openwalrus/Qwen3-1.7B
Same weights, converted vs Qwen/Qwen3-1.7B. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112
Same weights, converted vs Qwen/Qwen3-1.7B. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112