Smolvlm2 2.2B Instruct

🚀 SmolVLM2 2.2B

SmolVLM2-2.2B is a lightweight multimodal model crafted for video content analysis. It processes videos, images, and text inputs to generate text outputs, such as answering media - related questions, comparing visual content, or transcribing text from images. Despite its small size, only requiring 5.2GB of GPU RAM for video inference, it offers robust performance on complex multimodal tasks. This efficiency makes it ideal for on - device applications with limited computational resources.

✨ Features

• Multimodal Processing: Capable of handling images, multi - images, videos, and text inputs to generate text outputs.
• Lightweight: Only needs 5.2GB of GPU RAM for video inference, suitable for on - device applications.
• Robust Performance: Delivers strong performance on complex multimodal tasks.

📦 Installation

The original document does not provide specific installation steps, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import AutoProcessor, AutoModelForImageTextToText
import torch

model_path = "HuggingFaceTB/SmolVLM2-2.2B-Instruct"
processor = AutoProcessor.from_pretrained(model_path)
model = AutoModelForImageTextToText.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    _attn_implementation="flash_attention_2"
).to("cuda")

Advanced Usage

Simple Inference

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
            {"type": "text", "text": "Can you describe this image?"},
        ]
    },
]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device, dtype=torch.bfloat16)

generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
generated_texts = processor.batch_decode(
    generated_ids,
    skip_special_tokens=True,
)
print(generated_texts[0])

Video Inference

messages = [
    {
        "role": "user",
        "content": [
            {"type": "video", "path": "path_to_video.mp4"},
            {"type": "text", "text": "Describe this video in detail"}
        ]
    },
]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device, dtype=torch.bfloat16)

generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
generated_texts = processor.batch_decode(
    generated_ids,
    skip_special_tokens=True,
)

print(generated_texts[0])

Multi - image Interleaved Inference

import torch


messages = [
    {
        "role": "user",
        "content": [
          {"type": "text", "text": "What is the similarity between these two images?"},
          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"},            
        ]
    },
]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device, dtype=torch.bfloat16)

generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
generated_texts = processor.batch_decode(
    generated_ids,
    skip_special_tokens=True,
)
print(generated_texts[0])

📚 Documentation

Model Summary

Resources

• Demo: Video Highlight Generator
• Blog: Blog post

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.

Evaluation

Vision Evaluation

Video Evaluation

Model optimizations

The original document does not provide specific content about model optimizations, so this section is skipped.

Misuse and Out - of - scope Use

⚠️ Important Note

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:

• Prohibited Uses:
  • Evaluating or scoring individuals (e.g., in employment, education, credit)
  • Critical automated decision - making
  • Generating unreliable factual content
• Malicious Activities:
  • Spam generation
  • Disinformation campaigns
  • Harassment or abuse
  • Unauthorized surveillance

License

SmolVLM2 is built upon the shape - optimized SigLIP as image encoder and SmolLM2 for text decoder part.

We release the SmolVLM2 checkpoints under the Apache 2.0 license.

Citation information

You can cite us in the following way:

@article{marafioti2025smolvlm,
  title={SmolVLM: Redefining small and efficient multimodal models}, 
  author={Andrés Marafioti and Orr Zohar and Miquel Farré and Merve Noyan and Elie Bakouch and Pedro Cuenca and Cyril Zakka and Loubna Ben Allal and Anton Lozhkov and Nouamane Tazi and Vaibhav Srivastav and Joshua Lochner and Hugo Larcher and Mathieu Morlon and Lewis Tunstall and Leandro von Werra and Thomas Wolf},
  journal={arXiv preprint arXiv:2504.05299},
  year={2025}
}

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.

Data Split per modality

Granular dataset slices per modality

Text Datasets

Multi - image Datasets

Image Datasets

Video Datasets