Polygl0t/Tucano2-qwen-3.7B-Think
Full fine-tune vs Polygl0t/Tucano2-qwen-3.7B-Base. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 104/145, MLP 108/108, Attention 144/144
Full fine-tune vs Polygl0t/Tucano2-qwen-3.7B-Base. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 104/145, MLP 108/108, Attention 144/144