SmolVLA
Hugging FaceSmolVLA goes through a pretraining phase on general manipulation data, followed by task-specific post-training.
specific method · filed under post-training
Post-trains a model to execute a desired downstream task, with task specialization distinguishing it from broad-domain post-training.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See post-training for the methods filed beside it.
Also called post-training phase.
2 quotes from 2 sources, one card per model, each opening with its strongest.
SmolVLA goes through a pretraining phase on general manipulation data, followed by task-specific post-training.
the goal of the post-training phase is to provide the model with the ability to skillfully and fluently execute the desired downstream task.