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
ValueError: Unable to infer channel dimension format
#26
by vishal1278 - opened
I am able to successfully run the code that are provided as examples (in the Model card section) using bus.png and chart.png images. However, whenever I try to run it on any other images, I get the following error message:
Loading checkpoint shards: 100%|βββββββββββββββββββββββββββββββββββββ| 2/2 [00:07<00:00, 3.88s/it]
Traceback (most recent call last):
File "/home/vishal/code/fuyu/test_2.py", line 14, in <module>
model_inputs = processor(text_prompt, images=[image_pil], device="cuda:0")
File "/home/vishal/code/fuyu/.venv/lib/python3.10/site-packages/transformers/models/fuyu/processing_fuyu.py", line 464, in __call__
batch_images, image_unpadded_heights, image_unpadded_widths = self._process_images(images)
File "/home/vishal/code/fuyu/.venv/lib/python3.10/site-packages/transformers/models/fuyu/processing_fuyu.py", line 399, in _process_images
channel_dimension = in

fer_channel_dimension_format(image, 3)
File "/home/vishal/code/fuyu/.venv/lib/python3.10/site-packages/transformers/image_utils.py", line 189, in infer_channel_dimension_format
raise ValueError("Unable to infer channel dimension format")
ValueError: Unable to infer channel dimension format
I have attached one image that I have been trying to ask questions about using this model.
image = Image.open(image_path).convert("RGB") should fix this
I met the same question too, maybe png format like rgba image have not yet accept.
This comment has been hidden