nitky/Llama-3.3-SuperSwallowX-70B-Instruct-v0.1
Full fine-tune vs AXCXEPT/Llama-3.1-70B-EZO-1.1-it. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1