PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0
Full fine-tune vs Yhyu13/LMCocktail-10.7B-v1. Fine-tune: 98% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 141/144, Attention 188/192, lm_head 1/1
Full fine-tune vs Yhyu13/LMCocktail-10.7B-v1. Fine-tune: 98% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 141/144, Attention 188/192, lm_head 1/1