TinyLLaVA/TinyLLaVA_Factory
A framework for training and building small-scale large multimodal models combining vision and language capabilities.
Not currently ranked — collecting fresh signals.
star history
TinyLLaVA Factory provides a modularized codebase for developing small-scale large multimodal models (LMMs). It supports training and experimenting with vision-language models built on architectures like LLaVA and TinyLLaMA with transformer backends. The project includes model implementations, training pipelines, and evaluation tools for multimodal AI research.
Frequently asked
- What is TinyLLaVA/TinyLLaVA_Factory?
- A framework for training and building small-scale large multimodal models combining vision and language capabilities.
- Is TinyLLaVA_Factory open source?
- Yes — TinyLLaVA/TinyLLaVA_Factory is open source, released under the Apache-2.0 license.
- What language is TinyLLaVA_Factory written in?
- TinyLLaVA/TinyLLaVA_Factory is primarily written in Python.
- How popular is TinyLLaVA_Factory?
- TinyLLaVA/TinyLLaVA_Factory has 993 stars on GitHub.
- Where can I find TinyLLaVA_Factory?
- TinyLLaVA/TinyLLaVA_Factory is on GitHub at https://github.com/TinyLLaVA/TinyLLaVA_Factory.