LLaVA++ (LLaMA-3 and Phi-3-Mini)
Collection
Extending Visual Capabilities of LLaVA with LLaMA-3 and Phi-3
β’
11 items
β’
Updated
β’
23
This repository features LLaVA v1.5 trained with the Phi-3-mini-3.8B LLM. This integration aims to leverage the strengths of both models to offer advanced vision-language understanding.
git lfs install
git clone https://huggingface.co/MBZUAI/LLaVA-Phi-3-mini-4k-instruct
This project is available under the MIT License.
Contributions are welcome! Please π our repository LLaVA++ if you find this model useful.