nvidia/DeepSeek-V3-0324-NVFP4
Different architecture vs deepseek-ai/DeepSeek-V3-0324. Different architecture: only 1456 of 91991/180364 tensors match by name and shape.
1 other repos hold byte-for-byte identical weight files.
Different architecture vs deepseek-ai/DeepSeek-V3-0324. Different architecture: only 1456 of 91991/180364 tensors match by name and shape.
1 other repos hold byte-for-byte identical weight files.