amd/Deepseek-S3_sq_a05_v2_mlperf6_1
Different architecture vs deepseek-ai/DeepSeek-R1. Different architecture: only 607 of 91991/90183 tensors match by name and shape.
Different architecture vs deepseek-ai/DeepSeek-R1. Different architecture: only 607 of 91991/90183 tensors match by name and shape.