mradermacher/Mordant-3B-Think-GGUF
Same weights, converted vs Kezmark/Mordant-3B-Think. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160
Same weights, converted vs Kezmark/Mordant-3B-Think. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160