m3rg-iitd/llamat-3-chat
Full fine-tune vs m3rg-iitd/llamat-3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
Full fine-tune vs m3rg-iitd/llamat-3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128