jaredpalmer/kev-27b
Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 95% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 138/209, Attention 363/448, MLP 192/192, Embeddings 0/1
Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 95% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 138/209, Attention 363/448, MLP 192/192, Embeddings 0/1