yujiepan/kimi-linear-tiny-random
Different architecture vs moonshotai/Kimi-Linear-48B-A3B-Instruct. Different architecture: only 5 of 20493/3163 tensors match by name and shape.
1 other repos hold byte-for-byte identical weight files.
Different architecture vs moonshotai/Kimi-Linear-48B-A3B-Instruct. Different architecture: only 5 of 20493/3163 tensors match by name and shape.
1 other repos hold byte-for-byte identical weight files.