Instructions to use FreedomIntelligence/LongLLaVA-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/LongLLaVA-9B with Transformers:

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

pipe = pipeline("image-text-to-text", model="FreedomIntelligence/LongLLaVA-9B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/LongLLaVA-9B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FreedomIntelligence/LongLLaVA-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/LongLLaVA-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/LongLLaVA-9B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/LongLLaVA-9B

SGLang

How to use FreedomIntelligence/LongLLaVA-9B 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 "FreedomIntelligence/LongLLaVA-9B" \
    --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": "FreedomIntelligence/LongLLaVA-9B",
		"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 "FreedomIntelligence/LongLLaVA-9B" \
        --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": "FreedomIntelligence/LongLLaVA-9B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/LongLLaVA-9B with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/LongLLaVA-9B
```

📃 Paper • 🌐 Demo • 📃 Github • 🤗 LongLLaVA-53B-A13B

🌈 Update

[2024.09.05] LongLLaVA repo is published！🎉
[2024.10.12] LongLLaVA-53B-A13B, LongLLaVA-9b and Jamba-9B-Instruct are repleased！🎉

Architecture

Click to view the architecture image

Results

Click to view the Results

Main Results
Diagnostic Results
Video-NIAH

Results reproduction

Evaluation

Preparation

Get the model inference code from Github.

git clone https://github.com/FreedomIntelligence/LongLLaVA.git

Environment Setup

pip install -r requirements.txt

Command Line Interface

python cli.py --model_dir path-to-longllava

Model Inference

query = 'What does the picture show?'
image_paths = ['image_path1'] # image or video path

from cli import Chatbot
bot = Chatbot(path-to-longllava)
output = bot.chat(query, image_paths)
print(output) # Prints the output of the model

Acknowledgement

LLaVA: Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Citation

@misc{wang2024longllavascalingmultimodalllms,
      title={LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture}, 
      author={Xidong Wang and Dingjie Song and Shunian Chen and Chen Zhang and Benyou Wang},
      year={2024},
      eprint={2409.02889},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2409.02889}, 
}