AEON-7/Nemotron-3-Nano-Omni-AEON-Ultimate-Uncensored-BF16

Partial fine-tune vs nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16. Partial change: 44% of the weights changed (attention, embeddings, lm_head, mlp, other), in 52 of 52 layers.

Tensors changed: Norms 0/567, Embeddings 1/4, other 23/296, MLP 772/1812, Attention 6/320, lm_head 1/1

4 derivatives checked