Instructions to use adept/fuyu-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use adept/fuyu-8b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="adept/fuyu-8b")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("adept/fuyu-8b") model = AutoModelForImageTextToText.from_pretrained("adept/fuyu-8b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use adept/fuyu-8b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "adept/fuyu-8b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "adept/fuyu-8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/adept/fuyu-8b
- SGLang
How to use adept/fuyu-8b 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 "adept/fuyu-8b" \ --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": "adept/fuyu-8b", "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 "adept/fuyu-8b" \ --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": "adept/fuyu-8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use adept/fuyu-8b with Docker Model Runner:
docker model run hf.co/adept/fuyu-8b
The Numbers
#33
by changgeli - opened
+1
Also if the numbers are the result of the released base model, what prompts did you use exactly for each of those datasets?
From https://huggingface.co/adept/fuyu-8b/discussions/28#6544b662f0d77ba425f100d0 I assume for VQAv2 you added "Answer the following VQAv2 question based on the image: " as prefix. What about the rest? How were the multiple choice questions composed for AI2D?
