Layer 5 attention chimaera. Early-layer FFN transplanted via GRC basis alignment from donor layer 15. 105% PPL recovery — grafted model outperforms original on simple sentences. The FFN from a deep reasoning layer now processes at an early attention layer, creating a unique 'deep insight at shallow depth' effect.
Perplexity testing confirms the graft transfers functional structure without destroying the model.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained("NagusameCS/minSøde", trust_remote_code=True)
4tokenizer = AutoTokenizer.from_pretrained("NagusameCS/minSøde")
