westlake-repl/Evolla-10B-hf
Full fine-tune (fewer layers) vs meta-llama/Llama-3.1-8B-Instruct. meta-llama/Llama-3.1-8B-Instruct matches part of westlake-repl/Evolla-10B-hf (291 of its 1047 tensors; the rest of westlake-repl/Evolla-10B-hf has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1