Instructions to use MYTH-Lab/VW-LMM-Vicuna-pif-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MYTH-Lab/VW-LMM-Vicuna-pif-7b with Transformers:

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

pipe = pipeline("text-generation", model="MYTH-Lab/VW-LMM-Vicuna-pif-7b")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("MYTH-Lab/VW-LMM-Vicuna-pif-7b")
model = AutoModelForCausalLM.from_pretrained("MYTH-Lab/VW-LMM-Vicuna-pif-7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MYTH-Lab/VW-LMM-Vicuna-pif-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MYTH-Lab/VW-LMM-Vicuna-pif-7b

SGLang

How to use MYTH-Lab/VW-LMM-Vicuna-pif-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 "MYTH-Lab/VW-LMM-Vicuna-pif-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": "MYTH-Lab/VW-LMM-Vicuna-pif-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 "MYTH-Lab/VW-LMM-Vicuna-pif-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": "MYTH-Lab/VW-LMM-Vicuna-pif-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MYTH-Lab/VW-LMM-Vicuna-pif-7b with Docker Model Runner:
```
docker model run hf.co/MYTH-Lab/VW-LMM-Vicuna-pif-7b
```

VW-LMM Model Card

This repo contains the weights of VW-LMM-Vicuna-pif-7b proposed in paper "Multi-modal Auto-regressive Modeling via Visual Words"

The term "pif" in the model name stands for "pseudo image features". This model is capable of accepting pseudo-image features constructed using the VM_head and word embeddings of the model as a substitute for real image inputs.

For specific usage and chat templates, please refer to our project repo https://github.com/pengts/VW-LMM

Model details

Model type: VW-LMM is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.

paper: https://arxiv.org/abs/2403.07720

code: https://github.com/pengts/VW-LMM

License

Citation

If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil:.

@misc{peng2024multimodal,
      title={Multi-modal Auto-regressive Modeling via Visual Words}, 
      author={Tianshuo Peng and Zuchao Li and Lefei Zhang and Hai Zhao and Ping Wang and Bo Du},
      year={2024},
      eprint={2403.07720},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Downloads last month: 3

Paper for MYTH-Lab/VW-LMM-Vicuna-pif-7b

Multi-modal Auto-regressive Modeling via Visual Words

Paper • 2403.07720 • Published Mar 12, 2024