HAD653/qwen3-1.7b-magistral-math-gguf
Same weights, converted vs HAD653/qwen3-1.7b-magistral-math. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112
Same weights, converted vs HAD653/qwen3-1.7b-magistral-math. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112