bunnycore/Replete-Qwen-2.5-3b-CoT-RP

Full fine-tune vs bunnycore/Qwen-2.5-3b-RP. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 6/73, MLP 108/108, Attention 151/252

2 derivatives checked