jmichaelov/parc-mamba-seed2
Full fine-tune vs state-spaces/mamba-130m-hf. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: other 216/216, Norms 25/25
Full fine-tune vs state-spaces/mamba-130m-hf. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: other 216/216, Norms 25/25