bharatgenai/AyurParam
Full fine-tune vs bharatgenai/Param-1-2.9B-Instruct. 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 bharatgenai/Param-1-2.9B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128