# CSHaitao/LexiLaw

LexiLaw - 中文法律大模型

Repository: https://github.com/CSHaitao/LexiLaw
Canonical: https://ross.abutalabs.com/products/lexilaw
Language: Python
License: MIT
License Family: permissive
Last push: 2026-03-12T05:47:03+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 71, release rhythm 35, longevity 86
- inputs: {"age_days": 1205, "days_push": 174, "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 1041, forks 147 (observed 2026-08-28T04:03:20.688880+00:00)

## What it is
LexiLaw is a fine-tuned Chinese legal large language model based on ChatGLM-6B, providing legal consultation and Q&A capabilities. It includes inference scripts, multiple fine-tuning checkpoints (full finetune, P-Tuning v2, LoRA), and a knowledge-base-augmented demo.

## Use cases
- answer chinese legal questions with an llm
- build a legal consultation chatbot in chinese
- fine-tune chatglm-6b on legal domain data
- add a legal knowledge base with retrieval to a chat model
- study vertical-domain llm fine-tuning techniques

## When to choose
- you need a chinese-language legal Q&A model for academic research
- you want reference implementations of finetune, P-Tuning v2, and LoRA on ChatGLM-6B
- you want a knowledge-base-augmented legal chat demo

## When to avoid
- you need legally reliable advice for real legal matters - the project explicitly forbids real-world legal use
- you need commercial usage - the license restricts use to academic research
- you need a non-Chinese legal system or English-language legal model

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, rag, chatbot, nlp
- domain: large-language-models, legal, artificial-intelligence
- platform: python, cli, self-hosted
- tags: chinese-legal-ai, chatglm, fine-tuning, legal-consultation, knowledge-base, lora, ptuning, natural-language-processing, gpu

## Member repositories
- CSHaitao/LexiLaw (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.688880+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 2026-08-30T07:02:49.693255+00:00, confidence not recorded.
  - readme: https://github.com/CSHaitao/LexiLaw (fetched 2026-08-28T04:03:20.688880+00:00, sha 2f2d29ff845c)
- Data as of 2026-08-30T08:39:29.467469+00:00.