Instructions to use brainworkup/granite-vision-4.1-4b-oQ8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brainworkup/granite-vision-4.1-4b-oQ8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="brainworkup/granite-vision-4.1-4b-oQ8", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("brainworkup/granite-vision-4.1-4b-oQ8", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("brainworkup/granite-vision-4.1-4b-oQ8", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use brainworkup/granite-vision-4.1-4b-oQ8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brainworkup/granite-vision-4.1-4b-oQ8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brainworkup/granite-vision-4.1-4b-oQ8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/brainworkup/granite-vision-4.1-4b-oQ8

SGLang

How to use brainworkup/granite-vision-4.1-4b-oQ8 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 "brainworkup/granite-vision-4.1-4b-oQ8" \
    --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": "brainworkup/granite-vision-4.1-4b-oQ8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "brainworkup/granite-vision-4.1-4b-oQ8" \
        --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": "brainworkup/granite-vision-4.1-4b-oQ8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use brainworkup/granite-vision-4.1-4b-oQ8 with Docker Model Runner:
```
docker model run hf.co/brainworkup/granite-vision-4.1-4b-oQ8
```

granite-vision-4.1-4b-oQ8 / processing.py

brainworkup

Upload granite-vision-4.1-4b-oQ8 via oMLX

cf6dc1c verified about 1 month ago

Raw

History Blame Contribute Delete

2.35 kB

	from fractions import Fraction

	from transformers import LlavaNextProcessor
	from transformers.image_processing_utils import select_best_resolution



	class Granite4VisionProcessor(LlavaNextProcessor):
	model_type = "granite4_vision"

	def __init__(
	self,
	image_processor=None,
	tokenizer=None,
	patch_size=None,
	vision_feature_select_strategy=None,
	chat_template=None,
	image_token="<image>", # set the default and let users change if they have peculiar special tokens in rare cases
	num_additional_image_tokens=0,
	downsample_rate=None,
	**kwargs,
	):
	super().__init__(image_processor=image_processor,
	tokenizer=tokenizer,
	patch_size=patch_size,
	vision_feature_select_strategy=vision_feature_select_strategy,
	chat_template=chat_template,
	image_token=image_token,
	num_additional_image_tokens=num_additional_image_tokens,
	)
	self.downsample_rate = downsample_rate

	def _get_number_of_features(self, orig_height: int, orig_width: int, height: int, width: int) -> int:
	image_grid_pinpoints = self.image_processor.image_grid_pinpoints

	height_best_resolution, width_best_resolution = select_best_resolution(
	[orig_height, orig_width], image_grid_pinpoints
	)
	scale_height, scale_width = height_best_resolution // height, width_best_resolution // width

	patches_height = height // self.patch_size
	patches_width = width // self.patch_size
	if self.downsample_rate is not None:
	ds_rate = Fraction(self.downsample_rate)
	patches_height = int(patches_height * ds_rate)
	patches_width = int(patches_width * ds_rate)

	unpadded_features, newline_features = self._get_unpadded_features(
	orig_height, orig_width, patches_height, patches_width, scale_height, scale_width
	)
	# The base patch covers the entire image (+1 for the CLS)
	base_features = patches_height * patches_width + self.num_additional_image_tokens
	num_image_tokens = unpadded_features + newline_features + base_features
	return num_image_tokens