Instructions to use HuggingFaceTB/SmolVLM-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolVLM-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="HuggingFaceTB/SmolVLM-Instruct")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("HuggingFaceTB/SmolVLM-Instruct", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceTB/SmolVLM-Instruct with vLLM:

Install from pip and serve model

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

SGLang

How to use HuggingFaceTB/SmolVLM-Instruct 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 "HuggingFaceTB/SmolVLM-Instruct" \
    --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": "HuggingFaceTB/SmolVLM-Instruct",
		"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 "HuggingFaceTB/SmolVLM-Instruct" \
        --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": "HuggingFaceTB/SmolVLM-Instruct",
		"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 HuggingFaceTB/SmolVLM-Instruct with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolVLM-Instruct
```

mfarre commited on Nov 26, 2024

Commit

78b5928

verified ·

1 Parent(s): 16aea32

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -7

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ SmolVLM is a compact open multimodal model that accepts arbitrary sequences of i
 - **Model type:** Multi-modal model (image+text)
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
-- **Architecture:** Based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) (see more details below)
 ## Resources
@@ -160,15 +160,19 @@ We release the SmolVLM checkpoints under the Apache 2.0 license.
 ### Training Data
-![Data mixture](mixture_the_cauldron.png)
-The training data is: ![Training data](smolvlm-data.pdf)
-#### Speeds, Sizes, Times [optional]
-TODO
 ## Evaluation
-TODO

 - **Model type:** Multi-modal model (image+text)
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
+- **Architecture:** Based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) (see technical summary)
 ## Resources
 ### Training Data
+The training data comes from [The Cauldron](https://huggingface.co/datasets/HuggingFaceM4/the_cauldron) and [Docmatix](https://huggingface.co/datasets/HuggingFaceM4/Docmatix) datasets, with emphasis on document understanding (25%) and image captioning (18%), while maintaining balanced coverage across other crucial capabilities like visual reasoning, chart comprehension, and general instruction following.<img src="https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct/resolve/main/mixture_the_cauldron.png" alt="Example Image" style="width:70%;" />
 ## Evaluation
+| Model             | MMMU (val) | MathVista (testmini) | MMStar (val) | DocVQA (test) | TextVQA (val) | Min GPU RAM required (GB) |
+|-------------------|------------|----------------------|--------------|---------------|---------------|---------------------------|
+| SmolVLM           | 38.8       | 44.6                | 42.1         | 81.6          | 72.7          | 5.02                      |
+| Qwen-VL 2B        | 41.1       | 47.8                | 47.5         | 90.1          | 79.7          | 13.70                     |
+| InternVL2 2B      | 34.3       | 46.3                | 49.8         | 86.9          | 73.4          | 10.52                     |
+| PaliGemma 3B 448px| 34.9       | 28.7                | 48.3         | 32.2          | 56.0          | 6.72                      |
+| moondream2        | 32.4       | 24.3                | 40.3         | 70.5          | 65.2          | 3.87                      |
+| MiniCPM-V-2       | 38.2       | 39.8                | 39.1         | 71.9          | 74.1          | 7.88                      |
+| MM1.5 1B          | 35.8       | 37.2                | 0.0          | 81.0          | 72.5          | NaN                       |