yamatazen/Shisa-v2-Mistral-Nemo-12B-Abliterated
Full fine-tune vs natong19/Mistral-Nemo-Instruct-2407-abliterated. Fine-tune: 97% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 19/81, MLP 116/120, Attention 157/160, lm_head 1/1