lerobot/smolvla_libero

Partial fine-tune vs lerobot/smolvla_base. Partial change: 77% of the weights changed (attention, embeddings, mlp, norms, other), in 16 of 16 layers.

Tensors changed: other 7/7, MLP 145/148, Attention 222/224, Norms 44/116, lm_head 0/1, Embeddings 3/4

On the Hub · Downloads on Model Pulse