Smolvlm2 500M Video Instruct

🚀 SmolVLM2-500M-Video

SmolVLM2-500M-Video is a lightweight multimodal model crafted for video content analysis. It can process 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 1.8GB of GPU RAM for video inference, it offers strong performance in complex multimodal tasks. This makes it ideal for on - device applications with limited computational resources.

✨ Features

• Analyze video, image, and text inputs to generate text outputs.
• Deliver robust performance on complex multimodal tasks with low GPU RAM requirements.
• Well - suited for on - device applications.

📦 Installation

To use SmolVLM for inference and fine - tuning, ensure you have num2words, flash - attn, and the latest transformers installed. You can load the model as follows:

from transformers import AutoProcessor, AutoModelForImageTextToText
import torch

model_path = "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
processor = AutoProcessor.from_pretrained(model_path)
model = AutoModelForImageTextToText.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    _attn_implementation="flash_attention_2"
).to("cuda")

💻 Usage Examples

Basic Usage

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])

Advanced Usage - Video Inference

To use SmolVLM2 for video inference, make sure you have decord installed.

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])

Advanced Usage - Multi - image Interleaved Inference

You can interleave multiple media with text using chat templates.

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

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:

• 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.

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

🔧 Technical Details

SmolVLM2 is built upon SigLIP as image encoder and SmolLM2 for text decoder part.

📄 License

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}
}