REPOGEO REPORT · LITE

TinyLLaVA/TinyLLaVA_Factory

Default branch main · commit 53f12c78 · scanned 6/9/2026, 1:23:01 AM

GitHub: 985 stars · 101 forks

AI VISIBILITY SCORE

40 /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

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 TinyLLaVA/TinyLLaVA_Factory, 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 the project's role as a framework in the README's opening

Why:

CURRENT

The current README starts with a centered H2 title followed by news and then takeaways.

COPY-PASTE FIX

Add the following sentence immediately after the main title: "TinyLLaVA Factory is an open-source modular codebase for small-scale large multimodal models (LMMs), implemented in PyTorch and HuggingFace, focusing on simplicity, extensibility, and reproducibility."

mediumtopics#2

Add more specific topics to emphasize the framework aspect

Why:

CURRENT

large-multimodal-models, llama, llava, nlp, tinyllama, transformers, vision-language

COPY-PASTE FIX

large-multimodal-models, llama, llava, nlp, tinyllama, transformers, vision-language, lmm-framework, multimodal-codebase, small-lmm, efficient-lmm, pytorch-lmm

mediumcomparison#3

Add a 'Why TinyLLaVA Factory?' section to differentiate from general models and frameworks

Why:

COPY-PASTE FIX

Add a new section to the README, e.g., "## &#x1F9E9; Why TinyLLaVA Factory?
Unlike general LMMs like CLIP or BLIP, or broad ML frameworks such as Hugging Face Transformers, TinyLLaVA Factory provides a dedicated, modular codebase for *building and customizing* small-scale LLaVA-style models. Our focus is on efficiency, extensibility, and reproducibility, making it ideal for researchers and developers working with resource-optimized multimodal AI."

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 TinyLLaVA/TinyLLaVA_Factory

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

OpenCLIP

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

OpenCLIP · recommended 1×
BLIP · recommended 1×
MiniGPT-4 · recommended 1×
CLIP · recommended 1×
MobileCLIP · recommended 1×

CATEGORY QUERY
seeking efficient multimodal models that achieve strong performance without large resource requirements
you: not recommended
AI recommended (in order):
1. OpenCLIP
2. BLIP
3. MiniGPT-4
4. CLIP
5. MobileCLIP
6. DeCLIP
AI recommended 6 alternatives but never named TinyLLaVA/TinyLLaVA_Factory. This is the gap to close.
Show full AI answer
CATEGORY QUERY
looking for a modular framework to develop custom small vision-language models efficiently
you: not recommended
AI recommended (in order):
1. Hugging Face Transformers (huggingface/transformers)
2. diffusers (huggingface/diffusers)
3. peft (huggingface/peft)
4. PyTorch Lightning (Lightning-AI/lightning)
5. Keras (keras-team/keras)
6. OpenMMLab
7. MMDetection (open-mmlab/mmdetection)
8. MMEngine (open-mmlab/mmengine)
9. MMPretrain (open-mmlab/mmpretrain)
10. JAX (google/jax)
11. Flax (google/flax)
AI recommended 11 alternatives but never named TinyLLaVA/TinyLLaVA_Factory. 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 TinyLLaVA/TinyLLaVA_Factory?
pass
AI named TinyLLaVA/TinyLLaVA_Factory explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts TinyLLaVA/TinyLLaVA_Factory in production, what risks or prerequisites should they evaluate first?
pass
AI named TinyLLaVA/TinyLLaVA_Factory 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 TinyLLaVA/TinyLLaVA_Factory solve, and who is the primary audience?
pass
AI named TinyLLaVA/TinyLLaVA_Factory 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 TinyLLaVA/TinyLLaVA_Factory. 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/TinyLLaVA/TinyLLaVA_Factory.svg)](https://repogeo.com/en/r/TinyLLaVA/TinyLLaVA_Factory)

HTML

<a href="https://repogeo.com/en/r/TinyLLaVA/TinyLLaVA_Factory"><img src="https://repogeo.com/badge/TinyLLaVA/TinyLLaVA_Factory.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

TinyLLaVA/TinyLLaVA_Factory — 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