eth-nlped/Eduardo-27b

Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 94% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 123/319, Attention 354/556, MLP 192/304, Embeddings 0/4, lm_head 1/1

2 derivatives checked