RabotniKuma/Fast-OpenMath-Nemotron-14B

Partial fine-tune vs nvidia/OpenMath-Nemotron-14B. Partial change: 89% of the weights changed (attention, mlp, norms), in 48 of 48 layers.

Tensors changed: Embeddings 0/1, Norms 92/97, MLP 144/144, Attention 336/336, lm_head 0/1

2 derivatives checked