yujiepan/hunyuan-moe-tiny-random
Different architecture vs tencent/Hunyuan-A13B-Instruct. Different architecture: only 0 of 6530/74 tensors match by name and shape.
1 other repos hold byte-for-byte identical weight files.
Different architecture vs tencent/Hunyuan-A13B-Instruct. Different architecture: only 0 of 6530/74 tensors match by name and shape.
1 other repos hold byte-for-byte identical weight files.