Instructions to use zhuoyanxu/ada-llava-L-v1.5-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zhuoyanxu/ada-llava-L-v1.5-7b with Transformers:

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

pipe = pipeline("image-text-to-text", model="zhuoyanxu/ada-llava-L-v1.5-7b")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("zhuoyanxu/ada-llava-L-v1.5-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zhuoyanxu/ada-llava-L-v1.5-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zhuoyanxu/ada-llava-L-v1.5-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zhuoyanxu/ada-llava-L-v1.5-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zhuoyanxu/ada-llava-L-v1.5-7b

SGLang

How to use zhuoyanxu/ada-llava-L-v1.5-7b 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 "zhuoyanxu/ada-llava-L-v1.5-7b" \
    --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": "zhuoyanxu/ada-llava-L-v1.5-7b",
		"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 "zhuoyanxu/ada-llava-L-v1.5-7b" \
        --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": "zhuoyanxu/ada-llava-L-v1.5-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zhuoyanxu/ada-llava-L-v1.5-7b with Docker Model Runner:
```
docker model run hf.co/zhuoyanxu/ada-llava-L-v1.5-7b
```

Ada-LLaVA Model Card

Ada-LLaVA-L-7B is an open-source adaptive inference framework for multimodal Large Language Models (MLLMs) that dynamically adjusts its operations based on available computational resources and latency requirements.

See the paper for more details: Learning to Inference Adaptively for Multimodal Large Language Models

Model details: https://zhuoyan-xu.github.io/ada-llava/

Github repository: https://github.com/zhuoyan-xu/AdaLLaVA

Model Details

Model Type: Ada LLaVA 7B follows the LLaVA-v1.5 stage-2 training pipeline, with CLIP-ViT-L-336px as visual encoder (336*336 image resolution), Vicuna-v1.5-7B as base LLM and a two-layer MLP as vision-language connector, customized embedding model and MLP as latency scheduler.

It was trained with stage-2 pipeline as LLaVA:

Instruction tuning: Freeze vision encoder, train the remaining model with multimodal instruction following data of tabular and non-tabular tasks.

Code Base: We use the official code of LLaVA-v1.5 for model training and inference, and the saved model checkpoint is uploaded to this repository.

Model Date: Ada-LLaVA 7B was trained in Oct 2024.

License

Intended use

Primary intended uses: The primary use of Ada LLaVA is research on multimodal large multimodal models and chatbots, especially for resource-constrain inference and deployment.

Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

665K image level instruction data from LLaVA-1.5 stage-2, see details in original LLaVA repo.

Limitations

While Ada-LLaVA is currently limited to processing one image at a time and only applies adaptive operations in its later half of layers, future work could explore multi-image input support and extend the adaptive mechanisms throughout the entire model architecture, including the vision encoder. These improvements would make the model more versatile and applicable to a broader range of real-world scenarios.