RRepoGEO

REPOGEO REPORT · LITE

AndrewZhe/lawyer-llama

Default branch main · commit abaa0958 · scanned 6/1/2026, 4:58:39 PM

GitHub: 992 stars · 130 forks

AI VISIBILITY SCORE
28 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
2 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface AndrewZhe/lawyer-llama, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Explicitly state this repository is the official Lawyer LLaMA (律师LLaMA)

    Why:

    CURRENT
    # Lawyer LLaMA

通过指令微调，LLaMA 模型在通用领域展现出了非常好的表现。但由于缺少合适的数据，少有人探究LLaMA在法律领域的能力。为了弥补这一空白，我们提出了Lawyer LLaMA，一个在法律领域数据上进行了额外训练的模型。
    COPY-PASTE FIX
    # Lawyer LLaMA (律师LLaMA)

本仓库是Lawyer LLaMA (律师LLaMA)的官方实现。通过指令微调，LLaMA 模型在通用领域展现出了非常好的表现。但由于缺少合适的数据，少有人探究LLaMA在法律领域的能力。为了弥补这一空白，我们提出了Lawyer LLaMA，一个在法律领域数据上进行了额外训练的模型。
  • mediumhomepage#2
    Add the repository URL as the project homepage

    Why:

    COPY-PASTE FIX
    https://github.com/AndrewZhe/lawyer-llama
  • mediumtopics#3
    Add more specific topics related to Chinese legal AI and legal tech

    Why:

    CURRENT
    alpaca, large-language-models, legal-ai, llama, llm, nlp, plm, pretrained-language-model, pretrained-models
    COPY-PASTE FIX
    alpaca, large-language-models, legal-ai, llama, llm, nlp, plm, pretrained-language-model, pretrained-models, chinese-legal-ai, chinese-llm, legal-tech, law-tech

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface AndrewZhe/lawyer-llama
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Lawyer LLaMA (律师LLaMA)
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Lawyer LLaMA (律师LLaMA) · recommended 1×
  2. ChatLaw (ChatGLM-6B based) · recommended 1×
  3. CPM-Live (Legal Domain) · recommended 1×
  4. Baichuan 2 (7B/13B/53B) · recommended 1×
  5. Qwen (7B/14B/72B) · recommended 1×
  • CATEGORY QUERY
    What open source models are available for developing a Chinese legal AI assistant?
    you: not recommended
    AI recommended (in order):
    1. Lawyer LLaMA (律师LLaMA)
    2. ChatLaw (ChatGLM-6B based)
    3. CPM-Live (Legal Domain)
    4. Baichuan 2 (7B/13B/53B)
    5. Qwen (7B/14B/72B)
    6. Pangu-Σ (盘古大模型)
    7. Chinese LLaMA/Alpaca (General Purpose)

    AI recommended 7 alternatives but never named AndrewZhe/lawyer-llama. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    How to fine-tune a large language model with specialized Chinese legal data?
    you: not recommended
    AI recommended (in order):
    1. DeepSpeed
    2. Hugging Face Transformers Library
    3. Megatron-LM
    4. OpenPrompt
    5. Colossal-AI
    6. MindSpore
    7. PaddlePaddle

    AI recommended 7 alternatives but never named AndrewZhe/lawyer-llama. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of AndrewZhe/lawyer-llama?
    pass
    AI did not name AndrewZhe/lawyer-llama — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts AndrewZhe/lawyer-llama in production, what risks or prerequisites should they evaluate first?
    pass
    AI named AndrewZhe/lawyer-llama explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo AndrewZhe/lawyer-llama solve, and who is the primary audience?
    pass
    AI named AndrewZhe/lawyer-llama explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of AndrewZhe/lawyer-llama. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/AndrewZhe/lawyer-llama.svg)](https://repogeo.com/en/r/AndrewZhe/lawyer-llama)
HTML
<a href="https://repogeo.com/en/r/AndrewZhe/lawyer-llama"><img src="https://repogeo.com/badge/AndrewZhe/lawyer-llama.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

AndrewZhe/lawyer-llama — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite