convert : fix conversion from FP8 for Deepseek-V3.1-Base

Author: compilade

convert_hf_to_gguf.py

@@ -254,6 +254,8 @@ def dequant_simple(weight: Tensor, scale: Tensor) -> Tensor:
                     # TODO: make sure it's a list of integers
                     for i, size in enumerate(weight_block_size):
                         scale = scale.repeat_interleave(size, i)
+                # unpad the scale (e.g. when the tensor size isn't a multiple of the block size)
+                scale = scale[tuple(slice(0, size) for size in weight.shape)]
 
                 return weight.float() * scale