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

Revert low cpu mem tie weights (#29135)

Browse Source 
* Revert "Add tie_weights() to LM heads and set bias in set_output_embeddings() (#28948)"

This reverts commit 725f4ad1cc.

* Revert "Patch to skip failing `test_save_load_low_cpu_mem_usage` tests (#29043)"

This reverts commit 4156f517ce.
This commit is contained in:
amyeroberts
2024-02-20 12:06:46 +00:00
committed by GitHub
parent 15cfe38942
commit 0996a10077
26 changed files with 0 additions and 144 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/models/bert_generation/test_modeling_bert_generation.py
View File

@@ -305,12 +305,6 @@ class BertGenerationEncoderTest(ModelTesterMixin, GenerationTesterMixin, Pipelin
model = BertGenerationEncoder.from_pretrained("google/bert_for_seq_generation_L-24_bbc_encoder")
self.assertIsNotNone(model)
@unittest.skip(
"Not currently compatible. Fails with - NotImplementedError: Cannot copy out of meta tensor; no data!"
)
def test_save_load_low_cpu_mem_usage(self):
pass
@require_torch
class BertGenerationEncoderIntegrationTest(unittest.TestCase):

4
tests/models/deformable_detr/test_modeling_deformable_detr.py
View File

@@ -564,10 +564,6 @@ class DeformableDetrModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineT
msg=f"Parameter {name} of model {model_class} seems not properly initialized",
)
@unittest.skip("Cannot be initialized on meta device as some weights are modified during the initialization")
def test_save_load_low_cpu_mem_usage(self):
pass
def test_two_stage_training(self):
model_class = DeformableDetrForObjectDetection
config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()

4
tests/models/deta/test_modeling_deta.py
View File

@@ -520,10 +520,6 @@ class DetaModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin
msg=f"Parameter {name} of model {model_class} seems not properly initialized",
)
@unittest.skip("Cannot be initialized on meta device as some weights are modified during the initialization")
def test_save_load_low_cpu_mem_usage(self):
pass
TOLERANCE = 1e-4

6
tests/models/fsmt/test_modeling_fsmt.py
View File

@@ -329,12 +329,6 @@ class FSMTModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin
def test_resize_embeddings_untied(self):
pass
@unittest.skip(
"Not currently compatible. Fails with - NotImplementedError: Cannot copy out of meta tensor; no data!"
)
def test_save_load_low_cpu_mem_usage(self):
pass
@require_torch
class FSMTHeadTests(unittest.TestCase):

6
tests/models/marian/test_modeling_marian.py
View File

@@ -372,12 +372,6 @@ class MarianModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMix
def test_training_gradient_checkpointing_use_reentrant_false(self):
pass
@unittest.skip(
"Not currently compatible. Fails with - NotImplementedError: Cannot copy out of meta tensor; no data!"
)
def test_save_load_low_cpu_mem_usage(self):
pass
def assert_tensors_close(a, b, atol=1e-12, prefix=""):
"""If tensors have different shapes, different values or a and b are not both tensors, raise a nice Assertion error."""

4
tests/models/musicgen/test_modeling_musicgen.py
View File

@@ -1144,10 +1144,6 @@ class MusicgenTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin,
self.assertNotIn(config.pad_token_id, output_generate)
@unittest.skip("Fails with - TypeError: _weight_norm_interface() missing 1 required positional argument: 'dim'")
def test_save_load_low_cpu_mem_usage(self):
pass
def get_bip_bip(bip_duration=0.125, duration=0.5, sample_rate=32000):
"""Produces a series of 'bip bip' sounds at a given frequency."""

12
tests/models/reformer/test_modeling_reformer.py
View File

@@ -687,12 +687,6 @@ class ReformerLocalAttnModelTest(ReformerTesterMixin, GenerationTesterMixin, Mod
def test_left_padding_compatibility(self):
pass
@unittest.skip(
"Not currently compatible. Fails with - NotImplementedError: Cannot copy out of meta tensor; no data!"
)
def test_save_load_low_cpu_mem_usage(self):
pass
@require_torch
class ReformerLSHAttnModelTest(
@@ -854,12 +848,6 @@ class ReformerLSHAttnModelTest(
def test_left_padding_compatibility(self):
pass
@unittest.skip(
"Not currently compatible. Fails with - NotImplementedError: Cannot copy out of meta tensor; no data!"
)
def test_save_load_low_cpu_mem_usage(self):
pass
@require_torch
@require_sentencepiece

6
tests/models/xlm_roberta_xl/test_modeling_xlm_roberta_xl.py
View File

@@ -515,12 +515,6 @@ class XLMRobertaXLModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTes
self.assertEqual(position_ids.shape, expected_positions.shape)
self.assertTrue(torch.all(torch.eq(position_ids, expected_positions)))
@unittest.skip(
"Not currently compatible. Fails with - NotImplementedError: Cannot copy out of meta tensor; no data!"
)
def test_save_load_low_cpu_mem_usage(self):
pass
@require_torch
class XLMRobertaModelXLIntegrationTest(unittest.TestCase):

17
tests/test_modeling_common.py
View File

@@ -435,23 +435,6 @@ class ModelTesterMixin:
max_diff = (model_slow_init.state_dict()[key] - model_fast_init.state_dict()[key]).sum().item()
self.assertLessEqual(max_diff, 1e-3, msg=f"{key} not identical")
def test_save_load_low_cpu_mem_usage(self):
with tempfile.TemporaryDirectory() as tmpdirname:
for model_class in self.all_model_classes:
config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
model_to_save = model_class(config)
model_to_save.save_pretrained(tmpdirname)
model = model_class.from_pretrained(
tmpdirname,
low_cpu_mem_usage=True,
)
# The low_cpu_mem_usage=True causes the model params to be initialized with device=meta. If there are
# any unloaded or untied parameters, then trying to move it to device=torch_device will throw an error.
model.to(torch_device)
def test_fast_init_context_manager(self):
# 1. Create a dummy class. Should have buffers as well? To make sure we test __init__
class MyClass(PreTrainedModel):