OPTML-Group/SimNPO-WMDP-zephyr-7b-beta
Full fine-tune vs HuggingFaceH4/zephyr-7b-beta. Fine-tune: 98% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 16/65, MLP 96/96, Attention 128/128, lm_head 1/1
Full fine-tune vs HuggingFaceH4/zephyr-7b-beta. Fine-tune: 98% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 16/65, MLP 96/96, Attention 128/128, lm_head 1/1