# pengxiao-song/LaWGPT

🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型

Repository: https://github.com/pengxiao-song/LaWGPT
Canonical: https://ross.abutalabs.com/products/lawgpt
Homepage: https://github.com/pengxiao-song/LaWGPT/
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2024-06-11T07:20:19+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 87
- inputs: {"age_days": 1231, "days_push": 813, "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 6059, forks 546 (observed 2026-08-28T04:09:34.712006+00:00)

## What it is
LaWGPT is a series of open-source large language models tuned with Chinese legal knowledge, built on Chinese-LLaMA/ChatGLM base models with legal vocabulary expansion, continued pretraining on legal corpora, and instruction fine-tuning on legal QA and judicial exam datasets. The repository provides training, inference, and a Gradio web UI for running the models.

## Use cases
- build a chinese legal question answering chatbot
- fine-tune llama on domain-specific chinese legal corpora
- run a legal assistant llm locally with a web ui
- continue pretraining a base model on judicial documents
- answer chinese bar exam questions with an llm

## When to choose
- you need a Chinese-language legal domain LLM with open weights
- you want to reproduce or extend domain-adaptive pretraining and instruction tuning pipelines
- you need a self-hosted legal QA model with a web interface

## When to avoid
- you need up-to-date legal advice with verified citations
- you need a general-purpose assistant rather than legal-domain text
- you lack GPU resources for 7B model inference or training

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-training, llm-inference, chatbot, nlp
- domain: large-language-models, legal, artificial-intelligence
- platform: python
- tags: chinese-legal, llama, fine-tuning, lora, legal-qa, domain-adaptation, webui, natural-language-processing, linux, gpu

## Member repositories
- pengxiao-song/LaWGPT (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:34.712006+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 2026-08-29T17:48:43.969003+00:00, confidence not recorded.
  - readme: https://github.com/pengxiao-song/LaWGPT (fetched 2026-08-28T04:09:34.712006+00:00, sha 11793330d852)
  - homepage: https://github.com/pengxiao-song/LaWGPT/ (fetched 2026-08-29T08:45:05.714072+00:00, sha 352f17674699)
- Data as of 2026-08-30T08:39:29.467469+00:00.