nvidia/DeepSeek-R1-0528-NVFP4
Different architecture vs deepseek-ai/DeepSeek-R1-0528. Different architecture: only 1456 of 91991/180488 tensors match by name and shape.
Different architecture vs deepseek-ai/DeepSeek-R1-0528. Different architecture: only 1456 of 91991/180488 tensors match by name and shape.