nvidia/GR00T-H-N1.7
Partial fine-tune vs nvidia/GR00T-N1.7-3B. Partial change: 81% of the weights changed (attention, embeddings, mlp, norms, other), in 24 of 24 layers.
Tensors changed: Embeddings 6/9, Attention 416/416, other 147/148, Norms 232/233, lm_head 0/1, MLP 160/160