ilsp/Llama-Krikri-8B-Instruct-v1.5
Full fine-tune vs ilsp/Llama-Krikri-8B-Base. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 49/65, MLP 96/96, Attention 128/128, lm_head 1/1
Full fine-tune vs ilsp/Llama-Krikri-8B-Base. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 49/65, MLP 96/96, Attention 128/128, lm_head 1/1