Theros/Q2.5-ColdBrew-R1-Obsidian
Partial fine-tune vs Theros/Qwen2.5-ColdBrew-R1. Partial change: 61% of the weights changed (attention, mlp, norms), in 20 of 28 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 40/57, MLP 60/84, Attention 140/196
2 derivatives checked
- mradermacher/Q2.5-ColdBrew-R1-Obsidian-i1-GGUF: Quantization
- mradermacher/Q2.5-ColdBrew-R1-Obsidian-GGUF: Same weights, converted