RRepoGEO

REPOGEO REPORT · LITE

zhanshijinwat/Steel-LLM

Default branch main · commit d6603699 · scanned 6/2/2026, 3:58:22 AM

GitHub: 808 stars · 79 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 zhanshijinwat/Steel-LLM, 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
    Clarify project's purpose and target audience in README's opening

    Why:

    CURRENT
    # 开源中文预训练语言模型Steel-LLM
    COPY-PASTE FIX
    # 开源中文预训练语言模型Steel-LLM

**Note: Steel-LLM is a project for pre-training Chinese LLMs from scratch, NOT related to the steel industry.**
  • highlicense#2
    Add a LICENSE file and specify the license

    Why:

    COPY-PASTE FIX
    Create a `LICENSE` file in the repository root containing the full text of a standard open-source license (e.g., MIT License or Apache-2.0 License). Then, add the following line to the README, preferably near the top or in the '介绍' (Introduction) section: 'This project is licensed under the [Chosen License Name]. See the LICENSE file for details.'
  • mediumhomepage#3
    Add a homepage URL to the repository settings

    Why:

    COPY-PASTE FIX
    Set the repository homepage URL in GitHub settings to `https://huggingface.co/gqszhanshijin/Steel-LLM` or `https://arxiv.org/abs/2502.06635`.

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 zhanshijinwat/Steel-LLM
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
huggingface/transformers
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. huggingface/transformers · recommended 1×
  2. huggingface/peft · recommended 1×
  3. microsoft/DeepSpeed · recommended 1×
  4. pytorch/pytorch · recommended 1×
  5. huggingface/accelerate · recommended 1×
  • CATEGORY QUERY
    How can I pre-train a performant Chinese language model with limited GPU resources?
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers Library (huggingface/transformers)
    2. PEFT (huggingface/peft)
    3. DeepSpeed (microsoft/DeepSpeed)
    4. PyTorch (pytorch/pytorch)
    5. Hugging Face Accelerate (huggingface/accelerate)
    6. FlashAttention (Dao-AILab/flash-attention)
    7. TinyBERT
    8. MobileBERT
    9. MiniCPM

    AI recommended 9 alternatives but never named zhanshijinwat/Steel-LLM. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for open-source frameworks to build a small Chinese LLM from scratch, including data pipelines.
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers
    2. Hugging Face Datasets
    3. PyTorch
    4. PyTorch Lightning
    5. Hugging Face Accelerate
    6. DeepSpeed
    7. PaddlePaddle
    8. ERNIE
    9. PaddleNLP
    10. TensorFlow
    11. Keras
    12. TensorFlow Datasets
    13. JAX
    14. Flax
    15. Haiku

    AI recommended 15 alternatives but never named zhanshijinwat/Steel-LLM. 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 zhanshijinwat/Steel-LLM?
    pass
    AI did not name zhanshijinwat/Steel-LLM — 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 zhanshijinwat/Steel-LLM in production, what risks or prerequisites should they evaluate first?
    pass
    AI named zhanshijinwat/Steel-LLM 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 zhanshijinwat/Steel-LLM solve, and who is the primary audience?
    pass
    AI named zhanshijinwat/Steel-LLM 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 zhanshijinwat/Steel-LLM. 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/zhanshijinwat/Steel-LLM.svg)](https://repogeo.com/en/r/zhanshijinwat/Steel-LLM)
HTML
<a href="https://repogeo.com/en/r/zhanshijinwat/Steel-LLM"><img src="https://repogeo.com/badge/zhanshijinwat/Steel-LLM.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

zhanshijinwat/Steel-LLM — 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