SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Regression] Fix Quark quantized model loading after refactorization (#37407)

Browse Source
This commit is contained in:
Bowen Bao
2025-04-11 04:43:36 -07:00
committed by GitHub
parent a563999a02
commit 6cef03ba66
2 changed files with 18 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/quantization/quark_integration/test_quark.py
View File

@@ -53,6 +53,7 @@ class QuarkTest(unittest.TestCase):
EXPECTED_OUTPUTS.add("Today I am in Paris and I am not in Paris, France\nToday I am in Paris, Illinois")
EXPECTED_OUTPUTS.add("Today I am in Paris and I am enjoying the city of light. I am not just any ordinary Paris")
EXPECTED_OUTPUTS.add("Today I am in Paris and I am enjoying my day off! The sun is shining, the birds are")
EXPECTED_OUTPUTS.add("Today I am in Paris and I'm here to tell you about it. It's a beautiful day,")
EXPECTED_RELATIVE_DIFFERENCE = 1.66
device_map = None