z-lab/Alpamayo-R1-10B

Partial fine-tune vs nvidia/Alpamayo-R1-10B. Partial change: 21% of the weights changed (attention, mlp, norms, other), in 36 of 36 layers.

Tensors changed: Embeddings 0/4, Norms 134/408, MLP 108/340, Attention 144/396, lm_head 0/1, other 9/17

1 derivatives checked