RRepoGEO

REPOGEO REPORT · LITE

Tongjilibo/build_MiniLLM_from_scratch

Default branch master · commit 1c559f6d · scanned 6/9/2026, 7:18:14 AM

GitHub: 552 stars · 62 forks

AI VISIBILITY SCORE
22 /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
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 Tongjilibo/build_MiniLLM_from_scratch, 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 README opening to emphasize 'from-scratch' guide

    Why:

    COPY-PASTE FIX
    这是一个从零开始构建小型大语言模型（MiniLLM）的实践项目，涵盖预训练、指令微调、奖励模型和强化学习的全过程。

Bert4torch | Torch4keras
  • mediumtopics#2
    Add more specific topics for better categorization

    Why:

    CURRENT
    bert4torch, llama2, llm
    COPY-PASTE FIX
    bert4torch, llama2, llm, llm-from-scratch, deep-learning-tutorial, educational-project, machine-learning-guide, sft, dpo, pretraining
  • lowhomepage#3
    Add a homepage URL

    Why:

    COPY-PASTE FIX
    https://github.com/Tongjilibo/build_MiniLLM_from_scratch

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 Tongjilibo/build_MiniLLM_from_scratch
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Hugging Face Transformers
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Hugging Face Transformers · recommended 1×
  2. Datasets · recommended 1×
  3. Accelerate · recommended 1×
  4. PyTorch · recommended 1×
  5. TensorFlow · recommended 1×
  • CATEGORY QUERY
    How to build a small language model from scratch, covering pre-training and fine-tuning?
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers
    2. Datasets
    3. Accelerate
    4. PyTorch
    5. TensorFlow
    6. Keras
    7. OpenAI GPT-2
    8. SentencePiece
    9. Hugging Face Tokenizers

    AI recommended 9 alternatives but never named Tongjilibo/build_MiniLLM_from_scratch. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for practical examples to train a custom LLM compatible with Hugging Face Transformers.
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers (huggingface/transformers)
    2. Hugging Face Course
    3. trl (huggingface/trl)
    4. peft (huggingface/peft)
    5. lit-gpt (Lightning-AI/lit-gpt)
    6. OpenAssistant/oasst-sft-1 (OpenAssistant/oasst-sft-1)
    7. lm-harness (EleutherAI/lm-harness)

    AI recommended 7 alternatives but never named Tongjilibo/build_MiniLLM_from_scratch. 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 Tongjilibo/build_MiniLLM_from_scratch?
    pass
    AI did not name Tongjilibo/build_MiniLLM_from_scratch — 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 Tongjilibo/build_MiniLLM_from_scratch in production, what risks or prerequisites should they evaluate first?
    pass
    AI named Tongjilibo/build_MiniLLM_from_scratch 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 Tongjilibo/build_MiniLLM_from_scratch solve, and who is the primary audience?
    pass
    AI did not name Tongjilibo/build_MiniLLM_from_scratch — 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 Tongjilibo/build_MiniLLM_from_scratch. 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/Tongjilibo/build_MiniLLM_from_scratch.svg)](https://repogeo.com/en/r/Tongjilibo/build_MiniLLM_from_scratch)
HTML
<a href="https://repogeo.com/en/r/Tongjilibo/build_MiniLLM_from_scratch"><img src="https://repogeo.com/badge/Tongjilibo/build_MiniLLM_from_scratch.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

Tongjilibo/build_MiniLLM_from_scratch — 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