Instructions to use MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT

SGLang

How to use MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT with Docker Model Runner:
```
docker model run hf.co/MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT
```

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.

Downloads last month: 42

Safetensors

Model size

4B params

Tensor type

F32

BF16

Collection including MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT

LLaVA++ (LLaMA-3 and Phi-3-Mini)

Collection

Extending Visual Capabilities of LLaVA with LLaMA-3 and Phi-3 • 11 items • Updated Jun 11, 2024 • 23