RRepoGEO

REPOGEO REPORT · LITE

VHellendoorn/Code-LMs

Default branch main · commit 570feba4 · scanned 6/30/2026, 5:52:36 PM

GitHub: 1,842 stars · 263 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
35 /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
3 / 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 VHellendoorn/Code-LMs, 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's opening to clarify its purpose as a guide

    Why:

    CURRENT
    # Large Models of Source Code
I occasionally train and publicly release large neural language models on programs, including PolyCoder. Here, I describe how to use these.
    COPY-PASTE FIX
    # Guide to Using Large Language Models of Source Code
This repository serves as a comprehensive guide and resource for leveraging pre-trained large language models (LLMs) specifically for source code. It details how to use models like PolyCoder for various code-related tasks, providing practical examples and setup instructions.
  • mediumhomepage#2
    Add a homepage URL

    Why:

    COPY-PASTE FIX
    https://huggingface.co/NinedayWang/PolyCoder-2.7B
  • lowtopics#3
    Expand topics for better categorization

    Why:

    CURRENT
    deep-learning, gpt-2, source-code
    COPY-PASTE FIX
    deep-learning, source-code, large-language-models, llms, code-generation, code-completion, transformers, polycoder

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 VHellendoorn/Code-LMs
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
GitHub Copilot
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. GitHub Copilot · recommended 2×
  2. OpenAI API · recommended 1×
  3. Google Gemini API · recommended 1×
  4. huggingface/transformers · recommended 1×
  5. facebookresearch/codellama · recommended 1×
  • CATEGORY QUERY
    How can I leverage pre-trained large language models for source code generation tasks?
    you: not recommended
    AI recommended (in order):
    1. GitHub Copilot
    2. OpenAI API
    3. Google Gemini API
    4. Hugging Face Transformers Library (huggingface/transformers)
    5. CodeLlama (facebookresearch/codellama)
    6. StarCoder (bigcode-project/starcoder)
    7. Incoder (facebookresearch/incoder)
    8. Replit AI (Ghostwriter)
    9. Tabnine

    AI recommended 9 alternatives but never named VHellendoorn/Code-LMs. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are effective deep learning models for intelligent code completion and suggestion?
    you: not recommended
    AI recommended (in order):
    1. GPT-3
    2. GPT-4
    3. Codex
    4. GitHub Copilot
    5. CodeBERT
    6. GraphCodeBERT
    7. CodeT5
    8. RoBERTa
    9. BERT
    10. LSTM networks
    11. N-gram based LMs
    12. Word2Vec
    13. GloVe

    AI recommended 13 alternatives but never named VHellendoorn/Code-LMs. 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 VHellendoorn/Code-LMs?
    pass
    AI named VHellendoorn/Code-LMs explicitly

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

  • If a team adopts VHellendoorn/Code-LMs in production, what risks or prerequisites should they evaluate first?
    pass
    AI named VHellendoorn/Code-LMs 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 VHellendoorn/Code-LMs solve, and who is the primary audience?
    pass
    AI named VHellendoorn/Code-LMs 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 VHellendoorn/Code-LMs. 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/VHellendoorn/Code-LMs.svg)](https://repogeo.com/en/r/VHellendoorn/Code-LMs)
HTML
<a href="https://repogeo.com/en/r/VHellendoorn/Code-LMs"><img src="https://repogeo.com/badge/VHellendoorn/Code-LMs.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

VHellendoorn/Code-LMs — 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