Skip to content

fix(testing): Fix BLOOM tokenizer, CLAP audio features, and CLVP text tester usage in tests #43798

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
Rocketknight1 merged 1 commit into from
Feb 6, 2026
Merged

fix(testing): Fix BLOOM tokenizer, CLAP audio features, and CLVP text tester usage in tests #43798

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
4 changes: 2 additions & 2 deletions tests/models/bloom/test_modeling_bloom.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -544,7 +544,7 @@ def test_batch_generation(self):

input_sentence = ["I enjoy walking with my cute dog", "I enjoy walking with my cute dog"]

inputs = tokenizer.batch_encode_plus(input_sentence, return_tensors="pt", padding=True)
inputs = tokenizer(input_sentence, return_tensors="pt", padding=True)
input_ids = inputs["input_ids"].to(torch_device)
attention_mask = inputs["attention_mask"]
greedy_output = model.generate(input_ids, attention_mask=attention_mask, max_length=50, do_sample=False)
Expand All @@ -565,7 +565,7 @@ def test_batch_generation_padding(self):
input_sentence = ["I enjoy walking with my cute dog", "Hello my name is"]
input_sentence_without_pad = "Hello my name is"

input_ids = tokenizer.batch_encode_plus(input_sentence, return_tensors="pt", padding=True)
input_ids = tokenizer(input_sentence, return_tensors="pt", padding=True)
input_ids_without_pad = tokenizer.encode(input_sentence_without_pad, return_tensors="pt")

input_ids, attention_mask = input_ids["input_ids"].to(torch_device), input_ids["attention_mask"]
Expand Down
16 changes: 12 additions & 4 deletions tests/models/clap/test_modeling_clap.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -538,7 +538,9 @@ def test_integration_unfused(self):
expected_mean = EXPECTED_MEANS_UNFUSED[padding]

self.assertTrue(
torch.allclose(audio_embed.cpu().mean(), torch.tensor([expected_mean]), atol=1e-3, rtol=1e-3)
torch.allclose(
audio_embed.pooler_output.cpu().mean(), torch.tensor([expected_mean]), atol=1e-3, rtol=1e-3
)
)

def test_integration_fused(self):
Expand All @@ -565,7 +567,9 @@ def test_integration_fused(self):
expected_mean = EXPECTED_MEANS_FUSED[padding]

self.assertTrue(
torch.allclose(audio_embed.cpu().mean(), torch.tensor([expected_mean]), atol=1e-3, rtol=1e-3)
torch.allclose(
audio_embed.pooler_output.cpu().mean(), torch.tensor([expected_mean]), atol=1e-3, rtol=1e-3
)
)

def test_batched_fused(self):
Expand All @@ -592,7 +596,9 @@ def test_batched_fused(self):
expected_mean = EXPECTED_MEANS_FUSED[padding]

self.assertTrue(
torch.allclose(audio_embed.cpu().mean(), torch.tensor([expected_mean]), atol=1e-3, rtol=1e-3)
torch.allclose(
audio_embed.pooler_output.cpu().mean(), torch.tensor([expected_mean]), atol=1e-3, rtol=1e-3
)
)

def test_batched_unfused(self):
Expand All @@ -617,5 +623,7 @@ def test_batched_unfused(self):
expected_mean = EXPECTED_MEANS_FUSED[padding]

self.assertTrue(
torch.allclose(audio_embed.cpu().mean(), torch.tensor([expected_mean]), atol=1e-3, rtol=1e-3)
torch.allclose(
audio_embed.pooler_output.cpu().mean(), torch.tensor([expected_mean]), atol=1e-3, rtol=1e-3
)
)
1 change: 1 addition & 0 deletions tests/models/clvp/test_modeling_clvp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -321,6 +321,7 @@ class ClvpModelForConditionalGenerationTester:
def __init__(self, parent, is_training=False):
self.parent = parent
self.clvp_encoder_tester = ClvpEncoderTester(parent)
self.text_model_tester = self.clvp_encoder_tester
self.is_training = is_training
self.batch_size = self.clvp_encoder_tester.batch_size # need bs for batching_equivalence test

Expand Down