HuggingFaceTB
/

SmolVLM2-2.2B-Instruct

Image-Text-to-Text

video-text-to-text

Model card Files Files and versions

Resources

View closed (11)

Create Ansu

#22 opened 7 days ago by

Use `attn_implementation` instead of `_attn_implementation`

#21 opened 10 days ago by

Add link to paper in description

#20 opened 15 days ago by

"ImportError: Package `num2words` is required to run SmolVLM processor" getting this issue wwhile importing SmolVLM2 from AutoProcessor

#18 opened about 1 month ago by

aryachakraborty

Inference endpoint not working

#17 opened about 2 months ago by

Ollama Availability

#16 opened about 2 months ago by

🏁Complete Model Optimization Section

#15 opened about 2 months ago by

Several questions on the same video

#8 opened 2 months ago by

checkpoint you are trying to load has model type `smolvlm` but Transformers does not recognize this

#7 opened 2 months ago by

Input Video length constraints

#6 opened 2 months ago by

Using pre-computed embeddings for images/frames and using as input

#2 opened 2 months ago by