Instructions to use FreedomIntelligence/HuatuoGPT-Vision-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/HuatuoGPT-Vision-7B with Transformers:

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

pipe = pipeline("text-generation", model="FreedomIntelligence/HuatuoGPT-Vision-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/HuatuoGPT-Vision-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FreedomIntelligence/HuatuoGPT-Vision-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/HuatuoGPT-Vision-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/HuatuoGPT-Vision-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/HuatuoGPT-Vision-7B

SGLang

How to use FreedomIntelligence/HuatuoGPT-Vision-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 "FreedomIntelligence/HuatuoGPT-Vision-7B" \
    --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": "FreedomIntelligence/HuatuoGPT-Vision-7B",
		"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 "FreedomIntelligence/HuatuoGPT-Vision-7B" \
        --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": "FreedomIntelligence/HuatuoGPT-Vision-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FreedomIntelligence/HuatuoGPT-Vision-7B with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/HuatuoGPT-Vision-7B
```

HuatuoGPT-Vision-7B / README.md

jymcc

Update README.md

34dfcdb verified about 2 years ago

preview code

Raw

History Blame Contribute Delete

1.76 kB

metadata

license: apache-2.0
datasets:
  - FreedomIntelligence/PubMedVision
language:
  - en
  - zh
pipeline_tag: text-generation

HuatuoGPT-Vision-7B

GitHub | Paper

Introduction

HuatuoGPT-Vision is a multimodal LLM for medical applications, built with the PubMedVision dataset. HuatuoGPT-Vision-7B is trained based on Qwen2-7B using the LLaVA-v1.5 architecture.

Quick Start

Get the model inference code from Github.

git clone https://github.com/FreedomIntelligence/HuatuoGPT-Vision.git

Model inference

query = 'What does the picture show?'
image_paths = ['image_path1']

from cli import HuatuoChatbot
bot = HuatuoChatbot(huatuogpt_vision_model_path) # loads the model 
output = bot.inference(query, image_paths) # generates
print(output)  # Prints the model output

Citation

@misc{chen2024huatuogptvisioninjectingmedicalvisual,
      title={HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale}, 
      author={Junying Chen and Ruyi Ouyang and Anningzhe Gao and Shunian Chen and Guiming Hardy Chen and Xidong Wang and Ruifei Zhang and Zhenyang Cai and Ke Ji and Guangjun Yu and Xiang Wan and Benyou Wang},
      year={2024},
      eprint={2406.19280},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2406.19280}, 
}