAM and want a self-hosted legal assistant

## When to avoid
- you need legal advice you can rely on without professional review
- you need a non-Chinese legal system or language
- you lack a GPU or want a hosted API
- you require a permissively licensed project (no license is provided)

## Facets
- artifact type: application
- maturity: maintenance
- function: llm-inference, rag, chatbot, machine-learning
- domain: large-language-models, legal, artificial-intelligence
- platform: python, cli
- tags: chinese-law, chatglm, lora-finetuning, legal-qa, law, fine-tuned-model, natural-language-processing, gpu

## Member repositories
- LiuHC0428/LAW-GPT (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.702584+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 2026-08-30T06:22:08.575642+00:00, confidence not recorded.
  - readme: https://github.com/LiuHC0428/LAW-GPT (fetched 2026-08-28T04:03:56.702584+00:00, sha 459d879364e4)
- Data as of 2026-08-30T08:39:29.467469+00:00.