yujiepan/deepseek-v4-bf16-tiny-random
Different architecture vs deepseek-ai/DeepSeek-V4-Pro. Different architecture: only 0 of 145116/5567 tensors match by name and shape.
1 other repos hold byte-for-byte identical weight files.
Different architecture vs deepseek-ai/DeepSeek-V4-Pro. Different architecture: only 0 of 145116/5567 tensors match by name and shape.
1 other repos hold byte-for-byte identical weight files.