From 996f512d52908beb7b89d835fe7eb7b900f78ad0 Mon Sep 17 00:00:00 2001 From: co63oc Date: Thu, 6 Mar 2025 07:04:06 +0800 Subject: [PATCH] Fix typos in tests (#36547) Signed-off-by: co63oc --- tests/bettertransformer/test_integration.py | 2 +- tests/models/align/test_modeling_align.py | 8 +++---- tests/models/altclip/test_modeling_altclip.py | 8 +++---- tests/models/aria/test_modeling_aria.py | 6 ++--- .../autoformer/test_modeling_autoformer.py | 6 ++--- tests/models/bart/test_modeling_bart.py | 2 +- tests/models/beit/test_modeling_beit.py | 4 ++-- .../models/big_bird/test_modeling_big_bird.py | 6 ++--- .../test_modeling_bigbird_pegasus.py | 2 +- tests/models/blip/test_modeling_blip.py | 12 +++++----- tests/models/blip/test_modeling_blip_text.py | 4 ++-- .../models/blip/test_modeling_tf_blip_text.py | 4 ++-- tests/models/blip_2/test_modeling_blip_2.py | 4 ++-- tests/models/canine/test_modeling_canine.py | 6 ++--- .../test_modeling_chinese_clip.py | 8 +++---- tests/models/clap/test_modeling_clap.py | 8 +++---- tests/models/clip/test_modeling_clip.py | 8 +++---- tests/models/clipseg/test_modeling_clipseg.py | 14 ++++++------ tests/models/colpali/test_modeling_colpali.py | 6 ++--- tests/models/deit/test_modeling_deit.py | 4 ++-- .../depth_pro/test_modeling_depth_pro.py | 4 ++-- tests/models/dinov2/test_modeling_dinov2.py | 6 ++--- .../test_modeling_dinov2_with_registers.py | 6 ++--- tests/models/dpt/test_modeling_dpt.py | 4 ++-- .../dpt/test_modeling_dpt_auto_backbone.py | 4 ++-- tests/models/dpt/test_modeling_dpt_hybrid.py | 4 ++-- tests/models/flava/test_modeling_flava.py | 22 +++++++++---------- tests/models/fnet/test_modeling_fnet.py | 6 ++--- tests/models/fuyu/test_modeling_fuyu.py | 6 ++--- tests/models/git/test_modeling_git.py | 4 ++-- tests/models/gpt2/test_modeling_gpt2.py | 6 ++--- .../models/groupvit/test_modeling_groupvit.py | 8 +++---- tests/models/idefics/test_modeling_idefics.py | 8 +++---- .../models/imagegpt/test_modeling_imagegpt.py | 8 +++---- .../models/informer/test_modeling_informer.py | 6 ++--- .../test_modeling_instructblip.py | 4 ++-- .../test_modeling_instructblipvideo.py | 4 ++-- .../models/layoutlm/test_modeling_layoutlm.py | 6 ++--- .../test_tokenization_layoutlmv3.py | 2 +- tests/models/lilt/test_modeling_lilt.py | 6 ++--- tests/models/llava/test_modeling_llava.py | 8 +++---- .../llava_next/test_modeling_llava_next.py | 6 ++--- .../test_modeling_llava_next_video.py | 6 ++--- .../test_modeling_llava_onevision.py | 6 ++--- tests/models/longt5/test_modeling_longt5.py | 4 ++-- tests/models/luke/test_modeling_luke.py | 6 ++--- tests/models/lxmert/test_modeling_lxmert.py | 2 +- tests/models/m2m_100/test_modeling_m2m_100.py | 2 +- tests/models/mamba/test_modeling_mamba.py | 2 +- tests/models/marian/test_modeling_marian.py | 6 ++--- tests/models/mbart/test_modeling_mbart.py | 2 +- tests/models/mllama/test_modeling_mllama.py | 4 ++-- tests/models/mra/test_modeling_mra.py | 6 ++--- .../models/nllb_moe/test_modeling_nllb_moe.py | 2 +- tests/models/owlv2/test_modeling_owlv2.py | 12 +++++----- tests/models/owlvit/test_modeling_owlvit.py | 12 +++++----- .../paligemma/test_modeling_paligemma.py | 8 +++---- .../paligemma2/test_modeling_paligemma2.py | 8 +++---- tests/models/pegasus/test_modeling_pegasus.py | 6 ++--- .../pix2struct/test_modeling_pix2struct.py | 8 +++---- tests/models/plbart/test_modeling_plbart.py | 2 +- .../models/reformer/test_modeling_reformer.py | 2 +- .../reformer/test_tokenization_reformer.py | 2 +- .../models/roformer/test_modeling_roformer.py | 6 ++--- tests/models/sam/test_modeling_sam.py | 4 ++-- .../test_modeling_seamless_m4t.py | 16 +++++++------- .../test_modeling_seamless_m4t_v2.py | 16 +++++++------- tests/models/smolvlm/test_modeling_smolvlm.py | 4 ++-- .../test_modeling_speech_to_text.py | 4 ++-- .../test_modeling_tf_speech_to_text.py | 4 ++-- .../models/speecht5/test_modeling_speecht5.py | 12 +++++----- tests/models/swin2sr/test_modeling_swin2sr.py | 4 ++-- .../test_modeling_switch_transformers.py | 8 +++---- .../test_modeling_time_series_transformer.py | 6 ++--- tests/models/udop/test_modeling_udop.py | 4 ++-- tests/models/umt5/test_modeling_umt5.py | 6 ++--- .../video_llava/test_modeling_video_llava.py | 6 ++--- tests/models/vilt/test_modeling_vilt.py | 4 ++-- .../models/vipllava/test_modeling_vipllava.py | 8 +++---- .../visual_bert/test_modeling_visual_bert.py | 6 ++--- .../models/vitmatte/test_modeling_vitmatte.py | 4 ++-- .../wav2vec2/test_modeling_flax_wav2vec2.py | 4 ++-- .../models/wav2vec2/test_modeling_wav2vec2.py | 4 ++-- .../test_modeling_wav2vec2_bert.py | 4 ++-- .../test_modeling_wav2vec2_conformer.py | 4 ++-- tests/models/whisper/test_modeling_whisper.py | 4 ++-- tests/models/x_clip/test_modeling_x_clip.py | 8 +++---- tests/pipelines/test_pipelines_common.py | 2 +- ...t_pipelines_document_question_answering.py | 4 ++-- .../test_pipelines_feature_extraction.py | 2 +- ...test_pipelines_image_feature_extraction.py | 2 +- .../test_pipelines_question_answering.py | 2 +- .../test_pipelines_text_classification.py | 2 +- .../test_pipelines_text_generation.py | 4 ++-- tests/test_configuration_common.py | 2 +- tests/test_image_processing_common.py | 2 +- tests/test_modeling_common.py | 10 ++++----- tests/test_modeling_flax_common.py | 12 +++++----- tests/test_tokenization_common.py | 2 +- 99 files changed, 282 insertions(+), 282 deletions(-) diff --git a/tests/bettertransformer/test_integration.py b/tests/bettertransformer/test_integration.py index 8f67852bfd..b123001f10 100644 --- a/tests/bettertransformer/test_integration.py +++ b/tests/bettertransformer/test_integration.py @@ -38,7 +38,7 @@ class BetterTransformerIntegrationTest(unittest.TestCase): def test_transform_and_reverse(self): r""" - Classic tests to simply check if the conversion has been successfull. + Classic tests to simply check if the conversion has been successful. """ model_id = "hf-internal-testing/tiny-random-t5" tokenizer = AutoTokenizer.from_pretrained(model_id) diff --git a/tests/models/align/test_modeling_align.py b/tests/models/align/test_modeling_align.py index 3a3a33edf6..dc41929dca 100644 --- a/tests/models/align/test_modeling_align.py +++ b/tests/models/align/test_modeling_align.py @@ -219,13 +219,13 @@ class AlignVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -361,13 +361,13 @@ class AlignTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/altclip/test_modeling_altclip.py b/tests/models/altclip/test_modeling_altclip.py index c70269b1d1..9fadadf4a7 100755 --- a/tests/models/altclip/test_modeling_altclip.py +++ b/tests/models/altclip/test_modeling_altclip.py @@ -187,13 +187,13 @@ class AltCLIPVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -335,13 +335,13 @@ class AltCLIPTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/aria/test_modeling_aria.py b/tests/models/aria/test_modeling_aria.py index fb74e914bd..e29a507d6a 100644 --- a/tests/models/aria/test_modeling_aria.py +++ b/tests/models/aria/test_modeling_aria.py @@ -241,19 +241,19 @@ class AriaForConditionalGenerationModelTest(ModelTesterMixin, GenerationTesterMi torch.testing.assert_close(out_embeds, out_ids) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/autoformer/test_modeling_autoformer.py b/tests/models/autoformer/test_modeling_autoformer.py index 3a2ed63851..92aa1ad4c9 100644 --- a/tests/models/autoformer/test_modeling_autoformer.py +++ b/tests/models/autoformer/test_modeling_autoformer.py @@ -245,19 +245,19 @@ class AutoformerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCa pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass diff --git a/tests/models/bart/test_modeling_bart.py b/tests/models/bart/test_modeling_bart.py index 1cddb898e9..b6173de20e 100644 --- a/tests/models/bart/test_modeling_bart.py +++ b/tests/models/bart/test_modeling_bart.py @@ -504,7 +504,7 @@ class BartModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin model.generate(num_beams=4, do_sample=True, early_stopping=False, num_return_sequences=3) @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/beit/test_modeling_beit.py b/tests/models/beit/test_modeling_beit.py index c455c9eebb..5c8d2215d4 100644 --- a/tests/models/beit/test_modeling_beit.py +++ b/tests/models/beit/test_modeling_beit.py @@ -379,13 +379,13 @@ class BeitModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): loss.backward() @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/big_bird/test_modeling_big_bird.py b/tests/models/big_bird/test_modeling_big_bird.py index 6174c22600..9603ae9a75 100644 --- a/tests/models/big_bird/test_modeling_big_bird.py +++ b/tests/models/big_bird/test_modeling_big_bird.py @@ -609,19 +609,19 @@ class BigBirdModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) self.model_tester.create_and_check_for_change_to_full_attn(*config_and_inputs) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/bigbird_pegasus/test_modeling_bigbird_pegasus.py b/tests/models/bigbird_pegasus/test_modeling_bigbird_pegasus.py index 9103c2d52f..c4752097e9 100644 --- a/tests/models/bigbird_pegasus/test_modeling_bigbird_pegasus.py +++ b/tests/models/bigbird_pegasus/test_modeling_bigbird_pegasus.py @@ -464,7 +464,7 @@ class BigBirdPegasusModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineT torch.testing.assert_close(outputs1, outputs2, rtol=1e-5, atol=1e-5) @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/blip/test_modeling_blip.py b/tests/models/blip/test_modeling_blip.py index 529e163111..50cc8baae5 100644 --- a/tests/models/blip/test_modeling_blip.py +++ b/tests/models/blip/test_modeling_blip.py @@ -202,13 +202,13 @@ class BlipVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -346,13 +346,13 @@ class BlipTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -977,13 +977,13 @@ class BlipTextRetrievalModelTest(ModelTesterMixin, unittest.TestCase): loss.backward() @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/blip/test_modeling_blip_text.py b/tests/models/blip/test_modeling_blip_text.py index ad550308fa..0be5d72002 100644 --- a/tests/models/blip/test_modeling_blip_text.py +++ b/tests/models/blip/test_modeling_blip_text.py @@ -150,13 +150,13 @@ class BlipTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/blip/test_modeling_tf_blip_text.py b/tests/models/blip/test_modeling_tf_blip_text.py index bba93551f0..6636ee3e21 100644 --- a/tests/models/blip/test_modeling_tf_blip_text.py +++ b/tests/models/blip/test_modeling_tf_blip_text.py @@ -148,13 +148,13 @@ class BlipTextModelTest(TFModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/blip_2/test_modeling_blip_2.py b/tests/models/blip_2/test_modeling_blip_2.py index 03bd268e24..6815b57571 100644 --- a/tests/models/blip_2/test_modeling_blip_2.py +++ b/tests/models/blip_2/test_modeling_blip_2.py @@ -209,13 +209,13 @@ class Blip2VisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/canine/test_modeling_canine.py b/tests/models/canine/test_modeling_canine.py index 31d02a2c04..803e942d7a 100644 --- a/tests/models/canine/test_modeling_canine.py +++ b/tests/models/canine/test_modeling_canine.py @@ -510,19 +510,19 @@ class CanineModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/chinese_clip/test_modeling_chinese_clip.py b/tests/models/chinese_clip/test_modeling_chinese_clip.py index d63c152431..4a27e7292e 100644 --- a/tests/models/chinese_clip/test_modeling_chinese_clip.py +++ b/tests/models/chinese_clip/test_modeling_chinese_clip.py @@ -397,13 +397,13 @@ class ChineseCLIPTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -477,13 +477,13 @@ class ChineseCLIPVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/clap/test_modeling_clap.py b/tests/models/clap/test_modeling_clap.py index 60b77d0efa..559db26206 100644 --- a/tests/models/clap/test_modeling_clap.py +++ b/tests/models/clap/test_modeling_clap.py @@ -252,13 +252,13 @@ class ClapAudioModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -417,13 +417,13 @@ class ClapTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/clip/test_modeling_clip.py b/tests/models/clip/test_modeling_clip.py index 63723bfe3b..6b75769b53 100644 --- a/tests/models/clip/test_modeling_clip.py +++ b/tests/models/clip/test_modeling_clip.py @@ -435,13 +435,13 @@ class CLIPVisionModelTest(CLIPModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -613,13 +613,13 @@ class CLIPTextModelTest(CLIPModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/clipseg/test_modeling_clipseg.py b/tests/models/clipseg/test_modeling_clipseg.py index a17b2b6a4f..c2f77e3066 100644 --- a/tests/models/clipseg/test_modeling_clipseg.py +++ b/tests/models/clipseg/test_modeling_clipseg.py @@ -191,13 +191,13 @@ class CLIPSegVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -330,13 +330,13 @@ class CLIPSegTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -493,19 +493,19 @@ class CLIPSegModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/colpali/test_modeling_colpali.py b/tests/models/colpali/test_modeling_colpali.py index 5e94ecaab9..f2e9270163 100644 --- a/tests/models/colpali/test_modeling_colpali.py +++ b/tests/models/colpali/test_modeling_colpali.py @@ -254,19 +254,19 @@ class ColPaliForRetrievalModelTest(ModelTesterMixin, unittest.TestCase): self.assertIsInstance(outputs, ColPaliForRetrievalOutput) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/deit/test_modeling_deit.py b/tests/models/deit/test_modeling_deit.py index bf58e1cd32..333ed0fa95 100644 --- a/tests/models/deit/test_modeling_deit.py +++ b/tests/models/deit/test_modeling_deit.py @@ -317,13 +317,13 @@ class DeiTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): loss.backward() @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/depth_pro/test_modeling_depth_pro.py b/tests/models/depth_pro/test_modeling_depth_pro.py index 2966c213b4..bd02373707 100644 --- a/tests/models/depth_pro/test_modeling_depth_pro.py +++ b/tests/models/depth_pro/test_modeling_depth_pro.py @@ -284,13 +284,13 @@ class DepthProModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase loss.backward() @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/dinov2/test_modeling_dinov2.py b/tests/models/dinov2/test_modeling_dinov2.py index 3e52ad49af..a8f11c9172 100644 --- a/tests/models/dinov2/test_modeling_dinov2.py +++ b/tests/models/dinov2/test_modeling_dinov2.py @@ -250,19 +250,19 @@ class Dinov2ModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/dinov2_with_registers/test_modeling_dinov2_with_registers.py b/tests/models/dinov2_with_registers/test_modeling_dinov2_with_registers.py index a276eedd3a..c40af0c197 100644 --- a/tests/models/dinov2_with_registers/test_modeling_dinov2_with_registers.py +++ b/tests/models/dinov2_with_registers/test_modeling_dinov2_with_registers.py @@ -267,19 +267,19 @@ class Dinov2WithRegistersModelTest(ModelTesterMixin, PipelineTesterMixin, unitte pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/dpt/test_modeling_dpt.py b/tests/models/dpt/test_modeling_dpt.py index 44fb2afb3b..fc652c2484 100644 --- a/tests/models/dpt/test_modeling_dpt.py +++ b/tests/models/dpt/test_modeling_dpt.py @@ -244,13 +244,13 @@ class DPTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): loss.backward() @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/dpt/test_modeling_dpt_auto_backbone.py b/tests/models/dpt/test_modeling_dpt_auto_backbone.py index 62240d24bc..4c0527687c 100644 --- a/tests/models/dpt/test_modeling_dpt_auto_backbone.py +++ b/tests/models/dpt/test_modeling_dpt_auto_backbone.py @@ -230,13 +230,13 @@ class DPTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/dpt/test_modeling_dpt_hybrid.py b/tests/models/dpt/test_modeling_dpt_hybrid.py index 568b05e2d4..cf16620314 100644 --- a/tests/models/dpt/test_modeling_dpt_hybrid.py +++ b/tests/models/dpt/test_modeling_dpt_hybrid.py @@ -258,13 +258,13 @@ class DPTModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): loss.backward() @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/flava/test_modeling_flava.py b/tests/models/flava/test_modeling_flava.py index e4949c54ca..a6cf75a722 100644 --- a/tests/models/flava/test_modeling_flava.py +++ b/tests/models/flava/test_modeling_flava.py @@ -309,13 +309,13 @@ class FlavaImageModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -470,13 +470,13 @@ class FlavaTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -635,13 +635,13 @@ class FlavaMultimodalModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -766,13 +766,13 @@ class FlavaImageCodebookTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -1247,19 +1247,19 @@ class FlavaForPreTrainingTest(FlavaModelTest): test_torchscript = False @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/fnet/test_modeling_fnet.py b/tests/models/fnet/test_modeling_fnet.py index 26eec0f299..9fdb7f240f 100644 --- a/tests/models/fnet/test_modeling_fnet.py +++ b/tests/models/fnet/test_modeling_fnet.py @@ -332,19 +332,19 @@ class FNetModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/fuyu/test_modeling_fuyu.py b/tests/models/fuyu/test_modeling_fuyu.py index 1b308973fb..a908567d24 100644 --- a/tests/models/fuyu/test_modeling_fuyu.py +++ b/tests/models/fuyu/test_modeling_fuyu.py @@ -282,19 +282,19 @@ class FuyuModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin self.model_tester = FuyuModelTester(self) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/git/test_modeling_git.py b/tests/models/git/test_modeling_git.py index 473bbe6db6..a2427dfbc1 100644 --- a/tests/models/git/test_modeling_git.py +++ b/tests/models/git/test_modeling_git.py @@ -176,13 +176,13 @@ class GitVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/gpt2/test_modeling_gpt2.py b/tests/models/gpt2/test_modeling_gpt2.py index b45c84fc64..4af2739ff5 100644 --- a/tests/models/gpt2/test_modeling_gpt2.py +++ b/tests/models/gpt2/test_modeling_gpt2.py @@ -601,19 +601,19 @@ class GPT2ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin self.model_tester.create_and_check_cached_forward_with_and_without_attention_mask(*config_and_inputs) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/groupvit/test_modeling_groupvit.py b/tests/models/groupvit/test_modeling_groupvit.py index e235033747..6eebdbf2e4 100644 --- a/tests/models/groupvit/test_modeling_groupvit.py +++ b/tests/models/groupvit/test_modeling_groupvit.py @@ -263,13 +263,13 @@ class GroupViTVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -461,13 +461,13 @@ class GroupViTTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/idefics/test_modeling_idefics.py b/tests/models/idefics/test_modeling_idefics.py index 151fa4a1c8..48860718ee 100644 --- a/tests/models/idefics/test_modeling_idefics.py +++ b/tests/models/idefics/test_modeling_idefics.py @@ -478,13 +478,13 @@ class IdeficsModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) loss.backward() @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -855,13 +855,13 @@ class IdeficsForVisionText2TextTest(IdeficsModelTest, GenerationTesterMixin, uni pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/imagegpt/test_modeling_imagegpt.py b/tests/models/imagegpt/test_modeling_imagegpt.py index a2d65f4d4b..b563dc69a7 100644 --- a/tests/models/imagegpt/test_modeling_imagegpt.py +++ b/tests/models/imagegpt/test_modeling_imagegpt.py @@ -188,7 +188,7 @@ class ImageGPTModelTester: labels = ids_tensor([self.batch_size, self.seq_length], self.vocab_size - 1) result = model(input_ids, token_type_ids=token_type_ids, labels=labels) self.parent.assertEqual(result.loss.shape, ()) - # ImageGPTForCausalImageModeling doens't have tied input- and output embeddings + # ImageGPTForCausalImageModeling doesn't have tied input- and output embeddings self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.vocab_size - 1)) def create_and_check_imagegpt_for_image_classification( @@ -281,19 +281,19 @@ class ImageGPTModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterM self.model_tester.create_and_check_imagegpt_for_image_classification(*config_and_inputs) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/informer/test_modeling_informer.py b/tests/models/informer/test_modeling_informer.py index 4551abd214..fcd2858ac5 100644 --- a/tests/models/informer/test_modeling_informer.py +++ b/tests/models/informer/test_modeling_informer.py @@ -294,19 +294,19 @@ class InformerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/instructblip/test_modeling_instructblip.py b/tests/models/instructblip/test_modeling_instructblip.py index bbf8772890..bccc8e230e 100644 --- a/tests/models/instructblip/test_modeling_instructblip.py +++ b/tests/models/instructblip/test_modeling_instructblip.py @@ -205,13 +205,13 @@ class InstructBlipVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/instructblipvideo/test_modeling_instructblipvideo.py b/tests/models/instructblipvideo/test_modeling_instructblipvideo.py index 351dea3d6f..27ed2d42e7 100644 --- a/tests/models/instructblipvideo/test_modeling_instructblipvideo.py +++ b/tests/models/instructblipvideo/test_modeling_instructblipvideo.py @@ -213,13 +213,13 @@ class InstructBlipVideoVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/layoutlm/test_modeling_layoutlm.py b/tests/models/layoutlm/test_modeling_layoutlm.py index ab2a9cd513..68605c1d6a 100644 --- a/tests/models/layoutlm/test_modeling_layoutlm.py +++ b/tests/models/layoutlm/test_modeling_layoutlm.py @@ -280,19 +280,19 @@ class LayoutLMModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase self.model_tester.create_and_check_for_question_answering(*config_and_inputs) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/layoutlmv3/test_tokenization_layoutlmv3.py b/tests/models/layoutlmv3/test_tokenization_layoutlmv3.py index 87babd853b..a67c7e4a11 100644 --- a/tests/models/layoutlmv3/test_tokenization_layoutlmv3.py +++ b/tests/models/layoutlmv3/test_tokenization_layoutlmv3.py @@ -54,7 +54,7 @@ class LayoutLMv3TokenizationTest(TokenizerTesterMixin, unittest.TestCase): tokenizer_class = LayoutLMv3Tokenizer rust_tokenizer_class = LayoutLMv3TokenizerFast test_rust_tokenizer = True - # determined by the tokenization algortihm and the way it's decoded by the fast tokenizers + # determined by the tokenization algorithm and the way it's decoded by the fast tokenizers space_between_special_tokens = False test_seq2seq = False from_pretrained_kwargs = {"cls_token": ""} diff --git a/tests/models/lilt/test_modeling_lilt.py b/tests/models/lilt/test_modeling_lilt.py index c24d375ccc..5ac02f9427 100644 --- a/tests/models/lilt/test_modeling_lilt.py +++ b/tests/models/lilt/test_modeling_lilt.py @@ -281,19 +281,19 @@ class LiltModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): self.model_tester.create_and_check_for_question_answering(*config_and_inputs) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/llava/test_modeling_llava.py b/tests/models/llava/test_modeling_llava.py index 347b147c76..66756784bd 100644 --- a/tests/models/llava/test_modeling_llava.py +++ b/tests/models/llava/test_modeling_llava.py @@ -259,7 +259,7 @@ class LlavaForConditionalGenerationModelTest(ModelTesterMixin, GenerationTesterM config, input_dict = self.model_tester.prepare_config_and_inputs_for_common() for model_class in self.all_model_classes: model = model_class(config).to(torch_device) - _ = model(**input_dict) # successfull forward with no modifications + _ = model(**input_dict) # successful forward with no modifications # remove one image but leave the image token in text input_dict["pixel_values"] = input_dict["pixel_values"][-1:, ...] @@ -306,19 +306,19 @@ class LlavaForConditionalGenerationModelTest(ModelTesterMixin, GenerationTesterM model(**input_dict) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/llava_next/test_modeling_llava_next.py b/tests/models/llava_next/test_modeling_llava_next.py index 0c75df53c1..327e33a9b7 100644 --- a/tests/models/llava_next/test_modeling_llava_next.py +++ b/tests/models/llava_next/test_modeling_llava_next.py @@ -348,19 +348,19 @@ class LlavaNextForConditionalGenerationModelTest(ModelTesterMixin, GenerationTes model(**input_dict) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/llava_next_video/test_modeling_llava_next_video.py b/tests/models/llava_next_video/test_modeling_llava_next_video.py index 6d4df92f5c..44c7deeffc 100644 --- a/tests/models/llava_next_video/test_modeling_llava_next_video.py +++ b/tests/models/llava_next_video/test_modeling_llava_next_video.py @@ -365,19 +365,19 @@ class LlavaNextVideoForConditionalGenerationModelTest(ModelTesterMixin, Generati model(**input_dict) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/llava_onevision/test_modeling_llava_onevision.py b/tests/models/llava_onevision/test_modeling_llava_onevision.py index c9bb448278..29f01c1e0e 100644 --- a/tests/models/llava_onevision/test_modeling_llava_onevision.py +++ b/tests/models/llava_onevision/test_modeling_llava_onevision.py @@ -319,19 +319,19 @@ class LlavaOnevisionForConditionalGenerationModelTest(ModelTesterMixin, Generati model(**input_dict) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, SiglipVisionModel does not support standalone training" + reason="This architecture seem to not compute gradients properly when using GC, SiglipVisionModel does not support standalone training" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, SiglipVisionModel does not support standalone training" + reason="This architecture seem to not compute gradients properly when using GC, SiglipVisionModel does not support standalone training" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, SiglipVisionModel does not support standalone training" + reason="This architecture seem to not compute gradients properly when using GC, SiglipVisionModel does not support standalone training" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/longt5/test_modeling_longt5.py b/tests/models/longt5/test_modeling_longt5.py index 6ec347fe05..06bb76b74d 100644 --- a/tests/models/longt5/test_modeling_longt5.py +++ b/tests/models/longt5/test_modeling_longt5.py @@ -780,7 +780,7 @@ class LongT5ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMix ) @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass @@ -1125,7 +1125,7 @@ class LongT5EncoderOnlyModelTest(ModelTesterMixin, unittest.TestCase): ) @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/luke/test_modeling_luke.py b/tests/models/luke/test_modeling_luke.py index 1a0b63d33e..8864e5687e 100644 --- a/tests/models/luke/test_modeling_luke.py +++ b/tests/models/luke/test_modeling_luke.py @@ -863,19 +863,19 @@ class LukeModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): self.assertIsNotNone(entity_hidden_states.grad) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/lxmert/test_modeling_lxmert.py b/tests/models/lxmert/test_modeling_lxmert.py index 50be9cce9b..308662335d 100644 --- a/tests/models/lxmert/test_modeling_lxmert.py +++ b/tests/models/lxmert/test_modeling_lxmert.py @@ -779,7 +779,7 @@ class LxmertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/m2m_100/test_modeling_m2m_100.py b/tests/models/m2m_100/test_modeling_m2m_100.py index 015a2c5f38..60b3d220b1 100644 --- a/tests/models/m2m_100/test_modeling_m2m_100.py +++ b/tests/models/m2m_100/test_modeling_m2m_100.py @@ -338,7 +338,7 @@ class M2M100ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMix model.generate(num_beams=4, do_sample=True, early_stopping=False, num_return_sequences=3) @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/mamba/test_modeling_mamba.py b/tests/models/mamba/test_modeling_mamba.py index 0c1bbef910..bab434d4bc 100644 --- a/tests/models/mamba/test_modeling_mamba.py +++ b/tests/models/mamba/test_modeling_mamba.py @@ -185,7 +185,7 @@ class MambaModelTester: output_two = outputs.last_hidden_state self.parent.assertTrue(torch.allclose(torch.cat([output_one, output_two], dim=1), output_whole, atol=1e-5)) - # TODO the orignal mamba does not support decoding more than 1 token neither do we + # TODO the original mamba does not support decoding more than 1 token neither do we def create_and_check_mamba_cached_slow_forward_and_backwards( self, config, input_ids, *args, gradient_checkpointing=False diff --git a/tests/models/marian/test_modeling_marian.py b/tests/models/marian/test_modeling_marian.py index c1fcb77303..8a1e2b4a33 100644 --- a/tests/models/marian/test_modeling_marian.py +++ b/tests/models/marian/test_modeling_marian.py @@ -335,19 +335,19 @@ class MarianModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMix pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/mbart/test_modeling_mbart.py b/tests/models/mbart/test_modeling_mbart.py index 9ff5ef33bd..6920ea9b74 100644 --- a/tests/models/mbart/test_modeling_mbart.py +++ b/tests/models/mbart/test_modeling_mbart.py @@ -368,7 +368,7 @@ class MBartModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixi ) @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/mllama/test_modeling_mllama.py b/tests/models/mllama/test_modeling_mllama.py index 9dcc712346..5c8e5c0e70 100644 --- a/tests/models/mllama/test_modeling_mllama.py +++ b/tests/models/mllama/test_modeling_mllama.py @@ -392,7 +392,7 @@ class MllamaForConditionalGenerationModelTest(ModelTesterMixin, GenerationTester pass @pytest.mark.generate - # overriden because mllama has special cache for self and cross attentions + # overridden because mllama has special cache for self and cross attentions def test_past_key_values_format(self): # Test that the KV cache is formatted correctly. Exceptions need to explicitly overwrite this test. Having a # standard KV cache format is important for a consistent API (and for advanced generation methods). @@ -444,7 +444,7 @@ class MllamaForConditionalGenerationModelTest(ModelTesterMixin, GenerationTester past_kv[i][1].shape, (batch_size, num_attention_heads, seq_length, per_head_embed_dim) ) - # overriden because mllama has special cache for self and cross attentions + # overridden because mllama has special cache for self and cross attentions def _check_past_key_values_for_generate(self, batch_size, decoder_past_key_values, cache_length, config): self.assertIsInstance(decoder_past_key_values, Cache) self.assertListEqual( diff --git a/tests/models/mra/test_modeling_mra.py b/tests/models/mra/test_modeling_mra.py index dfeebf28bc..d096b0a9d5 100644 --- a/tests/models/mra/test_modeling_mra.py +++ b/tests/models/mra/test_modeling_mra.py @@ -359,19 +359,19 @@ class MraModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): return @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/nllb_moe/test_modeling_nllb_moe.py b/tests/models/nllb_moe/test_modeling_nllb_moe.py index b3ae5779bd..8aee844b47 100644 --- a/tests/models/nllb_moe/test_modeling_nllb_moe.py +++ b/tests/models/nllb_moe/test_modeling_nllb_moe.py @@ -353,7 +353,7 @@ class NllbMoeModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMi self.assertIsNotNone(model(**input_dict)["decoder_router_logits"][0]) @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/owlv2/test_modeling_owlv2.py b/tests/models/owlv2/test_modeling_owlv2.py index e6aff1c702..e1278d3c93 100644 --- a/tests/models/owlv2/test_modeling_owlv2.py +++ b/tests/models/owlv2/test_modeling_owlv2.py @@ -196,13 +196,13 @@ class Owlv2VisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -340,13 +340,13 @@ class Owlv2TextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -702,13 +702,13 @@ class Owlv2ForObjectDetectionTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/owlvit/test_modeling_owlvit.py b/tests/models/owlvit/test_modeling_owlvit.py index 81034df4cb..315cdf813a 100644 --- a/tests/models/owlvit/test_modeling_owlvit.py +++ b/tests/models/owlvit/test_modeling_owlvit.py @@ -194,13 +194,13 @@ class OwlViTVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -336,13 +336,13 @@ class OwlViTTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -695,13 +695,13 @@ class OwlViTForObjectDetectionTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/paligemma/test_modeling_paligemma.py b/tests/models/paligemma/test_modeling_paligemma.py index 570ccf3742..b05998d1d0 100644 --- a/tests/models/paligemma/test_modeling_paligemma.py +++ b/tests/models/paligemma/test_modeling_paligemma.py @@ -243,7 +243,7 @@ class PaliGemmaForConditionalGenerationModelTest(ModelTesterMixin, GenerationTes config, input_dict = self.model_tester.prepare_config_and_inputs_for_common() for model_class in self.all_model_classes: model = model_class(config).to(torch_device) - _ = model(**input_dict) # successfull forward with no modifications + _ = model(**input_dict) # successful forward with no modifications # remove one image but leave the image token in text input_dict["pixel_values"] = input_dict["pixel_values"][-1:, ...] @@ -264,19 +264,19 @@ class PaliGemmaForConditionalGenerationModelTest(ModelTesterMixin, GenerationTes _ = model(input_ids=input_ids, pixel_values=pixel_values) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/paligemma2/test_modeling_paligemma2.py b/tests/models/paligemma2/test_modeling_paligemma2.py index 8eb9c9a2d9..a905d48350 100644 --- a/tests/models/paligemma2/test_modeling_paligemma2.py +++ b/tests/models/paligemma2/test_modeling_paligemma2.py @@ -239,7 +239,7 @@ class PaliGemma2ForConditionalGenerationModelTest(ModelTesterMixin, GenerationTe config, input_dict = self.model_tester.prepare_config_and_inputs_for_common() for model_class in self.all_model_classes: model = model_class(config).to(torch_device) - _ = model(**input_dict) # successfull forward with no modifications + _ = model(**input_dict) # successful forward with no modifications # remove one image but leave the image token in text input_dict["pixel_values"] = input_dict["pixel_values"][-1:, ...] @@ -260,19 +260,19 @@ class PaliGemma2ForConditionalGenerationModelTest(ModelTesterMixin, GenerationTe _ = model(input_ids=input_ids, pixel_values=pixel_values) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/pegasus/test_modeling_pegasus.py b/tests/models/pegasus/test_modeling_pegasus.py index 90e0fcaabc..b4367ff79b 100644 --- a/tests/models/pegasus/test_modeling_pegasus.py +++ b/tests/models/pegasus/test_modeling_pegasus.py @@ -288,19 +288,19 @@ class PegasusModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMi model.generate(num_beams=4, do_sample=True, early_stopping=False, num_return_sequences=3) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/pix2struct/test_modeling_pix2struct.py b/tests/models/pix2struct/test_modeling_pix2struct.py index cbef43f3fb..dd6846ac4c 100644 --- a/tests/models/pix2struct/test_modeling_pix2struct.py +++ b/tests/models/pix2struct/test_modeling_pix2struct.py @@ -197,13 +197,13 @@ class Pix2StructVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -346,13 +346,13 @@ class Pix2StructTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/plbart/test_modeling_plbart.py b/tests/models/plbart/test_modeling_plbart.py index 6a4e5df599..fec49c5559 100644 --- a/tests/models/plbart/test_modeling_plbart.py +++ b/tests/models/plbart/test_modeling_plbart.py @@ -330,7 +330,7 @@ class PLBartModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMix pass @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/reformer/test_modeling_reformer.py b/tests/models/reformer/test_modeling_reformer.py index d7e1e3c691..235db79a9d 100644 --- a/tests/models/reformer/test_modeling_reformer.py +++ b/tests/models/reformer/test_modeling_reformer.py @@ -249,7 +249,7 @@ class ReformerModelTester: model = ReformerModel(config=config) model.to(torch_device) model.eval() - # set all position encodings to zero so that postions don't matter + # set all position encodings to zero so that positions don't matter with torch.no_grad(): embedding = model.embeddings.position_embeddings.embedding embedding.weight = nn.Parameter(torch.zeros(embedding.weight.shape).to(torch_device)) diff --git a/tests/models/reformer/test_tokenization_reformer.py b/tests/models/reformer/test_tokenization_reformer.py index 89f3ef7c4e..cf7599014c 100644 --- a/tests/models/reformer/test_tokenization_reformer.py +++ b/tests/models/reformer/test_tokenization_reformer.py @@ -216,7 +216,7 @@ class ReformerTokenizationTest(TokenizerTesterMixin, unittest.TestCase): def test_tokenization_base_hard_symbols(self): symbols = ( 'This is a very long text with a lot of weird characters, such as: . , ~ ? ( ) " [ ] ! : - . Also we will' - " add words that should not exsist and be tokenized to , such as saoneuhaoesuth" + " add words that should not exist and be tokenized to , such as saoneuhaoesuth" ) original_tokenizer_encodings = [ 108, diff --git a/tests/models/roformer/test_modeling_roformer.py b/tests/models/roformer/test_modeling_roformer.py index abd8cf1dc5..0c11986268 100644 --- a/tests/models/roformer/test_modeling_roformer.py +++ b/tests/models/roformer/test_modeling_roformer.py @@ -486,19 +486,19 @@ class RoFormerModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase self.assertIsNotNone(model) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/sam/test_modeling_sam.py b/tests/models/sam/test_modeling_sam.py index f6d3c4fe4b..3c7e5a34b6 100644 --- a/tests/models/sam/test_modeling_sam.py +++ b/tests/models/sam/test_modeling_sam.py @@ -406,13 +406,13 @@ class SamModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/seamless_m4t/test_modeling_seamless_m4t.py b/tests/models/seamless_m4t/test_modeling_seamless_m4t.py index 558c9f7e4a..25bbc1c304 100644 --- a/tests/models/seamless_m4t/test_modeling_seamless_m4t.py +++ b/tests/models/seamless_m4t/test_modeling_seamless_m4t.py @@ -444,25 +444,25 @@ class SeamlessM4TModelWithSpeechInputTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass @@ -695,19 +695,19 @@ class SeamlessM4TModelWithTextInputTest(ModelTesterMixin, PipelineTesterMixin, u pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -719,7 +719,7 @@ class SeamlessM4TModelWithTextInputTest(ModelTesterMixin, PipelineTesterMixin, u pass @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/seamless_m4t_v2/test_modeling_seamless_m4t_v2.py b/tests/models/seamless_m4t_v2/test_modeling_seamless_m4t_v2.py index ecf5363fd8..c5b10ea34d 100644 --- a/tests/models/seamless_m4t_v2/test_modeling_seamless_m4t_v2.py +++ b/tests/models/seamless_m4t_v2/test_modeling_seamless_m4t_v2.py @@ -460,25 +460,25 @@ class SeamlessM4Tv2ModelWithSpeechInputTest(ModelTesterMixin, unittest.TestCase) pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass @@ -698,25 +698,25 @@ class SeamlessM4Tv2ModelWithTextInputTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/smolvlm/test_modeling_smolvlm.py b/tests/models/smolvlm/test_modeling_smolvlm.py index a0cc898c2c..11a3569f06 100644 --- a/tests/models/smolvlm/test_modeling_smolvlm.py +++ b/tests/models/smolvlm/test_modeling_smolvlm.py @@ -382,13 +382,13 @@ class SmolVLMForConditionalGenerationModelTest(GenerationTesterMixin, ModelTeste pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/speech_to_text/test_modeling_speech_to_text.py b/tests/models/speech_to_text/test_modeling_speech_to_text.py index 2edc283fc1..bcd76a87e9 100644 --- a/tests/models/speech_to_text/test_modeling_speech_to_text.py +++ b/tests/models/speech_to_text/test_modeling_speech_to_text.py @@ -324,13 +324,13 @@ class Speech2TextModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTest pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/speech_to_text/test_modeling_tf_speech_to_text.py b/tests/models/speech_to_text/test_modeling_tf_speech_to_text.py index dc7eec0dca..1c80e666d0 100644 --- a/tests/models/speech_to_text/test_modeling_tf_speech_to_text.py +++ b/tests/models/speech_to_text/test_modeling_tf_speech_to_text.py @@ -247,13 +247,13 @@ class TFSpeech2TextModelTest(TFModelTesterMixin, PipelineTesterMixin, unittest.T pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/speecht5/test_modeling_speecht5.py b/tests/models/speecht5/test_modeling_speecht5.py index f133099ef7..3c316dfee2 100644 --- a/tests/models/speecht5/test_modeling_speecht5.py +++ b/tests/models/speecht5/test_modeling_speecht5.py @@ -704,13 +704,13 @@ class SpeechT5ForSpeechToTextTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -1021,13 +1021,13 @@ class SpeechT5ForTextToSpeechTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -1723,13 +1723,13 @@ class SpeechT5ForSpeechToSpeechTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/swin2sr/test_modeling_swin2sr.py b/tests/models/swin2sr/test_modeling_swin2sr.py index 3752f6ef30..5310835e98 100644 --- a/tests/models/swin2sr/test_modeling_swin2sr.py +++ b/tests/models/swin2sr/test_modeling_swin2sr.py @@ -213,13 +213,13 @@ class Swin2SRModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase) pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/switch_transformers/test_modeling_switch_transformers.py b/tests/models/switch_transformers/test_modeling_switch_transformers.py index cb62d364c1..622c579843 100644 --- a/tests/models/switch_transformers/test_modeling_switch_transformers.py +++ b/tests/models/switch_transformers/test_modeling_switch_transformers.py @@ -694,7 +694,7 @@ class SwitchTransformersModelTest(ModelTesterMixin, GenerationTesterMixin, Pipel config_and_inputs = self.model_tester.prepare_config_and_inputs() self.model_tester.create_and_check_encoder_decoder_shared_weights(*config_and_inputs) - @unittest.skipIf(torch_device == "cpu", "Cant do half precision") + @unittest.skipIf(torch_device == "cpu", "Can't do half precision") def test_model_fp16_forward(self): config_and_inputs = self.model_tester.prepare_config_and_inputs() self.model_tester.create_and_check_model_fp16_forward(*config_and_inputs) @@ -744,7 +744,7 @@ class SwitchTransformersModelTest(ModelTesterMixin, GenerationTesterMixin, Pipel self.assertEqual(sum([w.sum().item() for w in attn_weights]), 0.0) @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass @@ -867,13 +867,13 @@ class SwitchTransformersEncoderOnlyModelTest(ModelTesterMixin, unittest.TestCase config_and_inputs = self.model_tester.prepare_config_and_inputs() self.model_tester.create_and_check_model(*config_and_inputs) - @unittest.skipIf(torch_device == "cpu", "Cant do half precision") + @unittest.skipIf(torch_device == "cpu", "Can't do half precision") def test_model_fp16_forward(self): config_and_inputs = self.model_tester.prepare_config_and_inputs() self.model_tester.create_and_check_model_fp16_forward(*config_and_inputs) @unittest.skip( - reason="This architecure has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" + reason="This architecture has tied weights by default and there is no way to remove it, check: https://github.com/huggingface/transformers/pull/31771#issuecomment-2210915245" ) def test_load_save_without_tied_weights(self): pass diff --git a/tests/models/time_series_transformer/test_modeling_time_series_transformer.py b/tests/models/time_series_transformer/test_modeling_time_series_transformer.py index 8dcdfd8ae7..50abfaa765 100644 --- a/tests/models/time_series_transformer/test_modeling_time_series_transformer.py +++ b/tests/models/time_series_transformer/test_modeling_time_series_transformer.py @@ -369,19 +369,19 @@ class TimeSeriesTransformerModelTest(ModelTesterMixin, PipelineTesterMixin, unit ) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/udop/test_modeling_udop.py b/tests/models/udop/test_modeling_udop.py index 0c12795990..c5f485d797 100644 --- a/tests/models/udop/test_modeling_udop.py +++ b/tests/models/udop/test_modeling_udop.py @@ -330,13 +330,13 @@ class UdopModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/umt5/test_modeling_umt5.py b/tests/models/umt5/test_modeling_umt5.py index c274efcf93..6a5e3957b7 100644 --- a/tests/models/umt5/test_modeling_umt5.py +++ b/tests/models/umt5/test_modeling_umt5.py @@ -564,19 +564,19 @@ class UMT5ModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMixin self.assertEqual(sum([w.sum().item() for w in attn_weights]), 0.0) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/video_llava/test_modeling_video_llava.py b/tests/models/video_llava/test_modeling_video_llava.py index 528f125693..d46b1ae111 100644 --- a/tests/models/video_llava/test_modeling_video_llava.py +++ b/tests/models/video_llava/test_modeling_video_llava.py @@ -209,19 +209,19 @@ class VideoLlavaForConditionalGenerationModelTest(ModelTesterMixin, GenerationTe self.config_tester.run_common_tests() @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/vilt/test_modeling_vilt.py b/tests/models/vilt/test_modeling_vilt.py index 7977d6298f..f85a851dd0 100644 --- a/tests/models/vilt/test_modeling_vilt.py +++ b/tests/models/vilt/test_modeling_vilt.py @@ -319,13 +319,13 @@ class ViltModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase): loss.backward() @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/vipllava/test_modeling_vipllava.py b/tests/models/vipllava/test_modeling_vipllava.py index 24f99d4b0b..8c8b3ea4df 100644 --- a/tests/models/vipllava/test_modeling_vipllava.py +++ b/tests/models/vipllava/test_modeling_vipllava.py @@ -237,7 +237,7 @@ class VipLlavaForConditionalGenerationModelTest(ModelTesterMixin, GenerationTest config, input_dict = self.model_tester.prepare_config_and_inputs_for_common() for model_class in self.all_model_classes: model = model_class(config).to(torch_device) - _ = model(**input_dict) # successfull forward with no modifications + _ = model(**input_dict) # successful forward with no modifications # remove one image but leave the image token in text input_dict["pixel_values"] = input_dict["pixel_values"][-1:, ...] @@ -289,19 +289,19 @@ class VipLlavaForConditionalGenerationModelTest(ModelTesterMixin, GenerationTest model(**input_dict) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/visual_bert/test_modeling_visual_bert.py b/tests/models/visual_bert/test_modeling_visual_bert.py index 5517f3e22e..1c32f26a62 100644 --- a/tests/models/visual_bert/test_modeling_visual_bert.py +++ b/tests/models/visual_bert/test_modeling_visual_bert.py @@ -555,19 +555,19 @@ class VisualBertModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCa self.assertIsNotNone(model) @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/vitmatte/test_modeling_vitmatte.py b/tests/models/vitmatte/test_modeling_vitmatte.py index 035e1a65b8..5abbc77413 100644 --- a/tests/models/vitmatte/test_modeling_vitmatte.py +++ b/tests/models/vitmatte/test_modeling_vitmatte.py @@ -171,13 +171,13 @@ class VitMatteModelTest(ModelTesterMixin, PipelineTesterMixin, unittest.TestCase pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/wav2vec2/test_modeling_flax_wav2vec2.py b/tests/models/wav2vec2/test_modeling_flax_wav2vec2.py index e888cc5ff3..3dadab891e 100644 --- a/tests/models/wav2vec2/test_modeling_flax_wav2vec2.py +++ b/tests/models/wav2vec2/test_modeling_flax_wav2vec2.py @@ -412,7 +412,7 @@ class FlaxWav2Vec2UtilsTest(unittest.TestCase): features = (np.arange(sequence_length * hidden_size) // hidden_size).reshape( sequence_length, hidden_size - ) # each value in vector consits of same value + ) # each value in vector consists of same value features = np.broadcast_to(features[None, :], (batch_size, sequence_length, hidden_size)) negative_indices = _sample_negative_indices(features.shape, num_negatives) @@ -442,7 +442,7 @@ class FlaxWav2Vec2UtilsTest(unittest.TestCase): features = (np.arange(sequence_length * hidden_size) // hidden_size).reshape( sequence_length, hidden_size - ) # each value in vector consits of same value + ) # each value in vector consists of same value # second half of last input tensor is padded attention_mask = np.ones((batch_size, sequence_length), dtype=np.int8) diff --git a/tests/models/wav2vec2/test_modeling_wav2vec2.py b/tests/models/wav2vec2/test_modeling_wav2vec2.py index e71c2d677a..8199ba04e1 100644 --- a/tests/models/wav2vec2/test_modeling_wav2vec2.py +++ b/tests/models/wav2vec2/test_modeling_wav2vec2.py @@ -1392,7 +1392,7 @@ class Wav2Vec2UtilsTest(unittest.TestCase): sequence = torch.div( torch.arange(sequence_length * hidden_size, device=torch_device), hidden_size, rounding_mode="floor" ) - features = sequence.view(sequence_length, hidden_size) # each value in vector consits of same value + features = sequence.view(sequence_length, hidden_size) # each value in vector consists of same value features = features[None, :].expand(batch_size, sequence_length, hidden_size).contiguous() # sample negative indices @@ -1422,7 +1422,7 @@ class Wav2Vec2UtilsTest(unittest.TestCase): sequence = torch.div( torch.arange(sequence_length * hidden_size, device=torch_device), hidden_size, rounding_mode="floor" ) - features = sequence.view(sequence_length, hidden_size) # each value in vector consits of same value + features = sequence.view(sequence_length, hidden_size) # each value in vector consists of same value features = features[None, :].expand(batch_size, sequence_length, hidden_size).contiguous() # replace masked feature vectors with -100 to test that those are not sampled diff --git a/tests/models/wav2vec2_bert/test_modeling_wav2vec2_bert.py b/tests/models/wav2vec2_bert/test_modeling_wav2vec2_bert.py index fc563df8f1..0bcdcf3e05 100644 --- a/tests/models/wav2vec2_bert/test_modeling_wav2vec2_bert.py +++ b/tests/models/wav2vec2_bert/test_modeling_wav2vec2_bert.py @@ -782,7 +782,7 @@ class Wav2Vec2BertUtilsTest(unittest.TestCase): features = (torch.arange(sequence_length * hidden_size, device=torch_device) // hidden_size).view( sequence_length, hidden_size - ) # each value in vector consits of same value + ) # each value in vector consists of same value features = features[None, :].expand(batch_size, sequence_length, hidden_size).contiguous() # sample negative indices @@ -811,7 +811,7 @@ class Wav2Vec2BertUtilsTest(unittest.TestCase): features = (torch.arange(sequence_length * hidden_size, device=torch_device) // hidden_size).view( sequence_length, hidden_size - ) # each value in vector consits of same value + ) # each value in vector consists of same value features = features[None, :].expand(batch_size, sequence_length, hidden_size).contiguous() # replace masked feature vectors with -100 to test that those are not sampled diff --git a/tests/models/wav2vec2_conformer/test_modeling_wav2vec2_conformer.py b/tests/models/wav2vec2_conformer/test_modeling_wav2vec2_conformer.py index 0c406bfbc8..0173135d52 100644 --- a/tests/models/wav2vec2_conformer/test_modeling_wav2vec2_conformer.py +++ b/tests/models/wav2vec2_conformer/test_modeling_wav2vec2_conformer.py @@ -800,7 +800,7 @@ class Wav2Vec2ConformerUtilsTest(unittest.TestCase): features = (torch.arange(sequence_length * hidden_size, device=torch_device) // hidden_size).view( sequence_length, hidden_size - ) # each value in vector consits of same value + ) # each value in vector consists of same value features = features[None, :].expand(batch_size, sequence_length, hidden_size).contiguous() # sample negative indices @@ -829,7 +829,7 @@ class Wav2Vec2ConformerUtilsTest(unittest.TestCase): features = (torch.arange(sequence_length * hidden_size, device=torch_device) // hidden_size).view( sequence_length, hidden_size - ) # each value in vector consits of same value + ) # each value in vector consists of same value features = features[None, :].expand(batch_size, sequence_length, hidden_size).contiguous() # replace masked feature vectors with -100 to test that those are not sampled diff --git a/tests/models/whisper/test_modeling_whisper.py b/tests/models/whisper/test_modeling_whisper.py index 9f17c026b3..a05e31bf93 100644 --- a/tests/models/whisper/test_modeling_whisper.py +++ b/tests/models/whisper/test_modeling_whisper.py @@ -546,13 +546,13 @@ class WhisperModelTest(ModelTesterMixin, GenerationTesterMixin, PipelineTesterMi pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/models/x_clip/test_modeling_x_clip.py b/tests/models/x_clip/test_modeling_x_clip.py index 80ee63fb15..8526558905 100644 --- a/tests/models/x_clip/test_modeling_x_clip.py +++ b/tests/models/x_clip/test_modeling_x_clip.py @@ -195,13 +195,13 @@ class XCLIPVisionModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass @@ -431,13 +431,13 @@ class XCLIPTextModelTest(ModelTesterMixin, unittest.TestCase): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant(self): pass @unittest.skip( - reason="This architecure seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" + reason="This architecture seem to not compute gradients properly when using GC, check: https://github.com/huggingface/transformers/pull/27124" ) def test_training_gradient_checkpointing_use_reentrant_false(self): pass diff --git a/tests/pipelines/test_pipelines_common.py b/tests/pipelines/test_pipelines_common.py index baee899928..7d9bc428ed 100644 --- a/tests/pipelines/test_pipelines_common.py +++ b/tests/pipelines/test_pipelines_common.py @@ -251,7 +251,7 @@ class CommonPipelineTest(unittest.TestCase): self.assertTrue(model.generation_config.num_beams == 1) # Under the hood: we now store a generation config in the pipeline. This generation config stores the - # task-specific paremeters. + # task-specific parameters. self.assertTrue(pipe.generation_config.num_beams == 4) # We can confirm that the task-specific parameters have an effect. (In this case, the default is `num_beams=1`, diff --git a/tests/pipelines/test_pipelines_document_question_answering.py b/tests/pipelines/test_pipelines_document_question_answering.py index 85d528ce91..17f3b9adb9 100644 --- a/tests/pipelines/test_pipelines_document_question_answering.py +++ b/tests/pipelines/test_pipelines_document_question_answering.py @@ -147,7 +147,7 @@ class DocumentQuestionAnsweringPipelineTests(unittest.TestCase): outputs = dqa_pipeline(image=image, question=question, top_k=2) self.assertEqual(outputs, []) - # We can optionnally pass directly the words and bounding boxes + # We can optionally pass directly the words and bounding boxes image = "./tests/fixtures/tests_samples/COCO/000000039769.png" words = [] boxes = [] @@ -183,7 +183,7 @@ class DocumentQuestionAnsweringPipelineTests(unittest.TestCase): outputs = dqa_pipeline(image=image, question=question, top_k=2) self.assertEqual(outputs, []) - # We can optionnally pass directly the words and bounding boxes + # We can optionally pass directly the words and bounding boxes image = "./tests/fixtures/tests_samples/COCO/000000039769.png" words = [] boxes = [] diff --git a/tests/pipelines/test_pipelines_feature_extraction.py b/tests/pipelines/test_pipelines_feature_extraction.py index bceb48d6ff..12bc3dc655 100644 --- a/tests/pipelines/test_pipelines_feature_extraction.py +++ b/tests/pipelines/test_pipelines_feature_extraction.py @@ -196,7 +196,7 @@ class FeatureExtractionPipelineTests(unittest.TestCase): elif model.config.is_encoder_decoder: self.skipTest( """encoder_decoder models are trickier for this pipeline. - Do we want encoder + decoder inputs to get some featues? + Do we want encoder + decoder inputs to get some features? Do we want encoder only features ? For now ignore those. """ diff --git a/tests/pipelines/test_pipelines_image_feature_extraction.py b/tests/pipelines/test_pipelines_image_feature_extraction.py index 67140f9122..d5d441bda6 100644 --- a/tests/pipelines/test_pipelines_image_feature_extraction.py +++ b/tests/pipelines/test_pipelines_image_feature_extraction.py @@ -177,7 +177,7 @@ class ImageFeatureExtractionPipelineTests(unittest.TestCase): elif model.config.is_encoder_decoder: self.skipTest( """encoder_decoder models are trickier for this pipeline. - Do we want encoder + decoder inputs to get some featues? + Do we want encoder + decoder inputs to get some features? Do we want encoder only features ? For now ignore those. """ diff --git a/tests/pipelines/test_pipelines_question_answering.py b/tests/pipelines/test_pipelines_question_answering.py index bf4fc7db1d..9b061032ea 100644 --- a/tests/pipelines/test_pipelines_question_answering.py +++ b/tests/pipelines/test_pipelines_question_answering.py @@ -347,7 +347,7 @@ class QAPipelineTests(unittest.TestCase): " Yes Bank a loss of ₹ 1,800 crore by extending credit facilities to Avantha Group, when it was" " not eligible for the same" ), - "question": "Is this person invovled in fraud?", + "question": "Is this person involved in fraud?", } ) self.assertEqual( diff --git a/tests/pipelines/test_pipelines_text_classification.py b/tests/pipelines/test_pipelines_text_classification.py index 23625f0d77..b3e25dbe23 100644 --- a/tests/pipelines/test_pipelines_text_classification.py +++ b/tests/pipelines/test_pipelines_text_classification.py @@ -109,7 +109,7 @@ class TextClassificationPipelineTests(unittest.TestCase): ) # Do not apply any function to output for regression tasks - # hack: changing problem_type artifically (so keep this test at last) + # hack: changing problem_type artificially (so keep this test at last) text_classifier.model.config.problem_type = "regression" outputs = text_classifier("This is great !") self.assertEqual(nested_simplify(outputs), [{"label": "LABEL_0", "score": 0.01}]) diff --git a/tests/pipelines/test_pipelines_text_generation.py b/tests/pipelines/test_pipelines_text_generation.py index 5c5d3de17a..9df47d5a22 100644 --- a/tests/pipelines/test_pipelines_text_generation.py +++ b/tests/pipelines/test_pipelines_text_generation.py @@ -500,7 +500,7 @@ class TextGenerationPipelineTests(unittest.TestCase): with self.assertRaises(ValueError): outputs = text_generator("test", return_text=True, return_tensors=True) - # Empty prompt is slighly special + # Empty prompt is slightly special # it requires BOS token to exist. # Special case for Pegasus which will always append EOS so will # work even without BOS. @@ -637,7 +637,7 @@ class TextGenerationPipelineTests(unittest.TestCase): logger = logging.get_logger("transformers.generation.tf_utils") else: logger = logging.get_logger("transformers.generation.utils") - logger_msg = "Both `max_new_tokens`" # The beggining of the message to be checked in this test + logger_msg = "Both `max_new_tokens`" # The beginning of the message to be checked in this test # Both are set by the user -> log warning with CaptureLogger(logger) as cl: diff --git a/tests/test_configuration_common.py b/tests/test_configuration_common.py index 4dbbdedbbc..d37dd92c71 100644 --- a/tests/test_configuration_common.py +++ b/tests/test_configuration_common.py @@ -118,7 +118,7 @@ class ConfigTester: def create_and_test_config_from_and_save_pretrained_composite(self): """ - Tests that composite or nested cofigs can be loaded and saved correctly. In case the config + Tests that composite or nested configs can be loaded and saved correctly. In case the config has a sub-config, we should be able to call `sub_config.from_pretrained('general_config_file')` and get a result same as if we loaded the whole config and obtained `config.sub_config` from it. """ diff --git a/tests/test_image_processing_common.py b/tests/test_image_processing_common.py index cd11c4ac01..0df30adada 100644 --- a/tests/test_image_processing_common.py +++ b/tests/test_image_processing_common.py @@ -392,7 +392,7 @@ class ImageProcessingTestMixin: image_inputs = self.image_processor_tester.prepare_image_inputs(equal_resolution=False, torchify=True) encoding = image_processor(image_inputs, return_tensors="pt") - # for layoutLM compatiblity + # for layoutLM compatibility self.assertEqual(encoding.pixel_values.device, torch.device("cpu")) self.assertEqual(encoding.pixel_values.dtype, torch.float32) diff --git a/tests/test_modeling_common.py b/tests/test_modeling_common.py index bb6f14ce3d..0c0005d828 100755 --- a/tests/test_modeling_common.py +++ b/tests/test_modeling_common.py @@ -1490,7 +1490,7 @@ class ModelTesterMixin: if model.config.is_encoder_decoder: signature = inspect.signature(model.forward) arg_names = [*signature.parameters.keys()] - if "decoder_head_mask" in arg_names: # necessary diferentiation because of T5 model + if "decoder_head_mask" in arg_names: # necessary differentiation because of T5 model inputs["decoder_head_mask"] = head_mask if "cross_attn_head_mask" in arg_names: inputs["cross_attn_head_mask"] = head_mask @@ -1852,7 +1852,7 @@ class ModelTesterMixin: cloned_embeddings = model_embed.weight.clone() # Check that resizing the position embeddings with a larger max_position_embeddings increases - # the model's postion embeddings size + # the model's position embeddings size model.resize_position_embeddings(max_position_embeddings + 10) self.assertEqual(model.config.max_position_embeddings, max_position_embeddings + 10) @@ -3998,7 +3998,7 @@ class ModelTesterMixin: config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common() model = model_class(config) if not self._is_composite: - self.skipTest("This model is not a composte model!") + self.skipTest("This model is not a composite model!") with tempfile.TemporaryDirectory() as tmpdirname: model.save_pretrained(tmpdirname) @@ -4411,9 +4411,9 @@ class ModelTesterMixin: exported_outputs = exported_model.module().forward(**inputs_dict) # Check if outputs are close: - # is_tested is a boolean flag idicating if we comapre any outputs, + # is_tested is a boolean flag indicating if we compare any outputs, # e.g. there might be a situation when outputs are empty list, then is_tested will be False. - # In case of outputs are different the error will be rasied in `recursively_check` function. + # In case of outputs are different the error will be raised in `recursively_check` function. is_tested = recursively_check(eager_outputs, exported_outputs) self.assertTrue(is_tested, msg=f"No outputs were compared for {model_class.__name__}") diff --git a/tests/test_modeling_flax_common.py b/tests/test_modeling_flax_common.py index ab126357f5..82cbf0901c 100644 --- a/tests/test_modeling_flax_common.py +++ b/tests/test_modeling_flax_common.py @@ -680,14 +680,14 @@ class FlaxModelTesterMixin: for model_class in self.all_model_classes: model = model_class(config, _do_init=False) - # Check that accesing parmas raises an ValueError when _do_init is False + # Check that accessing params raises an ValueError when _do_init is False with self.assertRaises(ValueError): params = model.params # Check if we params can be properly initialized when calling init_weights params = model.init_weights(model.key, model.input_shape) assert isinstance(params, (dict, FrozenDict)), f"params are not an instance of {FrozenDict}" - # Check if all required parmas are initialized + # Check if all required params are initialized keys = set(flatten_dict(unfreeze(params)).keys()) self.assertTrue(all(k in keys for k in model.required_params)) # Check if the shapes match @@ -713,7 +713,7 @@ class FlaxModelTesterMixin: config.return_dict = True def _assert_all_params_initialised(model, params): - # Check if all required parmas are loaded + # Check if all required params are loaded keys = set(flatten_dict(unfreeze(params)).keys()) self.assertTrue(all(k in keys for k in model.required_params)) # Check if the shapes match @@ -735,11 +735,11 @@ class FlaxModelTesterMixin: model.save_pretrained(tmpdirname) model, params = model_class.from_pretrained(tmpdirname, _do_init=False) - # Check that accesing parmas raises an ValueError when _do_init is False + # Check that accessing params raises an ValueError when _do_init is False with self.assertRaises(ValueError): params = model.params - # Check if all required parmas are loaded + # Check if all required params are loaded _assert_all_params_initialised(model, params) # Check that setting params raises an ValueError when _do_init is False @@ -757,7 +757,7 @@ class FlaxModelTesterMixin: model, params = model_class.from_pretrained(tmpdirname, _do_init=False) params = model.init_weights(model.key, model.input_shape, params=params) - # Check if all required parmas are loaded + # Check if all required params are loaded _assert_all_params_initialised(model, params) def test_checkpoint_sharding_from_hub(self): diff --git a/tests/test_tokenization_common.py b/tests/test_tokenization_common.py index f7263dcb81..f5723d5832 100644 --- a/tests/test_tokenization_common.py +++ b/tests/test_tokenization_common.py @@ -838,7 +838,7 @@ class TokenizerTesterMixin: toks_after_adding = tokenizer.tokenize(text) toks_after_adding2 = tokenizer.tokenize(text2) - # Rust tokenizers dont't lowercase added tokens at the time calling `tokenizer.add_tokens`, + # Rust tokenizers don't lowercase added tokens at the time calling `tokenizer.add_tokens`, # while python tokenizers do, so new_toks 0 and 2 would be treated as the same, so do new_toks 1 and 3. self.assertIn(added, [2, 4])