divinetribe/Nemotron-3-Nano-Omni-30B-Abliterated-MM-bf16

Partial fine-tune vs mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-bf16. Partial change: 47% of the weights changed (attention, embeddings, mlp, other), in 52 of 52 layers.

Tensors changed: Embeddings 1/4, other 23/294, Norms 0/543, MLP 46/319, Attention 6/320, lm_head 0/1

1 derivatives checked