kd13/Coder-o1-mini-reasoning
Full fine-tune vs Qwen/Qwen2.5-Coder-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 42/57, MLP 84/84, Attention 196/196
2 derivatives checked
- kd13/Coder-o1-mini-reasoning-GGUF: Quantization
- mradermacher/Coder-o1-mini-GGUF: Same weights, converted