Skip to content

Fix: ternary weight dequantization uses division instead of multiplication #616

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
puddintaim1975-dev wants to merge 1 commit into
base: main
Choose a base branch
from
+3 −3
Open

Fix: ternary weight dequantization uses division instead of multiplication #616

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions utils/convert-hf-to-gguf-bitnet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -804,7 +804,7 @@ def write_tensors(self):
data_torch = data_torch.unsqueeze(0).expand((4, *origin_shape)) >> shift
data_torch = data_torch & 3
data_torch = (data_torch.float() - 1).reshape((origin_shape[0] * 4, *origin_shape[1:]))
data_torch = data_torch / scale_map[name.replace(".weight", "")].float()
data_torch = data_torch * scale_map[name.replace(".weight", "")].float()

# use the first number-like part of the tensor name as the block id
bid = None
Expand Down Expand Up @@ -1102,10 +1102,10 @@ def write_tensors(self):
data_torch = data_torch.unsqueeze(0).expand((4, *origin_shape)) >> shift
data_torch = data_torch & 3
data_torch = (data_torch.float() - 1).reshape((origin_shape[0] * 4, *origin_shape[1:]))
# For F16/F32 output: divide by weight_scale to get full float values
# For F16/F32 output: multiply by weight_scale to get full float values
# For I2_S output: keep as ternary {-1,0,1}, scale is passed separately to quantize_to_i2_s
if self.ftype not in (gguf.GGMLQuantizationType.I2_S, gguf.GGMLQuantizationType.TL1, gguf.GGMLQuantizationType.TL2):
data_torch = data_torch / scale_map[name.replace(".weight", "")].float()
data_torch = data_torch * scale_map[name.replace(".weight", "")].float()
# convert any unsupported data types to float32
elif data_torch.dtype not in (torch.float16, torch.float32):
data_torch = data_torch.to(torch.float32)
Expand Down