0xSero/DeepSeek-V3.2-345B-W3A16
Different architecture vs deepseek-ai/DeepSeek-V3. Different architecture: only 247 of 91991/68643 tensors match by name and shape.
Different architecture vs deepseek-ai/DeepSeek-V3. Different architecture: only 247 of 91991/68643 tensors match by name and shape.