# TinyLLaVA/TinyLLaVA_Factory

A Framework of Small-scale Large Multimodal Models

Repository: https://github.com/TinyLLaVA/TinyLLaVA_Factory
Canonical: https://ross.abutalabs.com/products/tinyllava_factory
Homepage: https://arxiv.org/abs/2402.14289
Language: Python
License: Apache-2.0
License Family: permissive
Topics: large-multimodal-models, llama, llava, nlp, tinyllama, transformers, vision-language
Last push: 2026-07-23T13:03:14+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 35, longevity 66
- inputs: {"age_days": 925, "days_push": 41, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1004, forks 103 (observed 2026-09-03T02:15:08.414005+00:00)

## What it is
TinyLLaVA Factory is an open-source modular PyTorch/HuggingFace codebase for training small-scale large multimodal models (LMMs) that combine vision encoders with small language models. It lets researchers customize vision towers, connectors, LLMs, and training recipes (frozen, full, LoRA/QLoRA) with minimal coding effort.

## Use cases
- train a small vision-language model on custom image-text data
- fine-tune a multimodal model with LoRA or QLoRA
- build a LLaVA-style model with a small LLM like TinyLlama or Phi
- compare vision encoders like CLIP, SigLIP, and Dino for multimodal training
- reproduce small-scale LMM training results
- run a lightweight multimodal chatbot on limited GPU resources

## When to choose
- you want to train or customize a small multimodal (vision+language) model
- you need reproducible LMM training with modular component swaps
- you lack resources for 7B+ models and want competitive 3B-class performance
- you want to experiment with different vision towers, connectors, and tuning recipes

## When to avoid
- you need a production-ready inference server or end-user application
- you only want to run pretrained models without training
- you need video or audio multimodality out of the box
- you are not working in Python/PyTorch

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, deep-learning, llm-training, image-processing
- domain: large-language-models, machine-learning, computer-vision, deep-learning
- platform: python
- tags: multimodal, vision-language-models, llava, small-language-models, pytorch, huggingface, lora-fine-tuning, model-training, gpu, linux

## Member repositories
- TinyLLaVA/TinyLLaVA_Factory (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:08.414005+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:13:49.204437+00:00, confidence not recorded.
  - readme: https://github.com/TinyLLaVA/TinyLLaVA_Factory (fetched 2026-09-03T02:15:08.414005+00:00, sha 942aca124993)
  - homepage: https://arxiv.org/abs/2402.14289 (fetched 2026-08-29T13:13:37.816378+00:00, sha 2854b4613c66)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T13:13:37.819942+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T13:13:37.824271+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T13:13:37.826417+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T13:13:37.822190+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.