Skip to content
Closed
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions convert_hf_to_gguf.py
Original file line number Diff line number Diff line change
Expand Up @@ -164,8 +164,19 @@ def get_tensors(self) -> Iterator[tuple[str, Tensor]]:
for name in model_part.keys():
if self.is_safetensors:
if self.lazy:
if (name.endswith("_scale") and name.removesuffix("_scale") in model_part.keys()):
continue
data = model_part.get_slice(name)
data = LazyTorchTensor.from_safetensors_slice(data)
if (name + "_scale" in model_part.keys()):
orig_shape = data.shape
scale = model_part.get_slice(name + "_scale")
shift = torch.tensor([0, 2, 4, 6], dtype=torch.uint8).reshape((4, *(1 for _ in range(len(orig_shape)))))
data = data.unsqueeze(0).expand((4, *orig_shape)) >> shift
data = data & 3
data = (data.float() - 1).reshape((orig_shape[0] * 4, *orig_shape[1:]))
# The scale is inverted
data = data / LazyTorchTensor.from_safetensors_slice(scale).float()
else:
data = model_part.get_tensor(name)
else:
Expand Down