Skip to content

FIX TST Wrong attribute in LoftQ test #2841

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

Merged
BenjaminBossan merged 1 commit into from
Oct 15, 2025
Merged

FIX TST Wrong attribute in LoftQ test #2841

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
5 changes: 3 additions & 2 deletions tests/test_gpu_examples.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2950,8 +2950,9 @@ def test_bloomz_loftq_4bit(self, device, tmp_path):
assert mse_loftq > 0.0

# next, check that LoftQ quantization errors are smaller than LoRA errors by a certain margin
assert mse_loftq < (mse_quantized / self.error_factor)
assert mae_loftq < (mae_quantized / self.error_factor)
error_factor = self.get_error_factor(device)
assert mse_loftq < (mse_quantized / error_factor)
assert mae_loftq < (mae_quantized / error_factor)

@pytest.mark.parametrize("device", [torch_device, "cpu"])
def test_bloomz_loftq_4bit_iter_5(self, device, tmp_path):
Expand Down
Loading