BenevolenceMessiah/Qwen2.5-72B-Instruct-abliterated-2x-TIES-v1.0
Full fine-tune vs abacusai/Dracarys2-72B-Instruct. Fine-tune: 92% of the weights changed, across 80 of 80 layers.
Tensors changed: Norms 51/161, MLP 220/240, Attention 467/560
Full fine-tune vs abacusai/Dracarys2-72B-Instruct. Fine-tune: 92% of the weights changed, across 80 of 80 layers.
Tensors changed: Norms 51/161, MLP 220/240, Attention 467/560