juvi21/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B
Full fine-tune vs NousResearch/Hermes-2-Theta-Llama-3-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 158/161, MLP 240/240, Attention 320/320, lm_head 1/1