REPOGEO REPORT · LITE

merveenoyan/smol-vision

Default branch main · commit 420d2af9 · scanned 6/20/2026, 8:23:12 PM

GitHub: 1,948 stars · 152 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 merveenoyan/smol-vision, 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

hightopics#1

Add comprehensive topics to the repository

Why:

COPY-PASTE FIX

computer-vision, multimodal-ai, model-optimization, fine-tuning, deep-learning, machine-learning, quantization, knowledge-distillation, onnx, paligemma, florence-2, kosmos-2-5, recipes, examples

highreadme#2

Elevate and clarify the README's mention of external notebooks

Why:

CURRENT

The 'Note' about external notebooks is placed after the initial examples list.

COPY-PASTE FIX

Move the existing 'Note: GitHub refuses to render notebooks for a long time now, so the notebooks of smol-vision with rich outputs now lives here. I still update this repository but it's inconvenient to read here.' to be immediately after the initial description sentence ('Recipes for shrinking, optimizing, customizing cutting edge vision and multimodal AI models.').

mediumhomepage#3
Add a homepage URL to the repository metadata
Why:
COPY-PASTE FIX
```
[URL of the external notebook collection, as mentioned in the README]
```

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 merveenoyan/smol-vision

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

TensorRT

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

TensorRT · recommended 1×
OpenVINO · recommended 1×
ONNX Runtime · recommended 1×
PyTorch Quantization APIs · recommended 1×
TensorFlow Model Optimization Toolkit · recommended 1×

CATEGORY QUERY
How to optimize large vision models for faster inference and smaller deployment size?
you: not recommended
AI recommended (in order):
1. TensorRT
2. OpenVINO
3. ONNX Runtime
4. PyTorch Quantization APIs
5. TensorFlow Model Optimization Toolkit
6. PyTorch Pruning APIs
7. Hugging Face Transformers
8. MMDetection (open-mmlab/mmdetection)
9. MMSegmentation (open-mmlab/mmsegmentation)
10. AutoML
11. EfficientNet
12. MobileNet
13. TVM (apache/tvm)
AI recommended 13 alternatives but never named merveenoyan/smol-vision. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What are the best practices for fine-tuning state-of-the-art vision models for custom tasks?
you: not recommended
AI recommended (in order):
1. Albumentations (albumentations-team/albumentations)
2. torchvision (pytorch/vision)
3. Keras (keras-team/keras)
4. PyTorch (pytorch/pytorch)
5. TensorFlow (tensorflow/tensorflow)
6. fastai (fastai/fastai)
7. NVIDIA Apex (NVIDIA/apex)
AI recommended 7 alternatives but never named merveenoyan/smol-vision. 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 merveenoyan/smol-vision?
pass
AI named merveenoyan/smol-vision explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts merveenoyan/smol-vision in production, what risks or prerequisites should they evaluate first?
pass
AI named merveenoyan/smol-vision 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 merveenoyan/smol-vision solve, and who is the primary audience?
pass
AI named merveenoyan/smol-vision 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 merveenoyan/smol-vision. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/merveenoyan/smol-vision.svg)](https://repogeo.com/en/r/merveenoyan/smol-vision)

HTML

<a href="https://repogeo.com/en/r/merveenoyan/smol-vision"><img src="https://repogeo.com/badge/merveenoyan/smol-vision.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

merveenoyan/smol-vision — 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