Skip to content

Fix new BNB test failures #35345

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
merged 1 commit into from
Jan 2, 2025
Merged

Fix new BNB test failures #35345

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion tests/quantization/bnb/test_4bit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,7 +172,7 @@ def test_memory_footprint(self):
mem_fp16 = self.model_fp16.get_memory_footprint()
mem_4bit = self.model_4bit.get_memory_footprint()

self.assertAlmostEqual(mem_fp16 / mem_4bit, self.EXPECTED_RELATIVE_DIFFERENCE)
self.assertAlmostEqual(mem_fp16 / mem_4bit, self.EXPECTED_RELATIVE_DIFFERENCE, delta=1e-5)
linear = get_some_linear_layer(self.model_4bit)
self.assertTrue(linear.weight.__class__ == Params4bit)

Expand Down
7 changes: 6 additions & 1 deletion tests/quantization/bnb/test_mixed_int8.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,7 +229,7 @@ def test_memory_footprint(self):
mem_fp16 = self.model_fp16.get_memory_footprint()
mem_8bit = self.model_8bit.get_memory_footprint()

self.assertAlmostEqual(mem_fp16 / mem_8bit, self.EXPECTED_RELATIVE_DIFFERENCE)
self.assertAlmostEqual(mem_fp16 / mem_8bit, self.EXPECTED_RELATIVE_DIFFERENCE, delta=1e-5)
self.assertTrue(get_some_linear_layer(self.model_8bit).weight.__class__ == Int8Params)

def test_linear_are_8bit(self):
Expand Down Expand Up @@ -938,8 +938,13 @@ class MixedInt8LlamaTest(MixedInt8Test):
model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
EXPECTED_RELATIVE_DIFFERENCE = 1.7869331026479096
EXPECTED_OUTPUTS = set()

# Expected on Intel XPU
EXPECTED_OUTPUTS.add("Hello my name is John Smith and I am a software engineer. I")

# Expected on NVIDIA T4
EXPECTED_OUTPUTS.add("Hello my name is John and I am a software engineer. I have")

def test_int8_from_pretrained(self):
r"""
Test whether loading a 8bit model from the Hub works as expected
Expand Down
Loading