Llava Pool

This project provides functionalities for training and configuring Vision-Language Models (VLM).

Features

• Open Vision Language Model: Ex. Qwen2-VL, Pixtral, LLama 3.2 Vision
• Training methods for VLMs: Pre-Training, Supervised Fine-Tuning

Install

git clone https://github.com/thisisiron/LLaVA-Pool.git
cd LLaVA-Pool

pip install flash-attn --no-build-isolation

Pre-training model

SFT model list

Model	Converter
Qwen2-VL	qwen2_vl
Llama 3.2 Vision	llama3.2_vision
Pixtral	pixtral

References

This repository was built based on LLaMA-Factory.

• LLaMA-Factory
• LLaVA-NeXT