Saxo/Linkbricks-Horizon-AI-Nous-Hermes-3-Llama3.1-Korean-cpt-8b
Full fine-tune vs NousResearch/Hermes-3-Llama-3.1-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1