mradermacher/Q2.5-ColdBrew-R1-Obsidian-GGUF
Same weights, converted vs Theros/Q2.5-ColdBrew-R1-Obsidian. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/71, MLP 0/105, Attention 0/245
Same weights, converted vs Theros/Q2.5-ColdBrew-R1-Obsidian. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/71, MLP 0/105, Attention 0/245