Downloads · 30 days
21
1% of all-time downloads
LLaVA-Phi-3-mini-4k-instruct-FT
MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT
LLaVA-Phi-3-mini-4k-instruct-FT is a text generation model from MBZUAI. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
[](https://github.com/mbzuai-oryx/LLaVA-pp)
All-time downloads
2.7K
Public
Parameters
4.1B
8.3 GB on disk
Likes
5
Public
Repo makeup
Click a slice to open those files.
.safetensors8.3 GB · 100%
Parameter types
How the weights are stored.
BF164.1B · 100%
Try a prompt
Model card
From the Hugging Face model README
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: All model parameters including LLM are fine-tuned. Only the vision-backbone (CLIP) is kept frozen.
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-FT
License
This project is available under the MIT License.
Contributions
Contributions are welcome! Please 🌟 our repository LLaVA++ if you find this model useful.
- Task
- Text Generation
- Library
- transformers
- Type
- llava_phi
- License
- mit
- Created
- Apr 27, 2024
- Updated
- Apr 27, 2024