Saxo/Linkbricks-Horizon-AI-Korean-Mixtral-sft-dpo-8x7b

Full fine-tune vs NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO. Fine-tune: 99% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, MLP 768/768, other 32/32, Norms 0/65, Attention 128/128, lm_head 0/1

On the Hub · Downloads on Model Pulse