From be6cdace1b54dd14e1254d9ca9ac5cd784dc67be Mon Sep 17 00:00:00 2001
From: "[[ -z $EMAIL ]] && read -e -p \"Enter your email (for git
 configuration): \" EMAIL" <muellerzr@gmail.com>
Date: Thu, 30 Jan 2025 09:22:52 -0500
Subject: [PATCH] Rm file

---
 test_modeling_names.txt | 366 ----------------------------------------
 1 file changed, 366 deletions(-)
 delete mode 100644 test_modeling_names.txt

diff --git a/test_modeling_names.txt b/test_modeling_names.txt
deleted file mode 100644
index 3387a15c20c9..000000000000
--- a/test_modeling_names.txt
+++ /dev/null
@@ -1,366 +0,0 @@
-tests/models/albert/test_modeling_albert.py::AlbertModelTest::test_training_gradient_accumulation
-tests/models/align/test_modeling_align.py::AlignVisionModelTest::test_training_gradient_accumulation
-tests/models/align/test_modeling_align.py::AlignTextModelTest::test_training_gradient_accumulation
-tests/models/align/test_modeling_align.py::AlignModelTest::test_training_gradient_accumulation
-tests/models/altclip/test_modeling_altclip.py::AltCLIPVisionModelTest::test_training_gradient_accumulation
-tests/models/altclip/test_modeling_altclip.py::AltCLIPTextModelTest::test_training_gradient_accumulation
-tests/models/altclip/test_modeling_altclip.py::AltCLIPModelTest::test_training_gradient_accumulation
-tests/models/aria/test_modeling_aria.py::AriaForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/audio_spectrogram_transformer/test_modeling_audio_spectrogram_transformer.py::ASTModelTest::test_training_gradient_accumulation
-tests/models/autoformer/test_modeling_autoformer.py::AutoformerModelTest::test_training_gradient_accumulation
-tests/models/bamba/test_modeling_bamba.py::BambaModelTest::test_training_gradient_accumulation
-tests/models/bark/test_modeling_bark.py::BarkSemanticModelTest::test_training_gradient_accumulation
-tests/models/bark/test_modeling_bark.py::BarkCoarseModelTest::test_training_gradient_accumulation
-tests/models/bark/test_modeling_bark.py::BarkFineModelTest::test_training_gradient_accumulation
-tests/models/bart/test_modeling_bart.py::BartModelTest::test_training_gradient_accumulation
-tests/models/bart/test_modeling_bart.py::BartStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/beit/test_modeling_beit.py::BeitModelTest::test_training_gradient_accumulation
-tests/models/bert/test_modeling_bert.py::BertModelTest::test_training_gradient_accumulation
-tests/models/bert_generation/test_modeling_bert_generation.py::BertGenerationEncoderTest::test_training_gradient_accumulation
-tests/models/big_bird/test_modeling_big_bird.py::BigBirdModelTest::test_training_gradient_accumulation
-tests/models/bigbird_pegasus/test_modeling_bigbird_pegasus.py::BigBirdPegasusModelTest::test_training_gradient_accumulation
-tests/models/bigbird_pegasus/test_modeling_bigbird_pegasus.py::BigBirdPegasusStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/biogpt/test_modeling_biogpt.py::BioGptModelTest::test_training_gradient_accumulation
-tests/models/bit/test_modeling_bit.py::BitModelTest::test_training_gradient_accumulation
-tests/models/blenderbot/test_modeling_blenderbot.py::BlenderbotModelTest::test_training_gradient_accumulation
-tests/models/blenderbot/test_modeling_blenderbot.py::BlenderbotStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/blenderbot_small/test_modeling_blenderbot_small.py::BlenderbotSmallModelTest::test_training_gradient_accumulation
-tests/models/blenderbot_small/test_modeling_blenderbot_small.py::BlenderbotSmallStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/blip/test_modeling_blip.py::BlipVisionModelTest::test_training_gradient_accumulation
-tests/models/blip/test_modeling_blip.py::BlipTextModelTest::test_training_gradient_accumulation
-tests/models/blip/test_modeling_blip.py::BlipModelTest::test_training_gradient_accumulation
-tests/models/blip/test_modeling_blip.py::BlipVQAModelTest::test_training_gradient_accumulation
-tests/models/blip/test_modeling_blip.py::BlipTextRetrievalModelTest::test_training_gradient_accumulation
-tests/models/blip/test_modeling_blip.py::BlipTextImageModelTest::test_training_gradient_accumulation
-tests/models/blip/test_modeling_blip_text.py::BlipTextModelTest::test_training_gradient_accumulation
-tests/models/blip_2/test_modeling_blip_2.py::Blip2VisionModelTest::test_training_gradient_accumulation
-tests/models/blip_2/test_modeling_blip_2.py::Blip2ForConditionalGenerationDecoderOnlyTest::test_training_gradient_accumulation
-tests/models/blip_2/test_modeling_blip_2.py::Blip2ModelTest::test_training_gradient_accumulation
-tests/models/blip_2/test_modeling_blip_2.py::Blip2TextModelWithProjectionTest::test_training_gradient_accumulation
-tests/models/blip_2/test_modeling_blip_2.py::Blip2VisionModelWithProjectionTest::test_training_gradient_accumulation
-tests/models/blip_2/test_modeling_blip_2.py::Blip2TextRetrievalModelTest::test_training_gradient_accumulation
-tests/models/bloom/test_modeling_bloom.py::BloomModelTest::test_training_gradient_accumulation
-tests/models/bridgetower/test_modeling_bridgetower.py::BridgeTowerModelTest::test_training_gradient_accumulation
-tests/models/bros/test_modeling_bros.py::BrosModelTest::test_training_gradient_accumulation
-tests/models/canine/test_modeling_canine.py::CanineModelTest::test_training_gradient_accumulation
-tests/models/chameleon/test_modeling_chameleon.py::ChameleonModelTest::test_training_gradient_accumulation
-tests/models/chinese_clip/test_modeling_chinese_clip.py::ChineseCLIPTextModelTest::test_training_gradient_accumulation
-tests/models/chinese_clip/test_modeling_chinese_clip.py::ChineseCLIPVisionModelTest::test_training_gradient_accumulation
-tests/models/chinese_clip/test_modeling_chinese_clip.py::ChineseCLIPModelTest::test_training_gradient_accumulation
-tests/models/clap/test_modeling_clap.py::ClapAudioModelTest::test_training_gradient_accumulation
-tests/models/clap/test_modeling_clap.py::ClapTextModelTest::test_training_gradient_accumulation
-tests/models/clap/test_modeling_clap.py::ClapModelTest::test_training_gradient_accumulation
-tests/models/clip/test_modeling_clip.py::CLIPVisionModelTest::test_training_gradient_accumulation
-tests/models/clip/test_modeling_clip.py::CLIPTextModelTest::test_training_gradient_accumulation
-tests/models/clip/test_modeling_clip.py::CLIPModelTest::test_training_gradient_accumulation
-tests/models/clip/test_modeling_clip.py::CLIPForImageClassificationModelTest::test_training_gradient_accumulation
-tests/models/clipseg/test_modeling_clipseg.py::CLIPSegVisionModelTest::test_training_gradient_accumulation
-tests/models/clipseg/test_modeling_clipseg.py::CLIPSegTextModelTest::test_training_gradient_accumulation
-tests/models/clipseg/test_modeling_clipseg.py::CLIPSegModelTest::test_training_gradient_accumulation
-tests/models/clvp/test_modeling_clvp.py::ClvpEncoderTest::test_training_gradient_accumulation
-tests/models/clvp/test_modeling_clvp.py::ClvpDecoderTest::test_training_gradient_accumulation
-tests/models/clvp/test_modeling_clvp.py::ClvpModelForConditionalGenerationTest::test_training_gradient_accumulation
-tests/models/codegen/test_modeling_codegen.py::CodeGenModelTest::test_training_gradient_accumulation
-tests/models/cohere/test_modeling_cohere.py::CohereModelTest::test_training_gradient_accumulation
-tests/models/cohere2/test_modeling_cohere2.py::CohereModelTest::test_training_gradient_accumulation
-tests/models/cohere2/test_modeling_cohere2.py::Cohere2ModelTest::test_training_gradient_accumulation
-tests/models/colpali/test_modeling_colpali.py::ColPaliForRetrievalModelTest::test_training_gradient_accumulation
-tests/models/conditional_detr/test_modeling_conditional_detr.py::ConditionalDetrModelTest::test_training_gradient_accumulation
-tests/models/convbert/test_modeling_convbert.py::ConvBertModelTest::test_training_gradient_accumulation
-tests/models/convnext/test_modeling_convnext.py::ConvNextModelTest::test_training_gradient_accumulation
-tests/models/convnextv2/test_modeling_convnextv2.py::ConvNextV2ModelTest::test_training_gradient_accumulation
-tests/models/cpmant/test_modeling_cpmant.py::CpmAntModelTest::test_training_gradient_accumulation
-tests/models/ctrl/test_modeling_ctrl.py::CTRLModelTest::test_training_gradient_accumulation
-tests/models/cvt/test_modeling_cvt.py::CvtModelTest::test_training_gradient_accumulation
-tests/models/dac/test_modeling_dac.py::DacModelTest::test_training_gradient_accumulation
-tests/models/data2vec/test_modeling_data2vec_audio.py::Data2VecAudioModelTest::test_training_gradient_accumulation
-tests/models/data2vec/test_modeling_data2vec_text.py::Data2VecTextModelTest::test_training_gradient_accumulation
-tests/models/data2vec/test_modeling_data2vec_vision.py::Data2VecVisionModelTest::test_training_gradient_accumulation
-tests/models/dbrx/test_modeling_dbrx.py::DbrxModelTest::test_training_gradient_accumulation
-tests/models/deberta/test_modeling_deberta.py::DebertaModelTest::test_training_gradient_accumulation
-tests/models/deberta_v2/test_modeling_deberta_v2.py::DebertaV2ModelTest::test_training_gradient_accumulation
-tests/models/decision_transformer/test_modeling_decision_transformer.py::DecisionTransformerModelTest::test_training_gradient_accumulation
-tests/models/deformable_detr/test_modeling_deformable_detr.py::DeformableDetrModelTest::test_training_gradient_accumulation
-tests/models/deit/test_modeling_deit.py::DeiTModelTest::test_training_gradient_accumulation
-tests/models/depth_anything/test_modeling_depth_anything.py::DepthAnythingModelTest::test_training_gradient_accumulation
-tests/models/detr/test_modeling_detr.py::DetrModelTest::test_training_gradient_accumulation
-tests/models/diffllama/test_modeling_diffllama.py::DiffLlamaModelTest::test_training_gradient_accumulation
-tests/models/dinat/test_modeling_dinat.py::DinatModelTest::test_training_gradient_accumulation
-tests/models/dinov2/test_modeling_dinov2.py::Dinov2ModelTest::test_training_gradient_accumulation
-tests/models/dinov2_with_registers/test_modeling_dinov2_with_registers.py::Dinov2WithRegistersModelTest::test_training_gradient_accumulation
-tests/models/distilbert/test_modeling_distilbert.py::DistilBertModelTest::test_training_gradient_accumulation
-tests/models/donut/test_modeling_donut_swin.py::DonutSwinModelTest::test_training_gradient_accumulation
-tests/models/dpr/test_modeling_dpr.py::DPRModelTest::test_training_gradient_accumulation
-tests/models/dpt/test_modeling_dpt.py::DPTModelTest::test_training_gradient_accumulation
-tests/models/dpt/test_modeling_dpt_auto_backbone.py::DPTModelTest::test_training_gradient_accumulation
-tests/models/dpt/test_modeling_dpt_hybrid.py::DPTModelTest::test_training_gradient_accumulation
-tests/models/efficientnet/test_modeling_efficientnet.py::EfficientNetModelTest::test_training_gradient_accumulation
-tests/models/electra/test_modeling_electra.py::ElectraModelTest::test_training_gradient_accumulation
-tests/models/emu3/test_modeling_emu3.py::Emu3Text2TextModelTest::test_training_gradient_accumulation
-tests/models/emu3/test_modeling_emu3.py::Emu3Vision2TextModelTest::test_training_gradient_accumulation
-tests/models/encodec/test_modeling_encodec.py::EncodecModelTest::test_training_gradient_accumulation
-tests/models/ernie/test_modeling_ernie.py::ErnieModelTest::test_training_gradient_accumulation
-tests/models/esm/test_modeling_esm.py::EsmModelTest::test_training_gradient_accumulation
-tests/models/esm/test_modeling_esmfold.py::EsmFoldModelTest::test_training_gradient_accumulation
-tests/models/falcon/test_modeling_falcon.py::FalconModelTest::test_training_gradient_accumulation
-tests/models/falcon_mamba/test_modeling_falcon_mamba.py::FalconMambaModelTest::test_training_gradient_accumulation
-tests/models/fastspeech2_conformer/test_modeling_fastspeech2_conformer.py::FastSpeech2ConformerModelTest::test_training_gradient_accumulation
-tests/models/fastspeech2_conformer/test_modeling_fastspeech2_conformer.py::FastSpeech2ConformerWithHifiGanTest::test_training_gradient_accumulation
-tests/models/flaubert/test_modeling_flaubert.py::FlaubertModelTest::test_training_gradient_accumulation
-tests/models/flava/test_modeling_flava.py::FlavaImageModelTest::test_training_gradient_accumulation
-tests/models/flava/test_modeling_flava.py::FlavaTextModelTest::test_training_gradient_accumulation
-tests/models/flava/test_modeling_flava.py::FlavaMultimodalModelTest::test_training_gradient_accumulation
-tests/models/flava/test_modeling_flava.py::FlavaImageCodebookTest::test_training_gradient_accumulation
-tests/models/flava/test_modeling_flava.py::FlavaModelTest::test_training_gradient_accumulation
-tests/models/flava/test_modeling_flava.py::FlavaForPreTrainingTest::test_training_gradient_accumulation
-tests/models/fnet/test_modeling_fnet.py::FNetModelTest::test_training_gradient_accumulation
-tests/models/focalnet/test_modeling_focalnet.py::FocalNetModelTest::test_training_gradient_accumulation
-tests/models/fsmt/test_modeling_fsmt.py::FSMTModelTest::test_training_gradient_accumulation
-tests/models/funnel/test_modeling_funnel.py::FunnelModelTest::test_training_gradient_accumulation
-tests/models/funnel/test_modeling_funnel.py::FunnelBaseModelTest::test_training_gradient_accumulation
-tests/models/fuyu/test_modeling_fuyu.py::FuyuModelTest::test_training_gradient_accumulation
-tests/models/gemma/test_modeling_gemma.py::GemmaModelTest::test_training_gradient_accumulation
-tests/models/gemma2/test_modeling_gemma2.py::GemmaModelTest::test_training_gradient_accumulation
-tests/models/gemma2/test_modeling_gemma2.py::Gemma2ModelTest::test_training_gradient_accumulation
-tests/models/git/test_modeling_git.py::GitVisionModelTest::test_training_gradient_accumulation
-tests/models/git/test_modeling_git.py::GitModelTest::test_training_gradient_accumulation
-tests/models/glm/test_modeling_glm.py::GlmModelTest::test_training_gradient_accumulation
-tests/models/glpn/test_modeling_glpn.py::GLPNModelTest::test_training_gradient_accumulation
-tests/models/gpt2/test_modeling_gpt2.py::GPT2ModelTest::test_training_gradient_accumulation
-tests/models/gpt_bigcode/test_modeling_gpt_bigcode.py::GPTBigCodeModelTest::test_training_gradient_accumulation
-tests/models/gpt_bigcode/test_modeling_gpt_bigcode.py::GPTBigCodeMHAModelTest::test_training_gradient_accumulation
-tests/models/gpt_neo/test_modeling_gpt_neo.py::GPTNeoModelTest::test_training_gradient_accumulation
-tests/models/gpt_neox/test_modeling_gpt_neox.py::GPTNeoXModelTest::test_training_gradient_accumulation
-tests/models/gpt_neox_japanese/test_modeling_gpt_neox_japanese.py::GPTNeoXModelJapaneseTest::test_training_gradient_accumulation
-tests/models/gptj/test_modeling_gptj.py::GPTJModelTest::test_training_gradient_accumulation
-tests/models/granite/test_modeling_granite.py::GraniteModelTest::test_training_gradient_accumulation
-tests/models/granitemoe/test_modeling_granitemoe.py::GraniteMoeModelTest::test_training_gradient_accumulation
-tests/models/grounding_dino/test_modeling_grounding_dino.py::GroundingDinoModelTest::test_training_gradient_accumulation
-tests/models/groupvit/test_modeling_groupvit.py::GroupViTVisionModelTest::test_training_gradient_accumulation
-tests/models/groupvit/test_modeling_groupvit.py::GroupViTTextModelTest::test_training_gradient_accumulation
-tests/models/groupvit/test_modeling_groupvit.py::GroupViTModelTest::test_training_gradient_accumulation
-tests/models/helium/test_modeling_helium.py::GemmaModelTest::test_training_gradient_accumulation
-tests/models/helium/test_modeling_helium.py::HeliumModelTest::test_training_gradient_accumulation
-tests/models/hiera/test_modeling_hiera.py::HieraModelTest::test_training_gradient_accumulation
-tests/models/hubert/test_modeling_hubert.py::HubertModelTest::test_training_gradient_accumulation
-tests/models/hubert/test_modeling_hubert.py::HubertRobustModelTest::test_training_gradient_accumulation
-tests/models/ibert/test_modeling_ibert.py::IBertModelTest::test_training_gradient_accumulation
-tests/models/idefics/test_modeling_idefics.py::IdeficsModelTest::test_training_gradient_accumulation
-tests/models/idefics/test_modeling_idefics.py::IdeficsForVisionText2TextTest::test_training_gradient_accumulation
-tests/models/idefics2/test_modeling_idefics2.py::Idefics2ModelTest::test_training_gradient_accumulation
-tests/models/idefics2/test_modeling_idefics2.py::Idefics2ForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/idefics3/test_modeling_idefics3.py::Idefics3ModelTest::test_training_gradient_accumulation
-tests/models/idefics3/test_modeling_idefics3.py::Idefics3ForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/ijepa/test_modeling_ijepa.py::IJepaModelTest::test_training_gradient_accumulation
-tests/models/imagegpt/test_modeling_imagegpt.py::ImageGPTModelTest::test_training_gradient_accumulation
-tests/models/informer/test_modeling_informer.py::InformerModelTest::test_training_gradient_accumulation
-tests/models/instructblip/test_modeling_instructblip.py::InstructBlipVisionModelTest::test_training_gradient_accumulation
-tests/models/instructblip/test_modeling_instructblip.py::InstructBlipForConditionalGenerationDecoderOnlyTest::test_training_gradient_accumulation
-tests/models/instructblipvideo/test_modeling_instructblipvideo.py::InstructBlipVideoVisionModelTest::test_training_gradient_accumulation
-tests/models/instructblipvideo/test_modeling_instructblipvideo.py::InstructBlipVideoForConditionalGenerationDecoderOnlyTest::test_training_gradient_accumulation
-tests/models/jamba/test_modeling_jamba.py::JambaModelTest::test_training_gradient_accumulation
-tests/models/jetmoe/test_modeling_jetmoe.py::JetMoeModelTest::test_training_gradient_accumulation
-tests/models/kosmos2/test_modeling_kosmos2.py::Kosmos2ModelTest::test_training_gradient_accumulation
-tests/models/layoutlm/test_modeling_layoutlm.py::LayoutLMModelTest::test_training_gradient_accumulation
-tests/models/layoutlmv2/test_modeling_layoutlmv2.py::LayoutLMv2ModelTest::test_training_gradient_accumulation
-tests/models/layoutlmv3/test_modeling_layoutlmv3.py::LayoutLMv3ModelTest::test_training_gradient_accumulation
-tests/models/led/test_modeling_led.py::LEDModelTest::test_training_gradient_accumulation
-tests/models/levit/test_modeling_levit.py::LevitModelTest::test_training_gradient_accumulation
-tests/models/lilt/test_modeling_lilt.py::LiltModelTest::test_training_gradient_accumulation
-tests/models/llama/test_modeling_llama.py::LlamaModelTest::test_training_gradient_accumulation
-tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/llava_next/test_modeling_llava_next.py::LlavaNextForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/llava_next_video/test_modeling_llava_next_video.py::LlavaNextVideoForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/llava_onevision/test_modeling_llava_onevision.py::LlavaOnevisionForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/longformer/test_modeling_longformer.py::LongformerModelTest::test_training_gradient_accumulation
-tests/models/longt5/test_modeling_longt5.py::LongT5ModelTest::test_training_gradient_accumulation
-tests/models/longt5/test_modeling_longt5.py::LongT5TGlobalModelTest::test_training_gradient_accumulation
-tests/models/longt5/test_modeling_longt5.py::LongT5EncoderOnlyModelTest::test_training_gradient_accumulation
-tests/models/longt5/test_modeling_longt5.py::LongT5EncoderOnlyTGlobalModelTest::test_training_gradient_accumulation
-tests/models/luke/test_modeling_luke.py::LukeModelTest::test_training_gradient_accumulation
-tests/models/lxmert/test_modeling_lxmert.py::LxmertModelTest::test_training_gradient_accumulation
-tests/models/m2m_100/test_modeling_m2m_100.py::M2M100ModelTest::test_training_gradient_accumulation
-tests/models/mamba/test_modeling_mamba.py::MambaModelTest::test_training_gradient_accumulation
-tests/models/mamba2/test_modeling_mamba2.py::Mamba2ModelTest::test_training_gradient_accumulation
-tests/models/marian/test_modeling_marian.py::MarianModelTest::test_training_gradient_accumulation
-tests/models/marian/test_modeling_marian.py::MarianStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/markuplm/test_modeling_markuplm.py::MarkupLMModelTest::test_training_gradient_accumulation
-tests/models/mask2former/test_modeling_mask2former.py::Mask2FormerModelTest::test_training_gradient_accumulation
-tests/models/maskformer/test_modeling_maskformer.py::MaskFormerModelTest::test_training_gradient_accumulation
-tests/models/maskformer/test_modeling_maskformer_swin.py::MaskFormerSwinModelTest::test_training_gradient_accumulation
-tests/models/mbart/test_modeling_mbart.py::MBartModelTest::test_training_gradient_accumulation
-tests/models/mbart/test_modeling_mbart.py::MBartStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/megatron_bert/test_modeling_megatron_bert.py::MegatronBertModelTest::test_training_gradient_accumulation
-tests/models/mgp_str/test_modeling_mgp_str.py::MgpstrModelTest::test_training_gradient_accumulation
-tests/models/mimi/test_modeling_mimi.py::MimiModelTest::test_training_gradient_accumulation
-tests/models/mistral/test_modeling_mistral.py::MistralModelTest::test_training_gradient_accumulation
-tests/models/mixtral/test_modeling_mixtral.py::MixtralModelTest::test_training_gradient_accumulation
-tests/models/mllama/test_modeling_mllama.py::MllamaForCausalLMModelTest::test_training_gradient_accumulation
-tests/models/mllama/test_modeling_mllama.py::MllamaForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/mobilebert/test_modeling_mobilebert.py::MobileBertModelTest::test_training_gradient_accumulation
-tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py::MobileNetV1ModelTest::test_training_gradient_accumulation
-tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py::MobileNetV2ModelTest::test_training_gradient_accumulation
-tests/models/mobilevit/test_modeling_mobilevit.py::MobileViTModelTest::test_training_gradient_accumulation
-tests/models/mobilevitv2/test_modeling_mobilevitv2.py::MobileViTV2ModelTest::test_training_gradient_accumulation
-tests/models/modernbert/test_modeling_modernbert.py::ModernBertModelTest::test_training_gradient_accumulation
-tests/models/moonshine/test_modeling_moonshine.py::MoonshineModelTest::test_training_gradient_accumulation
-tests/models/moshi/test_modeling_moshi.py::MoshiDecoderTest::test_training_gradient_accumulation
-tests/models/moshi/test_modeling_moshi.py::MoshiTest::test_training_gradient_accumulation
-tests/models/mpnet/test_modeling_mpnet.py::MPNetModelTest::test_training_gradient_accumulation
-tests/models/mpt/test_modeling_mpt.py::MptModelTest::test_training_gradient_accumulation
-tests/models/mra/test_modeling_mra.py::MraModelTest::test_training_gradient_accumulation
-tests/models/mt5/test_modeling_mt5.py::MT5ModelTest::test_training_gradient_accumulation
-tests/models/mt5/test_modeling_mt5.py::MT5EncoderOnlyModelTest::test_training_gradient_accumulation
-tests/models/musicgen/test_modeling_musicgen.py::MusicgenDecoderTest::test_training_gradient_accumulation
-tests/models/musicgen/test_modeling_musicgen.py::MusicgenTest::test_training_gradient_accumulation
-tests/models/musicgen_melody/test_modeling_musicgen_melody.py::MusicgenMelodyDecoderTest::test_training_gradient_accumulation
-tests/models/musicgen_melody/test_modeling_musicgen_melody.py::MusicgenMelodyTest::test_training_gradient_accumulation
-tests/models/mvp/test_modeling_mvp.py::MvpModelTest::test_training_gradient_accumulation
-tests/models/mvp/test_modeling_mvp.py::MvpStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/nemotron/test_modeling_nemotron.py::GemmaModelTest::test_training_gradient_accumulation
-tests/models/nemotron/test_modeling_nemotron.py::NemotronModelTest::test_training_gradient_accumulation
-tests/models/nllb_moe/test_modeling_nllb_moe.py::NllbMoeModelTest::test_training_gradient_accumulation
-tests/models/nystromformer/test_modeling_nystromformer.py::NystromformerModelTest::test_training_gradient_accumulation
-tests/models/olmo/test_modeling_olmo.py::OlmoModelTest::test_training_gradient_accumulation
-tests/models/olmo2/test_modeling_olmo2.py::Olmo2ModelTest::test_training_gradient_accumulation
-tests/models/olmoe/test_modeling_olmoe.py::OlmoeModelTest::test_training_gradient_accumulation
-tests/models/omdet_turbo/test_modeling_omdet_turbo.py::OmDetTurboModelTest::test_training_gradient_accumulation
-tests/models/oneformer/test_modeling_oneformer.py::OneFormerModelTest::test_training_gradient_accumulation
-tests/models/openai/test_modeling_openai.py::OpenAIGPTModelTest::test_training_gradient_accumulation
-tests/models/opt/test_modeling_opt.py::OPTModelTest::test_training_gradient_accumulation
-tests/models/owlv2/test_modeling_owlv2.py::Owlv2VisionModelTest::test_training_gradient_accumulation
-tests/models/owlv2/test_modeling_owlv2.py::Owlv2TextModelTest::test_training_gradient_accumulation
-tests/models/owlv2/test_modeling_owlv2.py::Owlv2ModelTest::test_training_gradient_accumulation
-tests/models/owlv2/test_modeling_owlv2.py::Owlv2ForObjectDetectionTest::test_training_gradient_accumulation
-tests/models/owlvit/test_modeling_owlvit.py::OwlViTVisionModelTest::test_training_gradient_accumulation
-tests/models/owlvit/test_modeling_owlvit.py::OwlViTTextModelTest::test_training_gradient_accumulation
-tests/models/owlvit/test_modeling_owlvit.py::OwlViTModelTest::test_training_gradient_accumulation
-tests/models/owlvit/test_modeling_owlvit.py::OwlViTForObjectDetectionTest::test_training_gradient_accumulation
-tests/models/paligemma/test_modeling_paligemma.py::PaliGemmaForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/patchtsmixer/test_modeling_patchtsmixer.py::PatchTSMixerModelTest::test_training_gradient_accumulation
-tests/models/patchtst/test_modeling_patchtst.py::PatchTSTModelTest::test_training_gradient_accumulation
-tests/models/pegasus/test_modeling_pegasus.py::PegasusModelTest::test_training_gradient_accumulation
-tests/models/pegasus/test_modeling_pegasus.py::PegasusStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/pegasus_x/test_modeling_pegasus_x.py::PegasusXModelTest::test_training_gradient_accumulation
-tests/models/pegasus_x/test_modeling_pegasus_x.py::PegasusXStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/perceiver/test_modeling_perceiver.py::PerceiverModelTest::test_training_gradient_accumulation
-tests/models/persimmon/test_modeling_persimmon.py::PersimmonModelTest::test_training_gradient_accumulation
-tests/models/phi/test_modeling_phi.py::PhiModelTest::test_training_gradient_accumulation
-tests/models/phi3/test_modeling_phi3.py::Phi3ModelTest::test_training_gradient_accumulation
-tests/models/phimoe/test_modeling_phimoe.py::PhimoeModelTest::test_training_gradient_accumulation
-tests/models/pix2struct/test_modeling_pix2struct.py::Pix2StructVisionModelTest::test_training_gradient_accumulation
-tests/models/pix2struct/test_modeling_pix2struct.py::Pix2StructTextModelTest::test_training_gradient_accumulation
-tests/models/pix2struct/test_modeling_pix2struct.py::Pix2StructModelTest::test_training_gradient_accumulation
-tests/models/pixtral/test_modeling_pixtral.py::PixtralVisionModelModelTest::test_training_gradient_accumulation
-tests/models/plbart/test_modeling_plbart.py::PLBartModelTest::test_training_gradient_accumulation
-tests/models/plbart/test_modeling_plbart.py::PLBartStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/poolformer/test_modeling_poolformer.py::PoolFormerModelTest::test_training_gradient_accumulation
-tests/models/pop2piano/test_modeling_pop2piano.py::Pop2PianoModelTest::test_training_gradient_accumulation
-tests/models/prophetnet/test_modeling_prophetnet.py::ProphetNetModelTest::test_training_gradient_accumulation
-tests/models/prophetnet/test_modeling_prophetnet.py::ProphetNetStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/prophetnet/test_modeling_prophetnet.py::ProphetNetStandaloneEncoderModelTest::test_training_gradient_accumulation
-tests/models/pvt/test_modeling_pvt.py::PvtModelTest::test_training_gradient_accumulation
-tests/models/pvt_v2/test_modeling_pvt_v2.py::PvtV2ModelTest::test_training_gradient_accumulation
-tests/models/qwen2/test_modeling_qwen2.py::Qwen2ModelTest::test_training_gradient_accumulation
-tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLModelTest::test_training_gradient_accumulation
-tests/models/qwen2_audio/test_modeling_qwen2_audio.py::Qwen2AudioForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/qwen2_moe/test_modeling_qwen2_moe.py::Qwen2MoeModelTest::test_training_gradient_accumulation
-tests/models/qwen2_vl/test_modeling_qwen2_vl.py::Qwen2VLModelTest::test_training_gradient_accumulation
-tests/models/recurrent_gemma/test_modeling_recurrent_gemma.py::RecurrentGemmaModelTest::test_training_gradient_accumulation
-tests/models/reformer/test_modeling_reformer.py::ReformerLocalAttnModelTest::test_training_gradient_accumulation
-tests/models/reformer/test_modeling_reformer.py::ReformerLSHAttnModelTest::test_training_gradient_accumulation
-tests/models/regnet/test_modeling_regnet.py::RegNetModelTest::test_training_gradient_accumulation
-tests/models/rembert/test_modeling_rembert.py::RemBertModelTest::test_training_gradient_accumulation
-tests/models/resnet/test_modeling_resnet.py::ResNetModelTest::test_training_gradient_accumulation
-tests/models/roberta/test_modeling_roberta.py::RobertaModelTest::test_training_gradient_accumulation
-tests/models/roberta_prelayernorm/test_modeling_roberta_prelayernorm.py::RobertaPreLayerNormModelTest::test_training_gradient_accumulation
-tests/models/roc_bert/test_modeling_roc_bert.py::RoCBertModelTest::test_training_gradient_accumulation
-tests/models/roformer/test_modeling_roformer.py::RoFormerModelTest::test_training_gradient_accumulation
-tests/models/rt_detr/test_modeling_rt_detr.py::RTDetrModelTest::test_training_gradient_accumulation
-tests/models/rwkv/test_modeling_rwkv.py::RwkvModelTest::test_training_gradient_accumulation
-tests/models/sam/test_modeling_sam.py::SamModelTest::test_training_gradient_accumulation
-tests/models/seamless_m4t/test_modeling_seamless_m4t.py::SeamlessM4TModelWithSpeechInputTest::test_training_gradient_accumulation
-tests/models/seamless_m4t/test_modeling_seamless_m4t.py::SeamlessM4TModelWithTextInputTest::test_training_gradient_accumulation
-tests/models/seamless_m4t_v2/test_modeling_seamless_m4t_v2.py::SeamlessM4Tv2ModelWithSpeechInputTest::test_training_gradient_accumulation
-tests/models/seamless_m4t_v2/test_modeling_seamless_m4t_v2.py::SeamlessM4Tv2ModelWithTextInputTest::test_training_gradient_accumulation
-tests/models/segformer/test_modeling_segformer.py::SegformerModelTest::test_training_gradient_accumulation
-tests/models/seggpt/test_modeling_seggpt.py::SegGptModelTest::test_training_gradient_accumulation
-tests/models/sew/test_modeling_sew.py::SEWModelTest::test_training_gradient_accumulation
-tests/models/sew_d/test_modeling_sew_d.py::SEWDModelTest::test_training_gradient_accumulation
-tests/models/siglip/test_modeling_siglip.py::SiglipVisionModelTest::test_training_gradient_accumulation
-tests/models/siglip/test_modeling_siglip.py::SiglipTextModelTest::test_training_gradient_accumulation
-tests/models/siglip/test_modeling_siglip.py::SiglipModelTest::test_training_gradient_accumulation
-tests/models/siglip/test_modeling_siglip.py::SiglipForImageClassificationModelTest::test_training_gradient_accumulation
-tests/models/speech_to_text/test_modeling_speech_to_text.py::Speech2TextModelTest::test_training_gradient_accumulation
-tests/models/speecht5/test_modeling_speecht5.py::SpeechT5ModelTest::test_training_gradient_accumulation
-tests/models/speecht5/test_modeling_speecht5.py::SpeechT5ForSpeechToTextTest::test_training_gradient_accumulation
-tests/models/speecht5/test_modeling_speecht5.py::SpeechT5ForTextToSpeechTest::test_training_gradient_accumulation
-tests/models/speecht5/test_modeling_speecht5.py::SpeechT5ForSpeechToSpeechTest::test_training_gradient_accumulation
-tests/models/speecht5/test_modeling_speecht5.py::SpeechT5HifiGanTest::test_training_gradient_accumulation
-tests/models/splinter/test_modeling_splinter.py::SplinterModelTest::test_training_gradient_accumulation
-tests/models/squeezebert/test_modeling_squeezebert.py::SqueezeBertModelTest::test_training_gradient_accumulation
-tests/models/stablelm/test_modeling_stablelm.py::StableLmModelTest::test_training_gradient_accumulation
-tests/models/starcoder2/test_modeling_starcoder2.py::Starcoder2ModelTest::test_training_gradient_accumulation
-tests/models/superglue/test_modeling_superglue.py::SuperGlueModelTest::test_training_gradient_accumulation
-tests/models/superpoint/test_modeling_superpoint.py::SuperPointModelTest::test_training_gradient_accumulation
-tests/models/swiftformer/test_modeling_swiftformer.py::SwiftFormerModelTest::test_training_gradient_accumulation
-tests/models/swin/test_modeling_swin.py::SwinModelTest::test_training_gradient_accumulation
-tests/models/swin2sr/test_modeling_swin2sr.py::Swin2SRModelTest::test_training_gradient_accumulation
-tests/models/swinv2/test_modeling_swinv2.py::Swinv2ModelTest::test_training_gradient_accumulation
-tests/models/switch_transformers/test_modeling_switch_transformers.py::SwitchTransformersModelTest::test_training_gradient_accumulation
-tests/models/switch_transformers/test_modeling_switch_transformers.py::SwitchTransformersEncoderOnlyModelTest::test_training_gradient_accumulation
-tests/models/t5/test_modeling_t5.py::T5ModelTest::test_training_gradient_accumulation
-tests/models/t5/test_modeling_t5.py::T5EncoderOnlyModelTest::test_training_gradient_accumulation
-tests/models/table_transformer/test_modeling_table_transformer.py::TableTransformerModelTest::test_training_gradient_accumulation
-tests/models/tapas/test_modeling_tapas.py::TapasModelTest::test_training_gradient_accumulation
-tests/models/textnet/test_modeling_textnet.py::TextNetModelTest::test_training_gradient_accumulation
-tests/models/time_series_transformer/test_modeling_time_series_transformer.py::TimeSeriesTransformerModelTest::test_training_gradient_accumulation
-tests/models/timesformer/test_modeling_timesformer.py::TimesformerModelTest::test_training_gradient_accumulation
-tests/models/timm_backbone/test_modeling_timm_backbone.py::TimmBackboneModelTest::test_training_gradient_accumulation
-tests/models/timm_wrapper/test_modeling_timm_wrapper.py::TimmWrapperModelTest::test_training_gradient_accumulation
-tests/models/trocr/test_modeling_trocr.py::TrOCRStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/tvp/test_modeling_tvp.py::TVPModelTest::test_training_gradient_accumulation
-tests/models/udop/test_modeling_udop.py::UdopModelTest::test_training_gradient_accumulation
-tests/models/udop/test_modeling_udop.py::UdopEncoderOnlyModelTest::test_training_gradient_accumulation
-tests/models/umt5/test_modeling_umt5.py::UMT5ModelTest::test_training_gradient_accumulation
-tests/models/umt5/test_modeling_umt5.py::UMT5EncoderOnlyModelTest::test_training_gradient_accumulation
-tests/models/unispeech/test_modeling_unispeech.py::UniSpeechRobustModelTest::test_training_gradient_accumulation
-tests/models/unispeech_sat/test_modeling_unispeech_sat.py::UniSpeechSatModelTest::test_training_gradient_accumulation
-tests/models/unispeech_sat/test_modeling_unispeech_sat.py::UniSpeechSatRobustModelTest::test_training_gradient_accumulation
-tests/models/univnet/test_modeling_univnet.py::UnivNetModelTest::test_training_gradient_accumulation
-tests/models/upernet/test_modeling_upernet.py::UperNetModelTest::test_training_gradient_accumulation
-tests/models/video_llava/test_modeling_video_llava.py::VideoLlavaForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/videomae/test_modeling_videomae.py::VideoMAEModelTest::test_training_gradient_accumulation
-tests/models/vilt/test_modeling_vilt.py::ViltModelTest::test_training_gradient_accumulation
-tests/models/vilt/test_modeling_vilt.py::ViltForImagesAndTextClassificationModelTest::test_training_gradient_accumulation
-tests/models/vipllava/test_modeling_vipllava.py::VipLlavaForConditionalGenerationModelTest::test_training_gradient_accumulation
-tests/models/visual_bert/test_modeling_visual_bert.py::VisualBertModelTest::test_training_gradient_accumulation
-tests/models/vit/test_modeling_vit.py::ViTModelTest::test_training_gradient_accumulation
-tests/models/vit_mae/test_modeling_vit_mae.py::ViTMAEModelTest::test_training_gradient_accumulation
-tests/models/vit_msn/test_modeling_vit_msn.py::ViTMSNModelTest::test_training_gradient_accumulation
-tests/models/vitdet/test_modeling_vitdet.py::VitDetModelTest::test_training_gradient_accumulation
-tests/models/vitmatte/test_modeling_vitmatte.py::VitMatteModelTest::test_training_gradient_accumulation
-tests/models/vitpose/test_modeling_vitpose.py::VitPoseModelTest::test_training_gradient_accumulation
-tests/models/vitpose_backbone/test_modeling_vitpose_backbone.py::VitPoseBackboneModelTest::test_training_gradient_accumulation
-tests/models/vits/test_modeling_vits.py::VitsModelTest::test_training_gradient_accumulation
-tests/models/vivit/test_modeling_vivit.py::VivitModelTest::test_training_gradient_accumulation
-tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelTest::test_training_gradient_accumulation
-tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2RobustModelTest::test_training_gradient_accumulation
-tests/models/wav2vec2_bert/test_modeling_wav2vec2_bert.py::Wav2Vec2BertModelTest::test_training_gradient_accumulation
-tests/models/wav2vec2_conformer/test_modeling_wav2vec2_conformer.py::Wav2Vec2ConformerModelTest::test_training_gradient_accumulation
-tests/models/wavlm/test_modeling_wavlm.py::WavLMModelTest::test_training_gradient_accumulation
-tests/models/whisper/test_modeling_whisper.py::WhisperModelTest::test_training_gradient_accumulation
-tests/models/whisper/test_modeling_whisper.py::WhisperEncoderModelTest::test_training_gradient_accumulation
-tests/models/whisper/test_modeling_whisper.py::WhisperStandaloneDecoderModelTest::test_training_gradient_accumulation
-tests/models/x_clip/test_modeling_x_clip.py::XCLIPVisionModelTest::test_training_gradient_accumulation
-tests/models/x_clip/test_modeling_x_clip.py::XCLIPTextModelTest::test_training_gradient_accumulation
-tests/models/x_clip/test_modeling_x_clip.py::XCLIPModelTest::test_training_gradient_accumulation
-tests/models/xglm/test_modeling_xglm.py::XGLMModelTest::test_training_gradient_accumulation
-tests/models/xlm/test_modeling_xlm.py::XLMModelTest::test_training_gradient_accumulation
-tests/models/xlm_roberta_xl/test_modeling_xlm_roberta_xl.py::XLMRobertaXLModelTest::test_training_gradient_accumulation
-tests/models/xlnet/test_modeling_xlnet.py::XLNetModelTest::test_training_gradient_accumulation
-tests/models/xmod/test_modeling_xmod.py::XmodModelTest::test_training_gradient_accumulation
-tests/models/yolos/test_modeling_yolos.py::YolosModelTest::test_training_gradient_accumulation
-tests/models/yoso/test_modeling_yoso.py::YosoModelTest::test_training_gradient_accumulation
-tests/models/zamba/test_modeling_zamba.py::ZambaModelTest::test_training_gradient_accumulation
-tests/models/zoedepth/test_modeling_zoedepth.py::ZoeDepthModelTest::test_training_gradient_accumulation