SmolVLA
Hugging Facereduce its hidden size to 75% of the VLM’s, keeping the model lightweight for deployment.
1 more from this model
To improve on inference’s efficiency, we use a reduced hidden size
implementation detail · filed under model architecture
Uses a smaller hidden size for the action expert to reduce computational cost.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See multimodal architecture for the methods filed beside it.
Also called reduce its hidden size to 75% of the VLM’s, Reduced hidden size for the action expert, reduced hidden size.
2 quotes from 2 sources, one card per model, each opening with its strongest.
reduce its hidden size to 75% of the VLM’s, keeping the model lightweight for deployment.
To improve on inference’s efficiency, we use a reduced hidden size