aday777/deepseek_v4_tiny_fixture
Different architecture vs deepseek-ai/DeepSeek-V4-Flash-Vision-Exp. Different architecture: only 0 of 72633/150 tensors match by name and shape.
Different architecture vs deepseek-ai/DeepSeek-V4-Flash-Vision-Exp. Different architecture: only 0 of 72633/150 tensors match by name and shape.