amd/DeepSeek-R1-0528-MXFP4
Different architecture vs deepseek-ai/DeepSeek-R1-0528. Different architecture: only 1456 of 91991/90910 tensors match by name and shape.
Different architecture vs deepseek-ai/DeepSeek-R1-0528. Different architecture: only 1456 of 91991/90910 tensors match by name and shape.