Instructions to use HuggingFaceTB/SmolVLM2-500M-Video-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolVLM2-500M-Video-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="HuggingFaceTB/SmolVLM2-500M-Video-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)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM2-500M-Video-Instruct")
model = AutoModelForImageTextToText.from_pretrained("HuggingFaceTB/SmolVLM2-500M-Video-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?"}
        ]
    },
]
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

vLLM

How to use HuggingFaceTB/SmolVLM2-500M-Video-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolVLM2-500M-Video-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/SmolVLM2-500M-Video-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/SmolVLM2-500M-Video-Instruct

SGLang

How to use HuggingFaceTB/SmolVLM2-500M-Video-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/SmolVLM2-500M-Video-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/SmolVLM2-500M-Video-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/SmolVLM2-500M-Video-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/SmolVLM2-500M-Video-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/SmolVLM2-500M-Video-Instruct with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct
```

Misc nits

by merve HF Staff - opened Feb 12, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-7

Files changed (1) hide show

README.md +5 -7

README.md CHANGED Viewed

@@ -30,11 +30,11 @@ SmolVLM2-500M-Video is a tiny video model, member of the SmolVLM family. It acce
 ## Resources
 - **Demo:** [Video Highlight Generator](https://huggingface.co/spaces/HuggingFaceTB/SmolVLM2-HighlightGenerator)
-- **Blog:** [Blog post](TODO)
 ## Uses
-SmolVLM2 can be used for inference on multimodal (video / image / text) tasks where the input comprises text queries along with video or one or more images. Text and media files can be interleaved arbitrarily, enabling tasks like captioning, visual question answering, and storytelling based on visual content. The model does not support image or video generation.
 To fine-tune SmolVLM2 on a specific task, you can follow [the fine-tuning tutorial](UPDATE).
@@ -53,13 +53,11 @@ We evaluated the performance of the SmolVLM2 family on the following scientific
 You can use transformers to load, infer and fine-tune SmolVLM.
 ### Model optimizations
 ## Misuse and Out-of-scope Use
 SmolVLM is not intended for high-stakes scenarios or critical decision-making processes that affect an individual's well-being or livelihood. The model may produce content that appears factual but may not be accurate. Misuse includes, but is not limited to:
@@ -82,11 +80,11 @@ We release the SmolVLM2 checkpoints under the Apache 2.0 license.
 ## Training Data
-SmolVLM2 used 3.3M samples for training originally from ten different datasets: : LlaVa Onevision, M4-Instruct, Mammoth, LlaVa Video 178K, FineVideo, VideoStar, VRipt, Vista-400K, MovieChat and ShareGPT4Video.
 In the following plots we give a general overview of the samples across modalities and the source of those samples.
 <center><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm2_data_split.png" width="auto" height="auto" alt="Image description">
 </center>
-### Detailed videw
 <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm2_datadetails.png" width="auto" height="auto" alt="Image description">

 ## Resources
 - **Demo:** [Video Highlight Generator](https://huggingface.co/spaces/HuggingFaceTB/SmolVLM2-HighlightGenerator)
+- **Blog:** [Blog post](https://huggingface.co/blog/smolvlm2)
 ## Uses
+SmolVLM2 can be used for inference on multimodal (video / image / text) tasks where the input consists of text queries along with video or one or more images. Text and media files can be interleaved arbitrarily, enabling tasks like captioning, visual question answering, and storytelling based on visual content. The model does not support image or video generation.
 To fine-tune SmolVLM2 on a specific task, you can follow [the fine-tuning tutorial](UPDATE).
 You can use transformers to load, infer and fine-tune SmolVLM.
+[TODO]
 ### Model optimizations
 ## Misuse and Out-of-scope Use
 SmolVLM is not intended for high-stakes scenarios or critical decision-making processes that affect an individual's well-being or livelihood. The model may produce content that appears factual but may not be accurate. Misuse includes, but is not limited to:
 ## Training Data
+SmolVLM2 used 3.3M samples for training originally from ten different datasets: [LlaVa Onevision](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data), [M4-Instruct](https://huggingface.co/datasets/lmms-lab/M4-Instruct-Data), [Mammoth](https://huggingface.co/datasets/MAmmoTH-VL/MAmmoTH-VL-Instruct-12M), [LlaVa Video 178K](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K), [FineVideo](https://huggingface.co/datasets/HuggingFaceFV/finevideo), [VideoStar](https://huggingface.co/datasets/orrzohar/Video-STaR), [VRipt](https://huggingface.co/datasets/Mutonix/Vript), [Vista-400K](https://huggingface.co/datasets/TIGER-Lab/VISTA-400K), [MovieChat](https://huggingface.co/datasets/Enxin/MovieChat-1K_train) and [ShareGPT4Video](https://huggingface.co/datasets/ShareGPT4Video/ShareGPT4Video).
 In the following plots we give a general overview of the samples across modalities and the source of those samples.
 <center><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm2_data_split.png" width="auto" height="auto" alt="Image description">
 </center>
+### Details
 <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm2_datadetails.png" width="auto" height="auto" alt="Image description">