LLaVA++ (LLaMA-3 and Phi-3-Mini)
Collection
Extending Visual Capabilities of LLaVA with LLaMA-3 and Phi-3
•
11 items
•
Updated
•
23
Phi-3-V: Extending the Visual Capabilities of LLaVA with Phi-3
Repository Overview
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.
Training Strategy
- Pretraining: Only Vision-to-Language projector is trained. The rest of the model is frozen.
- Fine-tuning: LLM is LoRA fine-tuned. Only the vision-backbone (CLIP) is kept frozen.
- Note: The repository contains merged weights.
Key Components
- Base Large Language Model (LLM): Phi-3-mini-4k-instruct
- Base Large Multimodal Model (LMM): LLaVA-v1.5
Training Data
- Pretraining Dataset: LCS-558K
- Fine-tuning Dataset: LLaVA-Instruct-665K
Download It As
git lfs install
git clone https://huggingface.co/MBZUAI/LLaVA-Phi-3-mini-4k-instruct
License
This project is available under the MIT License.
Contributions
Contributions are welcome! Please 🌟 our repository LLaVA++ if you find this model useful.
- Downloads last month
- 3,245
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.