---
library_name: transformers
license: apache-2.0
datasets:
- HuggingFaceM4/the_cauldron
- HuggingFaceM4/Docmatix
pipeline_tag: video-text-to-text
language:
- en
base_model:
- HuggingFaceTB/SmolLM2-360M-Instruct
- google/siglip-base-patch16-512
- HuggingFaceTB/SmolVLM-500M-Instruct
---
# SmolVLM2-500M-Video
SmolVLM2-500M-Video is a tiny video model, member of the SmolVLM family. It accepts video, arbitrary sequences of image and text inputs to produce text outputs. It's designed for efficiency. SmolVLM2 is optimized for video but can answer questions about images, describe visual content, or transcribe text. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks. It can run inference on a video with 1.8GB of GPU RAM.
## Model Summary
- **Developed by:** Hugging Face 🤗
- **Model type:** Multi-modal model (video+text)
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Architecture:** Based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) (see technical summary)
## 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).
## Evaluation
We evaluated the performance of the SmolVLM2 family on the following scientific benchmarks:
| Size | Video-MME | MLVU | MVBench |
|----------|-----------------|----------|---------------|
| 2.2B | 52.1 | 55.2 | 46.27 |
| 500M | 42.2 | 47.3 | 39.73 |
| 256M | 33.7 | 40.6 | 32.7 |
### How to get started
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:
- 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 [SigLIP](https://huggingface.co/google/siglip-base-patch16-512) as image encoder and [SmolLM2](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) for text decoder part.
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](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.
### Details
