RRepoGEO

REPOGEO REPORT · LITE

jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese

Default branch main · commit 0f309b13 · scanned 6/5/2026, 12:28:02 AM

GitHub: 657 stars · 67 forks

AI VISIBILITY SCORE
27 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
1 / 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 jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese, 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
    Reposition the README's H1 and opening paragraph to clearly state the project's dual purpose

    Why:

    CURRENT
    # Cornucopia-LLaMA-Fin-Chinese
    ### 聚宝盆(Cornucopia): 基于中文金融知识的 LLaMA 系微调模型
    
    本项目开源了基于 LLaMA 系基模型经过中文金融知识指令精调/指令微调(Instruct-tuning) 的微调模型。通过中文金融公开问答数据+爬取的金融问答数据构建指令数据集,并在此基础上对 LLaMA 系模型进行了指令微调,提高了 LLaMA 在金融领域的问答效果。
    COPY-PASTE FIX
    # Cornucopia-LLaMA-Fin-Chinese (聚宝盆): 中文金融系列开源可商用大模型与高效轻量化训练框架
    
    本项目开源了**聚宝盆(Cornucopia)**,一个专注于中文金融领域的开源可商用大模型系列,并提供一套高效轻量化的垂直领域LLM训练框架,支持预训练、SFT、RLHF、量化等功能。我们基于LLaMA系列基模型,通过中文金融知识指令精调,显著提升了模型在金融问答领域的表现。
  • mediumtopics#2
    Refine repository topics for better specificity

    Why:

    CURRENT
    chinese, finance, large-language-models, llama, nlp, qa, rlhf, sft, text-generation, transformers
    COPY-PASTE FIX
    chinese, finance, large-language-models, llama, nlp, rlhf, sft, transformers, llm-training-framework, financial-llm, chinese-llm
  • mediumcomparison#3
    Add a 'Comparison with Similar Projects' section to the README

    Why:

    COPY-PASTE FIX
    ## 💡 与同类项目的区别
    
    与DeepSpeed、TRL等通用LLM训练框架不同,Cornucopia(聚宝盆)专注于中文金融领域的大模型训练与微调。我们不仅提供高效轻量化的训练框架,更直接开源了基于LLaMA系列的中文金融微调模型。与Appen、FinQA等数据平台或数据集项目相比,Cornucopia提供的是完整的模型和训练解决方案,而非仅仅数据或标注服务。

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 jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese
Avg rank
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Appen
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Appen · recommended 1×
  2. Scale AI · recommended 1×
  3. CAIL2019 · recommended 1×
  4. FinQA · recommended 1×
  5. Scrapy · recommended 1×
  • CATEGORY QUERY
    How can I fine-tune a large language model for Chinese financial question answering?
    you: not recommended
    AI recommended (in order):
    1. Appen
    2. Scale AI
    3. CAIL2019
    4. FinQA
    5. Scrapy
    6. Beautiful Soup
    7. Baichuan 2
    8. Qwen
    9. ERNIE-Bot
    10. LLaMA 2
    11. ChatGLM
    12. LoRA
    13. Hugging Face PEFT
    14. Hugging Face Transformers
    15. Hugging Face Datasets
    16. Hugging Face Accelerate
    17. PyTorch
    18. TensorFlow
    19. AWS
    20. Google Cloud
    21. Azure
    22. Weights & Biases (W&B)
    23. MLflow
    24. ROUGE
    25. BLEU
    26. METEOR
    27. F1 Score

    AI recommended 27 alternatives but never named jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What open-source framework helps train financial LLMs with SFT and RLHF for Chinese text?
    you: not recommended
    AI recommended (in order):
    1. DeepSpeed
    2. TRL
    3. Colossal-AI
    4. OpenRLHF
    5. Megatron-LM

    AI recommended 5 alternatives but never named jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    pass

  • 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 jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese?
    pass
    AI did not name jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese — 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 jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese in production, what risks or prerequisites should they evaluate first?
    pass
    AI named jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese 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 jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese solve, and who is the primary audience?
    pass
    AI did not name jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese — 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?

Embed your GEO score

Drop this badge into the README of jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese. 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/jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese.svg)](https://repogeo.com/en/r/jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese)
HTML
<a href="https://repogeo.com/en/r/jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese"><img src="https://repogeo.com/badge/jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese — 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