Instructions to use soyrsoyr/granite-vision-4.1-0.2B-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use soyrsoyr/granite-vision-4.1-0.2B-tiny with Transformers:

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

pipe = pipeline("image-text-to-text", model="soyrsoyr/granite-vision-4.1-0.2B-tiny", 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("soyrsoyr/granite-vision-4.1-0.2B-tiny", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("soyrsoyr/granite-vision-4.1-0.2B-tiny", trust_remote_code=True, device_map="auto")
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 soyrsoyr/granite-vision-4.1-0.2B-tiny with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "soyrsoyr/granite-vision-4.1-0.2B-tiny"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "soyrsoyr/granite-vision-4.1-0.2B-tiny",
		"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/soyrsoyr/granite-vision-4.1-0.2B-tiny

SGLang

How to use soyrsoyr/granite-vision-4.1-0.2B-tiny 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 "soyrsoyr/granite-vision-4.1-0.2B-tiny" \
    --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": "soyrsoyr/granite-vision-4.1-0.2B-tiny",
		"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 "soyrsoyr/granite-vision-4.1-0.2B-tiny" \
        --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": "soyrsoyr/granite-vision-4.1-0.2B-tiny",
		"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 soyrsoyr/granite-vision-4.1-0.2B-tiny with Docker Model Runner:
```
docker model run hf.co/soyrsoyr/granite-vision-4.1-0.2B-tiny
```

This is a tiny version of ibm-granite/granite-vision-4.1-4b created for testing and development.

Intended Use

A small, fast stand-in for the granite4_vision architecture, useful for:

Inference / CI testing where a real 4B checkpoint is too large to download or run
Quantization & compression pipeline smoke tests (llm-compressor, compressed-tensors)
Offloaded / distributed loading tests (see below)
Exercising the vLLM Granite4VisionForConditionalGeneration model path, including the SigLIP vision tower + deepstack projectors

Weights are random (then briefly fine-tuned on a toy corpus), so generations are not meaningful — this model is for plumbing, not output quality.

Model Details

Base Model: ibm-granite/granite-vision-4.1-4b
Architecture: granite4_vision (Granite4VisionForConditionalGeneration)
Total Parameters: 0.162B
Activated Parameters: 0.162B

Configuration Changes

The following parameters were reduced from the original model:

Parameter	Original	Tiny
text_config.num_hidden_layers	40	4
text_config.hidden_size	2560	1024
text_config.intermediate_size	8192	2048
text_config.num_attention_heads	40	8
text_config.num_key_value_heads	8	2
vision_config.num_hidden_layers	27	4
vision_config.hidden_size	1152	384
vision_config.intermediate_size	4304	768
vision_config.num_attention_heads	16	4
spatial_target_layers	[12, 15, 18, 21]	[0, 1, 2, 3]
deepstack_layer_map	[(-19,9),(-13,6),(-7,3),(-1,0)]	[(-4,3),(-3,2),(-2,1),(-1,0)]

The full 100,352-token vocabulary is retained.

Checkpoint Structure

Single safetensors file (model.safetensors). Key naming matches the original checkpoint format (model.language_model.*, model.vision_tower.vision_model.* (SigLIP), model.layerwise_projectors.*, model.spatial_projectors.*, model.image_newline). Module-path structure was verified equal to the base checkpoint's safetensors header.

Usage

from transformers import AutoModelForImageTextToText, AutoProcessor

model = AutoModelForImageTextToText.from_pretrained(
    "soyrsoyr/granite-vision-4.1-0.2B-tiny", device_map="auto"
)
processor = AutoProcessor.from_pretrained("soyrsoyr/granite-vision-4.1-0.2B-tiny")

input_ids = processor.tokenizer("According to all known laws", return_tensors="pt").input_ids.to(model.device)
output = model.generate(input_ids, max_new_tokens=20)
print(processor.tokenizer.decode(output[0]))

Offloaded / distributed loading (compressed-tensors)

This is a multimodal ...ForConditionalGeneration model, so AutoModelForCausalLM does not resolve it. Pass AutoModelForImageTextToText to load_offloaded_model — the class you pass must match the class you call, since that is where device_map="auto_offload" support is injected:

from transformers import AutoModelForImageTextToText
from compressed_tensors.offload import load_offloaded_model
from compressed_tensors.distributed import init_dist

init_dist()
with load_offloaded_model(model_class=AutoModelForImageTextToText):
    model = AutoModelForImageTextToText.from_pretrained(
        "soyrsoyr/granite-vision-4.1-0.2B-tiny",
        device_map="auto_offload",                 # weights on CPU/disk, GPU for activations
    )

Creation Process

This model was created using the llm-compressor create-tiny-model claude skill.

Config inspected via inspect_config.py
Tiny model created via a modified save_tiny_model.py, adapted for the multimodal class (AutoModelForImageTextToText.from_config); the text tower and SigLIP vision tower were shrunk and any all-zero / non-finite / extreme param was fixed after init_weights()
Fine-tuned on the copypasta dataset; reached training perplexity 1.36 (target: ≤3.0) at lr=5e-4 (CPU, Adafactor)
Checkpoint structure validated against the original HuggingFace safetensors header (module-path match)
Inference validated via validate_tiny_model.py

Notes

Layer-index-sensitive fields remapped. spatial_target_layers and deepstack_layer_map reference specific vision/text layer indices; they were remapped to the reduced depths so they stay valid at 4 vision / 4 text layers.
Vision tower key nesting. Current transformers flattens SiglipVisionModel on save (model.vision_tower.*), but the published checkpoint and vLLM's loader expect the nested model.vision_tower.vision_model.* layout. A conversion step restores the nesting so the checkpoint loads cleanly in both transformers (via SiglipVisionModel.base_model_prefix) and vLLM.
tie_word_embeddings=True: lm_head shares embed_tokens and is not stored as a separate tensor.