amd/DeepSeek-R1-MXFP4
Different architecture vs deepseek-ai/DeepSeek-R1. Different architecture: only 1151 of 91991/91215 tensors match by name and shape.
Different architecture vs deepseek-ai/DeepSeek-R1. Different architecture: only 1151 of 91991/91215 tensors match by name and shape.