Instructions to use ShareGPTVideo/LLaVA-Hound-SFT-Image_only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ShareGPTVideo/LLaVA-Hound-SFT-Image_only with Transformers:

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

pipe = pipeline("text-generation", model="ShareGPTVideo/LLaVA-Hound-SFT-Image_only")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ShareGPTVideo/LLaVA-Hound-SFT-Image_only", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ShareGPTVideo/LLaVA-Hound-SFT-Image_only with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ShareGPTVideo/LLaVA-Hound-SFT-Image_only"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ShareGPTVideo/LLaVA-Hound-SFT-Image_only",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ShareGPTVideo/LLaVA-Hound-SFT-Image_only

SGLang

How to use ShareGPTVideo/LLaVA-Hound-SFT-Image_only 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 "ShareGPTVideo/LLaVA-Hound-SFT-Image_only" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ShareGPTVideo/LLaVA-Hound-SFT-Image_only",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ShareGPTVideo/LLaVA-Hound-SFT-Image_only" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ShareGPTVideo/LLaVA-Hound-SFT-Image_only",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ShareGPTVideo/LLaVA-Hound-SFT-Image_only with Docker Model Runner:
```
docker model run hf.co/ShareGPTVideo/LLaVA-Hound-SFT-Image_only
```

LLaVA-Hound Model Card

Model details

Model type: LLaVA-Hound is an open-source video large multimodal model, fine-tuned from video instruction following data based on large language model.

This model is the fine-tuned on image instruction and video caption trained from ShareGPTVideo/LLaVA-Hound-Pretrain..

Base LLM: lmsys/vicuna-7b-v1.5

Model date: Trained on March 15, 2024.

Paper or resources for more information: https://github.com/RifleZhang/LLaVA-Hound-DPO

License

lmsys/vicuna-7b-v1.5 license.

Where to send questions or comments about the model: https://github.com/RifleZhang/LLaVA-Hound-DPO/issues

Intended use

Primary intended uses: Video (and image) instruction-following.

Primary intended users: Researchers in artificial intelligence, large multimodal model, etc.

Training dataset

ShareGPTVideo dataset.

Evaluation

Follow https://github.com/RifleZhang/LLaVA-Hound-DPO/blob/main/README.md

Downloads last month: 2

Safetensors

Model size

7B params

Tensor type

BF16