[Feature] Add support for SmolVLM multimodal models
Open
- Dominant language
- Python
- Stars
- 8.1k
- Forks
- 748
- Avg merge
- 6d 2h
- Merged PRs (30d)
- 54
Description
### Motivation
The SmolVLM family of models appear to be quite impressive in terms of size/performance tradeoff. Please consider adding support, thanks!
### Related resources
[Blog post](https://huggingface.co/blog/smolervlm)
[Huggingface page](https://huggingface.co/collections/HuggingFaceTB/smolvlm-256m-and-500m-6791fafc5bb0ab8acc960fb0)
### Additional context
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.