jpacifico/Chocolatine-2-merged-qwen25arch

Full fine-tune vs arcee-ai/Virtuoso-Small-v2. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336, lm_head 1/1

2 derivatives checked