grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B
Full fine-tune vs core-3/kuno-royale-v2-7b. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 96/96, Attention 128/128, Norms 65/65, Embeddings 1/1, lm_head 1/1
Full fine-tune vs core-3/kuno-royale-v2-7b. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 96/96, Attention 128/128, Norms 65/65, Embeddings 1/1, lm_head 1/1