amd/DeepSeek-R1-0528-MXFP4-MTP-MoEFP4
Different architecture vs deepseek-ai/DeepSeek-R1-0528. Different architecture: only 685 of 91991/91991 tensors match by name and shape.
Different architecture vs deepseek-ai/DeepSeek-R1-0528. Different architecture: only 685 of 91991/91991 tensors match by name and shape.