CrystalReasoner/Qwen2.5-3B-CrysReas-Thinking
Full fine-tune vs Qwen/Qwen2.5-3B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 72/73, MLP 108/108, Attention 252/252
Full fine-tune vs Qwen/Qwen2.5-3B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 72/73, MLP 108/108, Attention 252/252