HuggingFaceTB
/

SmolVLM2-500M-Video-Instruct

Image-Text-to-Text

Model card Files Files and versions

Resources

View closed (13)

How to get infernece on video stream

#18 opened 30 days ago by

Set correct pipeline tag, add link to paper

#17 opened 3 months ago by

Is the padding side=right intended?

#16 opened 3 months ago by

Onnx inference code

#14 opened 4 months ago by

ValueError: The checkpoint you are trying to load has model type `smolvlm` but Transformers does not recognize this architecture.

#13 opened 4 months ago by