darkc0de/RICO

Partial fine-tune vs Qwen/Qwen3.8-27B. Partial change: 78% of the weights changed (attention, embeddings, mlp), in 64 of 64 layers.

Tensors changed: Norms 0/325, Attention 113/560, MLP 193/307, Embeddings 1/5, lm_head 0/1, other 0/1

4 derivatives checked