xiuyul/mamba-2.8b-zephyr
Full fine-tune vs xiuyul/mamba-2.8b-ultrachat. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, other 472/576, Norms 10/65
Full fine-tune vs xiuyul/mamba-2.8b-ultrachat. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, other 472/576, Norms 10/65