nvidia/DeepSeek-R1-NVFP4
Different architecture vs deepseek-ai/DeepSeek-R1. Different architecture: only 1456 of 91991/180364 tensors match by name and shape.
Different architecture vs deepseek-ai/DeepSeek-R1. Different architecture: only 1456 of 91991/180364 tensors match by name and shape.