SirSahOl/Qwen3-1.7B-Base-chat-mlx-16bit
Same weights, repacked vs Qwen/Qwen3-1.7B-Base. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112
Same weights, repacked vs Qwen/Qwen3-1.7B-Base. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112