Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "3ec40299c18c370011a39e0576faf1e90c0a8164"
Unverified Commit a564d10a authored by amyeroberts's avatar amyeroberts Committed by GitHub
Browse files

Deprecate low use models (#30781) 

* Deprecate models
- graphormer
- time_series_transformer
- xlm_prophetnet
- qdqbert
- nat
- ernie_m
- tvlt
- nezha
- mega
- jukebox
- vit_hybrid
- x_clip
- deta
- speech_to_text_2
- efficientformer
- realm
- gptsan_japanese

* Fix up

* Fix speech2text2 imports

* Make sure message isn't indented

* Fix docstrings

* Correctly map for deprecated models from model_type

* Uncomment out

* Add back time series transformer and x-clip

* Import fix and fix-up

* Fix up with updated ruff
parent 7f08817b
Show whitespace changes
Inline Side-by-side
Showing with 517 additions and 391 deletions
docs/source/en/model_doc/deta.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# DETA # DETA
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The DETA model was proposed in [NMS Strikes Back](https://arxiv.org/abs/2212.06137) by Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou, Philipp Krähenbühl. The DETA model was proposed in [NMS Strikes Back](https://arxiv.org/abs/2212.06137) by Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou, Philipp Krähenbühl.
......
docs/source/en/model_doc/efficientformer.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# EfficientFormer # EfficientFormer
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The EfficientFormer model was proposed in [EfficientFormer: Vision Transformers at MobileNet Speed](https://arxiv.org/abs/2206.01191) The EfficientFormer model was proposed in [EfficientFormer: Vision Transformers at MobileNet Speed](https://arxiv.org/abs/2206.01191)
......
docs/source/en/model_doc/ernie_m.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# ErnieM # ErnieM
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The ErnieM model was proposed in [ERNIE-M: Enhanced Multilingual Representation by Aligning The ErnieM model was proposed in [ERNIE-M: Enhanced Multilingual Representation by Aligning
......
docs/source/en/model_doc/gptsan-japanese.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# GPTSAN-japanese # GPTSAN-japanese
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The GPTSAN-japanese model was released in the repository by Toshiyuki Sakamoto (tanreinama). The GPTSAN-japanese model was released in the repository by Toshiyuki Sakamoto (tanreinama).
......
docs/source/en/model_doc/graphormer.md
View file @ a564d10a
...@@ -14,6 +14,14 @@ rendered properly in your Markdown viewer. ...@@ -14,6 +14,14 @@ rendered properly in your Markdown viewer.
# Graphormer # Graphormer
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The Graphormer model was proposed in [Do Transformers Really Perform Bad for Graph Representation?](https://arxiv.org/abs/2106.05234) by The Graphormer model was proposed in [Do Transformers Really Perform Bad for Graph Representation?](https://arxiv.org/abs/2106.05234) by
......
docs/source/en/model_doc/jukebox.md
View file @ a564d10a
...@@ -15,6 +15,14 @@ rendered properly in your Markdown viewer. ...@@ -15,6 +15,14 @@ rendered properly in your Markdown viewer.
--> -->
# Jukebox # Jukebox
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The Jukebox model was proposed in [Jukebox: A generative model for music](https://arxiv.org/pdf/2005.00341.pdf) The Jukebox model was proposed in [Jukebox: A generative model for music](https://arxiv.org/pdf/2005.00341.pdf)
......
docs/source/en/model_doc/mega.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# MEGA # MEGA
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The MEGA model was proposed in [Mega: Moving Average Equipped Gated Attention](https://arxiv.org/abs/2209.10655) by Xuezhe Ma, Chunting Zhou, Xiang Kong, Junxian He, Liangke Gui, Graham Neubig, Jonathan May, and Luke Zettlemoyer. The MEGA model was proposed in [Mega: Moving Average Equipped Gated Attention](https://arxiv.org/abs/2209.10655) by Xuezhe Ma, Chunting Zhou, Xiang Kong, Junxian He, Liangke Gui, Graham Neubig, Jonathan May, and Luke Zettlemoyer.
......
docs/source/en/model_doc/nat.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# Neighborhood Attention Transformer # Neighborhood Attention Transformer
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
NAT was proposed in [Neighborhood Attention Transformer](https://arxiv.org/abs/2204.07143) NAT was proposed in [Neighborhood Attention Transformer](https://arxiv.org/abs/2204.07143)
......
docs/source/en/model_doc/nezha.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# Nezha # Nezha
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The Nezha model was proposed in [NEZHA: Neural Contextualized Representation for Chinese Language Understanding](https://arxiv.org/abs/1909.00204) by Junqiu Wei et al. The Nezha model was proposed in [NEZHA: Neural Contextualized Representation for Chinese Language Understanding](https://arxiv.org/abs/1909.00204) by Junqiu Wei et al.
......
docs/source/en/model_doc/qdqbert.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# QDQBERT # QDQBERT
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The QDQBERT model can be referenced in [Integer Quantization for Deep Learning Inference: Principles and Empirical The QDQBERT model can be referenced in [Integer Quantization for Deep Learning Inference: Principles and Empirical
......
docs/source/en/model_doc/realm.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# REALM # REALM
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The REALM model was proposed in [REALM: Retrieval-Augmented Language Model Pre-Training](https://arxiv.org/abs/2002.08909) by Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat and Ming-Wei Chang. It's a The REALM model was proposed in [REALM: Retrieval-Augmented Language Model Pre-Training](https://arxiv.org/abs/2002.08909) by Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat and Ming-Wei Chang. It's a
......
docs/source/en/model_doc/speech_to_text_2.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# Speech2Text2 # Speech2Text2
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The Speech2Text2 model is used together with [Wav2Vec2](wav2vec2) for Speech Translation models proposed in The Speech2Text2 model is used together with [Wav2Vec2](wav2vec2) for Speech Translation models proposed in
......
docs/source/en/model_doc/tvlt.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# TVLT # TVLT
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The TVLT model was proposed in [TVLT: Textless Vision-Language Transformer](https://arxiv.org/abs/2209.14156) The TVLT model was proposed in [TVLT: Textless Vision-Language Transformer](https://arxiv.org/abs/2209.14156)
......
docs/source/en/model_doc/vit_hybrid.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# Hybrid Vision Transformer (ViT Hybrid) # Hybrid Vision Transformer (ViT Hybrid)
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
## Overview ## Overview
The hybrid Vision Transformer (ViT) model was proposed in [An Image is Worth 16x16 Words: Transformers for Image Recognition The hybrid Vision Transformer (ViT) model was proposed in [An Image is Worth 16x16 Words: Transformers for Image Recognition
......
docs/source/en/model_doc/xlm-prophetnet.md
View file @ a564d10a
...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer. ...@@ -16,6 +16,14 @@ rendered properly in your Markdown viewer.
# XLM-ProphetNet # XLM-ProphetNet
<Tip warning={true}>
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.40.2.
You can do so by running the following command: `pip install -U transformers==4.40.2`.
</Tip>
<div class="flex flex-wrap space-x-1"> <div class="flex flex-wrap space-x-1">
<a href="https://huggingface.co/models?filter=xprophetnet"> <a href="https://huggingface.co/models?filter=xprophetnet">
<img alt="Models" src="https://img.shields.io/badge/All_model_pages-xprophetnet-blueviolet"> <img alt="Models" src="https://img.shields.io/badge/All_model_pages-xprophetnet-blueviolet">
......
src/transformers/__init__.py
View file @ a564d10a
...@@ -321,17 +321,44 @@ _import_structure = { ...@@ -321,17 +321,44 @@ _import_structure = {
"models.deit": ["DeiTConfig"], "models.deit": ["DeiTConfig"],
"models.deprecated": [], "models.deprecated": [],
"models.deprecated.bort": [], "models.deprecated.bort": [],
"models.deprecated.deta": ["DetaConfig"],
"models.deprecated.efficientformer": ["EfficientFormerConfig"],
"models.deprecated.ernie_m": ["ErnieMConfig"],
"models.deprecated.gptsan_japanese": [
"GPTSanJapaneseConfig",
"GPTSanJapaneseTokenizer",
],
"models.deprecated.graphormer": ["GraphormerConfig"],
"models.deprecated.jukebox": [
"JukeboxConfig",
"JukeboxPriorConfig",
"JukeboxTokenizer",
"JukeboxVQVAEConfig",
],
"models.deprecated.mctct": [ "models.deprecated.mctct": [
"MCTCTConfig", "MCTCTConfig",
"MCTCTFeatureExtractor", "MCTCTFeatureExtractor",
"MCTCTProcessor", "MCTCTProcessor",
], ],
"models.deprecated.mega": ["MegaConfig"],
"models.deprecated.mmbt": ["MMBTConfig"], "models.deprecated.mmbt": ["MMBTConfig"],
"models.deprecated.nat": ["NatConfig"],
"models.deprecated.nezha": ["NezhaConfig"],
"models.deprecated.open_llama": ["OpenLlamaConfig"], "models.deprecated.open_llama": ["OpenLlamaConfig"],
"models.deprecated.qdqbert": ["QDQBertConfig"],
"models.deprecated.realm": [
"RealmConfig",
"RealmTokenizer",
],
"models.deprecated.retribert": [ "models.deprecated.retribert": [
"RetriBertConfig", "RetriBertConfig",
"RetriBertTokenizer", "RetriBertTokenizer",
], ],
"models.deprecated.speech_to_text_2": [
"Speech2Text2Config",
"Speech2Text2Processor",
"Speech2Text2Tokenizer",
],
"models.deprecated.tapex": ["TapexTokenizer"], "models.deprecated.tapex": ["TapexTokenizer"],
"models.deprecated.trajectory_transformer": ["TrajectoryTransformerConfig"], "models.deprecated.trajectory_transformer": ["TrajectoryTransformerConfig"],
"models.deprecated.transfo_xl": [ "models.deprecated.transfo_xl": [
...@@ -339,9 +366,15 @@ _import_structure = { ...@@ -339,9 +366,15 @@ _import_structure = {
"TransfoXLCorpus", "TransfoXLCorpus",
"TransfoXLTokenizer", "TransfoXLTokenizer",
], ],
"models.deprecated.tvlt": [
"TvltConfig",
"TvltFeatureExtractor",
"TvltProcessor",
],
"models.deprecated.van": ["VanConfig"], "models.deprecated.van": ["VanConfig"],
"models.deprecated.vit_hybrid": ["ViTHybridConfig"],
"models.deprecated.xlm_prophetnet": ["XLMProphetNetConfig"],
"models.depth_anything": ["DepthAnythingConfig"], "models.depth_anything": ["DepthAnythingConfig"],
"models.deta": ["DetaConfig"],
"models.detr": ["DetrConfig"], "models.detr": ["DetrConfig"],
"models.dialogpt": [], "models.dialogpt": [],
"models.dinat": ["DinatConfig"], "models.dinat": ["DinatConfig"],
...@@ -363,7 +396,6 @@ _import_structure = { ...@@ -363,7 +396,6 @@ _import_structure = {
"DPRReaderTokenizer", "DPRReaderTokenizer",
], ],
"models.dpt": ["DPTConfig"], "models.dpt": ["DPTConfig"],
"models.efficientformer": ["EfficientFormerConfig"],
"models.efficientnet": ["EfficientNetConfig"], "models.efficientnet": ["EfficientNetConfig"],
"models.electra": [ "models.electra": [
"ElectraConfig", "ElectraConfig",
...@@ -375,7 +407,6 @@ _import_structure = { ...@@ -375,7 +407,6 @@ _import_structure = {
], ],
"models.encoder_decoder": ["EncoderDecoderConfig"], "models.encoder_decoder": ["EncoderDecoderConfig"],
"models.ernie": ["ErnieConfig"], "models.ernie": ["ErnieConfig"],
"models.ernie_m": ["ErnieMConfig"],
"models.esm": ["EsmConfig", "EsmTokenizer"], "models.esm": ["EsmConfig", "EsmTokenizer"],
"models.falcon": ["FalconConfig"], "models.falcon": ["FalconConfig"],
"models.fastspeech2_conformer": [ "models.fastspeech2_conformer": [
...@@ -420,11 +451,6 @@ _import_structure = { ...@@ -420,11 +451,6 @@ _import_structure = {
"models.gpt_neox_japanese": ["GPTNeoXJapaneseConfig"], "models.gpt_neox_japanese": ["GPTNeoXJapaneseConfig"],
"models.gpt_sw3": [], "models.gpt_sw3": [],
"models.gptj": ["GPTJConfig"], "models.gptj": ["GPTJConfig"],
"models.gptsan_japanese": [
"GPTSanJapaneseConfig",
"GPTSanJapaneseTokenizer",
],
"models.graphormer": ["GraphormerConfig"],
"models.grounding_dino": [ "models.grounding_dino": [
"GroundingDinoConfig", "GroundingDinoConfig",
"GroundingDinoProcessor", "GroundingDinoProcessor",
...@@ -449,12 +475,6 @@ _import_structure = { ...@@ -449,12 +475,6 @@ _import_structure = {
], ],
"models.jamba": ["JambaConfig"], "models.jamba": ["JambaConfig"],
"models.jetmoe": ["JetMoeConfig"], "models.jetmoe": ["JetMoeConfig"],
"models.jukebox": [
"JukeboxConfig",
"JukeboxPriorConfig",
"JukeboxTokenizer",
"JukeboxVQVAEConfig",
],
"models.kosmos2": [ "models.kosmos2": [
"Kosmos2Config", "Kosmos2Config",
"Kosmos2Processor", "Kosmos2Processor",
...@@ -519,7 +539,6 @@ _import_structure = { ...@@ -519,7 +539,6 @@ _import_structure = {
], ],
"models.mbart": ["MBartConfig"], "models.mbart": ["MBartConfig"],
"models.mbart50": [], "models.mbart50": [],
"models.mega": ["MegaConfig"],
"models.megatron_bert": ["MegatronBertConfig"], "models.megatron_bert": ["MegatronBertConfig"],
"models.megatron_gpt2": [], "models.megatron_gpt2": [],
"models.mgp_str": [ "models.mgp_str": [
...@@ -554,8 +573,6 @@ _import_structure = { ...@@ -554,8 +573,6 @@ _import_structure = {
"MusicgenMelodyDecoderConfig", "MusicgenMelodyDecoderConfig",
], ],
"models.mvp": ["MvpConfig", "MvpTokenizer"], "models.mvp": ["MvpConfig", "MvpTokenizer"],
"models.nat": ["NatConfig"],
"models.nezha": ["NezhaConfig"],
"models.nllb": [], "models.nllb": [],
"models.nllb_moe": ["NllbMoeConfig"], "models.nllb_moe": ["NllbMoeConfig"],
"models.nougat": ["NougatProcessor"], "models.nougat": ["NougatProcessor"],
...@@ -613,17 +630,12 @@ _import_structure = { ...@@ -613,17 +630,12 @@ _import_structure = {
], ],
"models.pvt": ["PvtConfig"], "models.pvt": ["PvtConfig"],
"models.pvt_v2": ["PvtV2Config"], "models.pvt_v2": ["PvtV2Config"],
"models.qdqbert": ["QDQBertConfig"],
"models.qwen2": [ "models.qwen2": [
"Qwen2Config", "Qwen2Config",
"Qwen2Tokenizer", "Qwen2Tokenizer",
], ],
"models.qwen2_moe": ["Qwen2MoeConfig"], "models.qwen2_moe": ["Qwen2MoeConfig"],
"models.rag": ["RagConfig", "RagRetriever", "RagTokenizer"], "models.rag": ["RagConfig", "RagRetriever", "RagTokenizer"],
"models.realm": [
"RealmConfig",
"RealmTokenizer",
],
"models.recurrent_gemma": ["RecurrentGemmaConfig"], "models.recurrent_gemma": ["RecurrentGemmaConfig"],
"models.reformer": ["ReformerConfig"], "models.reformer": ["ReformerConfig"],
"models.regnet": ["RegNetConfig"], "models.regnet": ["RegNetConfig"],
...@@ -672,11 +684,6 @@ _import_structure = { ...@@ -672,11 +684,6 @@ _import_structure = {
"Speech2TextFeatureExtractor", "Speech2TextFeatureExtractor",
"Speech2TextProcessor", "Speech2TextProcessor",
], ],
"models.speech_to_text_2": [
"Speech2Text2Config",
"Speech2Text2Processor",
"Speech2Text2Tokenizer",
],
"models.speecht5": [ "models.speecht5": [
"SpeechT5Config", "SpeechT5Config",
"SpeechT5FeatureExtractor", "SpeechT5FeatureExtractor",
...@@ -712,11 +719,6 @@ _import_structure = { ...@@ -712,11 +719,6 @@ _import_structure = {
"TrOCRConfig", "TrOCRConfig",
"TrOCRProcessor", "TrOCRProcessor",
], ],
"models.tvlt": [
"TvltConfig",
"TvltFeatureExtractor",
"TvltProcessor",
],
"models.tvp": [ "models.tvp": [
"TvpConfig", "TvpConfig",
"TvpProcessor", "TvpProcessor",
...@@ -749,7 +751,6 @@ _import_structure = { ...@@ -749,7 +751,6 @@ _import_structure = {
], ],
"models.visual_bert": ["VisualBertConfig"], "models.visual_bert": ["VisualBertConfig"],
"models.vit": ["ViTConfig"], "models.vit": ["ViTConfig"],
"models.vit_hybrid": ["ViTHybridConfig"],
"models.vit_mae": ["ViTMAEConfig"], "models.vit_mae": ["ViTMAEConfig"],
"models.vit_msn": ["ViTMSNConfig"], "models.vit_msn": ["ViTMSNConfig"],
"models.vitdet": ["VitDetConfig"], "models.vitdet": ["VitDetConfig"],
...@@ -788,7 +789,6 @@ _import_structure = { ...@@ -788,7 +789,6 @@ _import_structure = {
], ],
"models.xglm": ["XGLMConfig"], "models.xglm": ["XGLMConfig"],
"models.xlm": ["XLMConfig", "XLMTokenizer"], "models.xlm": ["XLMConfig", "XLMTokenizer"],
"models.xlm_prophetnet": ["XLMProphetNetConfig"],
"models.xlm_roberta": ["XLMRobertaConfig"], "models.xlm_roberta": ["XLMRobertaConfig"],
"models.xlm_roberta_xl": ["XLMRobertaXLConfig"], "models.xlm_roberta_xl": ["XLMRobertaXLConfig"],
"models.xlnet": ["XLNetConfig"], "models.xlnet": ["XLNetConfig"],
...@@ -943,7 +943,8 @@ else: ...@@ -943,7 +943,8 @@ else:
_import_structure["models.code_llama"].append("CodeLlamaTokenizer") _import_structure["models.code_llama"].append("CodeLlamaTokenizer")
_import_structure["models.cpm"].append("CpmTokenizer") _import_structure["models.cpm"].append("CpmTokenizer")
_import_structure["models.deberta_v2"].append("DebertaV2Tokenizer") _import_structure["models.deberta_v2"].append("DebertaV2Tokenizer")
_import_structure["models.ernie_m"].append("ErnieMTokenizer") _import_structure["models.deprecated.ernie_m"].append("ErnieMTokenizer")
_import_structure["models.deprecated.xlm_prophetnet"].append("XLMProphetNetTokenizer")
_import_structure["models.fnet"].append("FNetTokenizer") _import_structure["models.fnet"].append("FNetTokenizer")
_import_structure["models.gemma"].append("GemmaTokenizer") _import_structure["models.gemma"].append("GemmaTokenizer")
_import_structure["models.gpt_sw3"].append("GPTSw3Tokenizer") _import_structure["models.gpt_sw3"].append("GPTSw3Tokenizer")
...@@ -967,7 +968,6 @@ else: ...@@ -967,7 +968,6 @@ else:
_import_structure["models.t5"].append("T5Tokenizer") _import_structure["models.t5"].append("T5Tokenizer")
_import_structure["models.udop"].append("UdopTokenizer") _import_structure["models.udop"].append("UdopTokenizer")
_import_structure["models.xglm"].append("XGLMTokenizer") _import_structure["models.xglm"].append("XGLMTokenizer")
_import_structure["models.xlm_prophetnet"].append("XLMProphetNetTokenizer")
_import_structure["models.xlm_roberta"].append("XLMRobertaTokenizer") _import_structure["models.xlm_roberta"].append("XLMRobertaTokenizer")
_import_structure["models.xlnet"].append("XLNetTokenizer") _import_structure["models.xlnet"].append("XLNetTokenizer")
...@@ -1000,6 +1000,7 @@ else: ...@@ -1000,6 +1000,7 @@ else:
_import_structure["models.cpm"].append("CpmTokenizerFast") _import_structure["models.cpm"].append("CpmTokenizerFast")
_import_structure["models.deberta"].append("DebertaTokenizerFast") _import_structure["models.deberta"].append("DebertaTokenizerFast")
_import_structure["models.deberta_v2"].append("DebertaV2TokenizerFast") _import_structure["models.deberta_v2"].append("DebertaV2TokenizerFast")
_import_structure["models.deprecated.realm"].append("RealmTokenizerFast")
_import_structure["models.deprecated.retribert"].append("RetriBertTokenizerFast") _import_structure["models.deprecated.retribert"].append("RetriBertTokenizerFast")
_import_structure["models.distilbert"].append("DistilBertTokenizerFast") _import_structure["models.distilbert"].append("DistilBertTokenizerFast")
_import_structure["models.dpr"].extend( _import_structure["models.dpr"].extend(
...@@ -1037,7 +1038,6 @@ else: ...@@ -1037,7 +1038,6 @@ else:
_import_structure["models.openai"].append("OpenAIGPTTokenizerFast") _import_structure["models.openai"].append("OpenAIGPTTokenizerFast")
_import_structure["models.pegasus"].append("PegasusTokenizerFast") _import_structure["models.pegasus"].append("PegasusTokenizerFast")
_import_structure["models.qwen2"].append("Qwen2TokenizerFast") _import_structure["models.qwen2"].append("Qwen2TokenizerFast")
_import_structure["models.realm"].append("RealmTokenizerFast")
_import_structure["models.reformer"].append("ReformerTokenizerFast") _import_structure["models.reformer"].append("ReformerTokenizerFast")
_import_structure["models.rembert"].append("RemBertTokenizerFast") _import_structure["models.rembert"].append("RemBertTokenizerFast")
_import_structure["models.roberta"].append("RobertaTokenizerFast") _import_structure["models.roberta"].append("RobertaTokenizerFast")
...@@ -1122,11 +1122,13 @@ else: ...@@ -1122,11 +1122,13 @@ else:
["DeformableDetrFeatureExtractor", "DeformableDetrImageProcessor"] ["DeformableDetrFeatureExtractor", "DeformableDetrImageProcessor"]
) )
_import_structure["models.deit"].extend(["DeiTFeatureExtractor", "DeiTImageProcessor"]) _import_structure["models.deit"].extend(["DeiTFeatureExtractor", "DeiTImageProcessor"])
_import_structure["models.deta"].append("DetaImageProcessor") _import_structure["models.deprecated.deta"].append("DetaImageProcessor")
_import_structure["models.deprecated.efficientformer"].append("EfficientFormerImageProcessor")
_import_structure["models.deprecated.tvlt"].append("TvltImageProcessor")
_import_structure["models.deprecated.vit_hybrid"].extend(["ViTHybridImageProcessor"])
_import_structure["models.detr"].extend(["DetrFeatureExtractor", "DetrImageProcessor"]) _import_structure["models.detr"].extend(["DetrFeatureExtractor", "DetrImageProcessor"])
_import_structure["models.donut"].extend(["DonutFeatureExtractor", "DonutImageProcessor"]) _import_structure["models.donut"].extend(["DonutFeatureExtractor", "DonutImageProcessor"])
_import_structure["models.dpt"].extend(["DPTFeatureExtractor", "DPTImageProcessor"]) _import_structure["models.dpt"].extend(["DPTFeatureExtractor", "DPTImageProcessor"])
_import_structure["models.efficientformer"].append("EfficientFormerImageProcessor")
_import_structure["models.efficientnet"].append("EfficientNetImageProcessor") _import_structure["models.efficientnet"].append("EfficientNetImageProcessor")
_import_structure["models.flava"].extend(["FlavaFeatureExtractor", "FlavaImageProcessor", "FlavaProcessor"]) _import_structure["models.flava"].extend(["FlavaFeatureExtractor", "FlavaImageProcessor", "FlavaProcessor"])
_import_structure["models.fuyu"].extend(["FuyuImageProcessor", "FuyuProcessor"]) _import_structure["models.fuyu"].extend(["FuyuImageProcessor", "FuyuProcessor"])
...@@ -1158,13 +1160,11 @@ else: ...@@ -1158,13 +1160,11 @@ else:
_import_structure["models.siglip"].append("SiglipImageProcessor") _import_structure["models.siglip"].append("SiglipImageProcessor")
_import_structure["models.superpoint"].extend(["SuperPointImageProcessor"]) _import_structure["models.superpoint"].extend(["SuperPointImageProcessor"])
_import_structure["models.swin2sr"].append("Swin2SRImageProcessor") _import_structure["models.swin2sr"].append("Swin2SRImageProcessor")
_import_structure["models.tvlt"].append("TvltImageProcessor")
_import_structure["models.tvp"].append("TvpImageProcessor") _import_structure["models.tvp"].append("TvpImageProcessor")
_import_structure["models.video_llava"].append("VideoLlavaImageProcessor") _import_structure["models.video_llava"].append("VideoLlavaImageProcessor")
_import_structure["models.videomae"].extend(["VideoMAEFeatureExtractor", "VideoMAEImageProcessor"]) _import_structure["models.videomae"].extend(["VideoMAEFeatureExtractor", "VideoMAEImageProcessor"])
_import_structure["models.vilt"].extend(["ViltFeatureExtractor", "ViltImageProcessor", "ViltProcessor"]) _import_structure["models.vilt"].extend(["ViltFeatureExtractor", "ViltImageProcessor", "ViltProcessor"])
_import_structure["models.vit"].extend(["ViTFeatureExtractor", "ViTImageProcessor"]) _import_structure["models.vit"].extend(["ViTFeatureExtractor", "ViTImageProcessor"])
_import_structure["models.vit_hybrid"].extend(["ViTHybridImageProcessor"])
_import_structure["models.vitmatte"].append("VitMatteImageProcessor") _import_structure["models.vitmatte"].append("VitMatteImageProcessor")
_import_structure["models.vivit"].append("VivitImageProcessor") _import_structure["models.vivit"].append("VivitImageProcessor")
_import_structure["models.yolos"].extend(["YolosFeatureExtractor", "YolosImageProcessor"]) _import_structure["models.yolos"].extend(["YolosFeatureExtractor", "YolosImageProcessor"])
...@@ -1767,6 +1767,54 @@ else: ...@@ -1767,6 +1767,54 @@ else:
"DeiTPreTrainedModel", "DeiTPreTrainedModel",
] ]
) )
_import_structure["models.deprecated.deta"].extend(
[
"DetaForObjectDetection",
"DetaModel",
"DetaPreTrainedModel",
]
)
_import_structure["models.deprecated.efficientformer"].extend(
[
"EfficientFormerForImageClassification",
"EfficientFormerForImageClassificationWithTeacher",
"EfficientFormerModel",
"EfficientFormerPreTrainedModel",
]
)
_import_structure["models.deprecated.ernie_m"].extend(
[
"ErnieMForInformationExtraction",
"ErnieMForMultipleChoice",
"ErnieMForQuestionAnswering",
"ErnieMForSequenceClassification",
"ErnieMForTokenClassification",
"ErnieMModel",
"ErnieMPreTrainedModel",
]
)
_import_structure["models.deprecated.gptsan_japanese"].extend(
[
"GPTSanJapaneseForConditionalGeneration",
"GPTSanJapaneseModel",
"GPTSanJapanesePreTrainedModel",
]
)
_import_structure["models.deprecated.graphormer"].extend(
[
"GraphormerForGraphClassification",
"GraphormerModel",
"GraphormerPreTrainedModel",
]
)
_import_structure["models.deprecated.jukebox"].extend(
[
"JukeboxModel",
"JukeboxPreTrainedModel",
"JukeboxPrior",
"JukeboxVQVAE",
]
)
_import_structure["models.deprecated.mctct"].extend( _import_structure["models.deprecated.mctct"].extend(
[ [
"MCTCTForCTC", "MCTCTForCTC",
...@@ -1774,7 +1822,40 @@ else: ...@@ -1774,7 +1822,40 @@ else:
"MCTCTPreTrainedModel", "MCTCTPreTrainedModel",
] ]
) )
_import_structure["models.deprecated.mega"].extend(
[
"MegaForCausalLM",
"MegaForMaskedLM",
"MegaForMultipleChoice",
"MegaForQuestionAnswering",
"MegaForSequenceClassification",
"MegaForTokenClassification",
"MegaModel",
"MegaPreTrainedModel",
]
)
_import_structure["models.deprecated.mmbt"].extend(["MMBTForClassification", "MMBTModel", "ModalEmbeddings"]) _import_structure["models.deprecated.mmbt"].extend(["MMBTForClassification", "MMBTModel", "ModalEmbeddings"])
_import_structure["models.deprecated.nat"].extend(
[
"NatBackbone",
"NatForImageClassification",
"NatModel",
"NatPreTrainedModel",
]
)
_import_structure["models.deprecated.nezha"].extend(
[
"NezhaForMaskedLM",
"NezhaForMultipleChoice",
"NezhaForNextSentencePrediction",
"NezhaForPreTraining",
"NezhaForQuestionAnswering",
"NezhaForSequenceClassification",
"NezhaForTokenClassification",
"NezhaModel",
"NezhaPreTrainedModel",
]
)
_import_structure["models.deprecated.open_llama"].extend( _import_structure["models.deprecated.open_llama"].extend(
[ [
"OpenLlamaForCausalLM", "OpenLlamaForCausalLM",
...@@ -1783,12 +1864,42 @@ else: ...@@ -1783,12 +1864,42 @@ else:
"OpenLlamaPreTrainedModel", "OpenLlamaPreTrainedModel",
] ]
) )
_import_structure["models.deprecated.qdqbert"].extend(
[
"QDQBertForMaskedLM",
"QDQBertForMultipleChoice",
"QDQBertForNextSentencePrediction",
"QDQBertForQuestionAnswering",
"QDQBertForSequenceClassification",
"QDQBertForTokenClassification",
"QDQBertLayer",
"QDQBertLMHeadModel",
"QDQBertModel",
"QDQBertPreTrainedModel",
"load_tf_weights_in_qdqbert",
]
)
_import_structure["models.deprecated.realm"].extend(
[
"RealmEmbedder",
"RealmForOpenQA",
"RealmKnowledgeAugEncoder",
"RealmPreTrainedModel",
"RealmReader",
"RealmRetriever",
"RealmScorer",
"load_tf_weights_in_realm",
]
)
_import_structure["models.deprecated.retribert"].extend( _import_structure["models.deprecated.retribert"].extend(
[ [
"RetriBertModel", "RetriBertModel",
"RetriBertPreTrainedModel", "RetriBertPreTrainedModel",
] ]
) )
_import_structure["models.deprecated.speech_to_text_2"].extend(
["Speech2Text2ForCausalLM", "Speech2Text2PreTrainedModel"]
)
_import_structure["models.deprecated.trajectory_transformer"].extend( _import_structure["models.deprecated.trajectory_transformer"].extend(
[ [
"TrajectoryTransformerModel", "TrajectoryTransformerModel",
...@@ -1805,6 +1916,14 @@ else: ...@@ -1805,6 +1916,14 @@ else:
"load_tf_weights_in_transfo_xl", "load_tf_weights_in_transfo_xl",
] ]
) )
_import_structure["models.deprecated.tvlt"].extend(
[
"TvltForAudioVisualClassification",
"TvltForPreTraining",
"TvltModel",
"TvltPreTrainedModel",
]
)
_import_structure["models.deprecated.van"].extend( _import_structure["models.deprecated.van"].extend(
[ [
"VanForImageClassification", "VanForImageClassification",
...@@ -1812,17 +1931,27 @@ else: ...@@ -1812,17 +1931,27 @@ else:
"VanPreTrainedModel", "VanPreTrainedModel",
] ]
) )
_import_structure["models.depth_anything"].extend( _import_structure["models.deprecated.vit_hybrid"].extend(
[ [
"DepthAnythingForDepthEstimation", "ViTHybridForImageClassification",
"DepthAnythingPreTrainedModel", "ViTHybridModel",
"ViTHybridPreTrainedModel",
] ]
) )
_import_structure["models.deta"].extend( _import_structure["models.deprecated.xlm_prophetnet"].extend(
[ [
"DetaForObjectDetection", "XLMProphetNetDecoder",
"DetaModel", "XLMProphetNetEncoder",
"DetaPreTrainedModel", "XLMProphetNetForCausalLM",
"XLMProphetNetForConditionalGeneration",
"XLMProphetNetModel",
"XLMProphetNetPreTrainedModel",
]
)
_import_structure["models.depth_anything"].extend(
[
"DepthAnythingForDepthEstimation",
"DepthAnythingPreTrainedModel",
] ]
) )
_import_structure["models.detr"].extend( _import_structure["models.detr"].extend(
...@@ -1885,14 +2014,6 @@ else: ...@@ -1885,14 +2014,6 @@ else:
"DPTPreTrainedModel", "DPTPreTrainedModel",
] ]
) )
_import_structure["models.efficientformer"].extend(
[
"EfficientFormerForImageClassification",
"EfficientFormerForImageClassificationWithTeacher",
"EfficientFormerModel",
"EfficientFormerPreTrainedModel",
]
)
_import_structure["models.efficientnet"].extend( _import_structure["models.efficientnet"].extend(
[ [
"EfficientNetForImageClassification", "EfficientNetForImageClassification",
...@@ -1935,17 +2056,6 @@ else: ...@@ -1935,17 +2056,6 @@ else:
"ErniePreTrainedModel", "ErniePreTrainedModel",
] ]
) )
_import_structure["models.ernie_m"].extend(
[
"ErnieMForInformationExtraction",
"ErnieMForMultipleChoice",
"ErnieMForQuestionAnswering",
"ErnieMForSequenceClassification",
"ErnieMForTokenClassification",
"ErnieMModel",
"ErnieMPreTrainedModel",
]
)
_import_structure["models.esm"].extend( _import_structure["models.esm"].extend(
[ [
"EsmFoldPreTrainedModel", "EsmFoldPreTrainedModel",
...@@ -2121,20 +2231,6 @@ else: ...@@ -2121,20 +2231,6 @@ else:
"GPTJPreTrainedModel", "GPTJPreTrainedModel",
] ]
) )
_import_structure["models.gptsan_japanese"].extend(
[
"GPTSanJapaneseForConditionalGeneration",
"GPTSanJapaneseModel",
"GPTSanJapanesePreTrainedModel",
]
)
_import_structure["models.graphormer"].extend(
[
"GraphormerForGraphClassification",
"GraphormerModel",
"GraphormerPreTrainedModel",
]
)
_import_structure["models.grounding_dino"].extend( _import_structure["models.grounding_dino"].extend(
[ [
"GroundingDinoForObjectDetection", "GroundingDinoForObjectDetection",
...@@ -2225,14 +2321,6 @@ else: ...@@ -2225,14 +2321,6 @@ else:
"JetMoePreTrainedModel", "JetMoePreTrainedModel",
] ]
) )
_import_structure["models.jukebox"].extend(
[
"JukeboxModel",
"JukeboxPreTrainedModel",
"JukeboxPrior",
"JukeboxVQVAE",
]
)
_import_structure["models.kosmos2"].extend( _import_structure["models.kosmos2"].extend(
[ [
"Kosmos2ForConditionalGeneration", "Kosmos2ForConditionalGeneration",
...@@ -2410,18 +2498,6 @@ else: ...@@ -2410,18 +2498,6 @@ else:
"MBartPreTrainedModel", "MBartPreTrainedModel",
] ]
) )
_import_structure["models.mega"].extend(
[
"MegaForCausalLM",
"MegaForMaskedLM",
"MegaForMultipleChoice",
"MegaForQuestionAnswering",
"MegaForSequenceClassification",
"MegaForTokenClassification",
"MegaModel",
"MegaPreTrainedModel",
]
)
_import_structure["models.megatron_bert"].extend( _import_structure["models.megatron_bert"].extend(
[ [
"MegatronBertForCausalLM", "MegatronBertForCausalLM",
...@@ -2580,27 +2656,6 @@ else: ...@@ -2580,27 +2656,6 @@ else:
"MvpPreTrainedModel", "MvpPreTrainedModel",
] ]
) )
_import_structure["models.nat"].extend(
[
"NatBackbone",
"NatForImageClassification",
"NatModel",
"NatPreTrainedModel",
]
)
_import_structure["models.nezha"].extend(
[
"NezhaForMaskedLM",
"NezhaForMultipleChoice",
"NezhaForNextSentencePrediction",
"NezhaForPreTraining",
"NezhaForQuestionAnswering",
"NezhaForSequenceClassification",
"NezhaForTokenClassification",
"NezhaModel",
"NezhaPreTrainedModel",
]
)
_import_structure["models.nllb_moe"].extend( _import_structure["models.nllb_moe"].extend(
[ [
"NllbMoeForConditionalGeneration", "NllbMoeForConditionalGeneration",
...@@ -2811,21 +2866,6 @@ else: ...@@ -2811,21 +2866,6 @@ else:
"PvtV2PreTrainedModel", "PvtV2PreTrainedModel",
] ]
) )
_import_structure["models.qdqbert"].extend(
[
"QDQBertForMaskedLM",
"QDQBertForMultipleChoice",
"QDQBertForNextSentencePrediction",
"QDQBertForQuestionAnswering",
"QDQBertForSequenceClassification",
"QDQBertForTokenClassification",
"QDQBertLayer",
"QDQBertLMHeadModel",
"QDQBertModel",
"QDQBertPreTrainedModel",
"load_tf_weights_in_qdqbert",
]
)
_import_structure["models.qwen2"].extend( _import_structure["models.qwen2"].extend(
[ [
"Qwen2ForCausalLM", "Qwen2ForCausalLM",
...@@ -2852,18 +2892,6 @@ else: ...@@ -2852,18 +2892,6 @@ else:
"RagTokenForGeneration", "RagTokenForGeneration",
] ]
) )
_import_structure["models.realm"].extend(
[
"RealmEmbedder",
"RealmForOpenQA",
"RealmKnowledgeAugEncoder",
"RealmPreTrainedModel",
"RealmReader",
"RealmRetriever",
"RealmScorer",
"load_tf_weights_in_realm",
]
)
_import_structure["models.recurrent_gemma"].extend( _import_structure["models.recurrent_gemma"].extend(
[ [
"RecurrentGemmaForCausalLM", "RecurrentGemmaForCausalLM",
...@@ -3052,7 +3080,6 @@ else: ...@@ -3052,7 +3080,6 @@ else:
"Speech2TextPreTrainedModel", "Speech2TextPreTrainedModel",
] ]
) )
_import_structure["models.speech_to_text_2"].extend(["Speech2Text2ForCausalLM", "Speech2Text2PreTrainedModel"])
_import_structure["models.speecht5"].extend( _import_structure["models.speecht5"].extend(
[ [
"SpeechT5ForSpeechToSpeech", "SpeechT5ForSpeechToSpeech",
...@@ -3200,14 +3227,6 @@ else: ...@@ -3200,14 +3227,6 @@ else:
"TrOCRPreTrainedModel", "TrOCRPreTrainedModel",
] ]
) )
_import_structure["models.tvlt"].extend(
[
"TvltForAudioVisualClassification",
"TvltForPreTraining",
"TvltModel",
"TvltPreTrainedModel",
]
)
_import_structure["models.tvp"].extend( _import_structure["models.tvp"].extend(
[ [
"TvpForVideoGrounding", "TvpForVideoGrounding",
...@@ -3320,13 +3339,6 @@ else: ...@@ -3320,13 +3339,6 @@ else:
"ViTPreTrainedModel", "ViTPreTrainedModel",
] ]
) )
_import_structure["models.vit_hybrid"].extend(
[
"ViTHybridForImageClassification",
"ViTHybridModel",
"ViTHybridPreTrainedModel",
]
)
_import_structure["models.vit_mae"].extend( _import_structure["models.vit_mae"].extend(
[ [
"ViTMAEForPreTraining", "ViTMAEForPreTraining",
...@@ -3447,16 +3459,6 @@ else: ...@@ -3447,16 +3459,6 @@ else:
"XLMWithLMHeadModel", "XLMWithLMHeadModel",
] ]
) )
_import_structure["models.xlm_prophetnet"].extend(
[
"XLMProphetNetDecoder",
"XLMProphetNetEncoder",
"XLMProphetNetForCausalLM",
"XLMProphetNetForConditionalGeneration",
"XLMProphetNetModel",
"XLMProphetNetPreTrainedModel",
]
)
_import_structure["models.xlm_roberta"].extend( _import_structure["models.xlm_roberta"].extend(
[ [
"XLMRobertaForCausalLM", "XLMRobertaForCausalLM",
...@@ -3799,6 +3801,14 @@ else: ...@@ -3799,6 +3801,14 @@ else:
"TFDeiTPreTrainedModel", "TFDeiTPreTrainedModel",
] ]
) )
_import_structure["models.deprecated.efficientformer"].extend(
[
"TFEfficientFormerForImageClassification",
"TFEfficientFormerForImageClassificationWithTeacher",
"TFEfficientFormerModel",
"TFEfficientFormerPreTrainedModel",
]
)
_import_structure["models.deprecated.transfo_xl"].extend( _import_structure["models.deprecated.transfo_xl"].extend(
[ [
"TFAdaptiveEmbedding", "TFAdaptiveEmbedding",
...@@ -3831,14 +3841,6 @@ else: ...@@ -3831,14 +3841,6 @@ else:
"TFDPRReader", "TFDPRReader",
] ]
) )
_import_structure["models.efficientformer"].extend(
[
"TFEfficientFormerForImageClassification",
"TFEfficientFormerForImageClassificationWithTeacher",
"TFEfficientFormerModel",
"TFEfficientFormerPreTrainedModel",
]
)
_import_structure["models.electra"].extend( _import_structure["models.electra"].extend(
[ [
"TFElectraForMaskedLM", "TFElectraForMaskedLM",
...@@ -4888,19 +4890,48 @@ if TYPE_CHECKING: ...@@ -4888,19 +4890,48 @@ if TYPE_CHECKING:
DeformableDetrConfig, DeformableDetrConfig,
) )
from .models.deit import DeiTConfig from .models.deit import DeiTConfig
from .models.deprecated.deta import DetaConfig
from .models.deprecated.efficientformer import (
EfficientFormerConfig,
)
from .models.deprecated.ernie_m import ErnieMConfig
from .models.deprecated.gptsan_japanese import (
GPTSanJapaneseConfig,
GPTSanJapaneseTokenizer,
)
from .models.deprecated.graphormer import GraphormerConfig
from .models.deprecated.jukebox import (
JukeboxConfig,
JukeboxPriorConfig,
JukeboxTokenizer,
JukeboxVQVAEConfig,
)
from .models.deprecated.mctct import ( from .models.deprecated.mctct import (
MCTCTConfig, MCTCTConfig,
MCTCTFeatureExtractor, MCTCTFeatureExtractor,
MCTCTProcessor, MCTCTProcessor,
) )
from .models.deprecated.mega import MegaConfig
from .models.deprecated.mmbt import MMBTConfig from .models.deprecated.mmbt import MMBTConfig
from .models.deprecated.nat import NatConfig
from .models.deprecated.nezha import NezhaConfig
from .models.deprecated.open_llama import ( from .models.deprecated.open_llama import (
OpenLlamaConfig, OpenLlamaConfig,
) )
from .models.deprecated.qdqbert import QDQBertConfig
from .models.deprecated.realm import (
RealmConfig,
RealmTokenizer,
)
from .models.deprecated.retribert import ( from .models.deprecated.retribert import (
RetriBertConfig, RetriBertConfig,
RetriBertTokenizer, RetriBertTokenizer,
) )
from .models.deprecated.speech_to_text_2 import (
Speech2Text2Config,
Speech2Text2Processor,
Speech2Text2Tokenizer,
)
from .models.deprecated.tapex import TapexTokenizer from .models.deprecated.tapex import TapexTokenizer
from .models.deprecated.trajectory_transformer import ( from .models.deprecated.trajectory_transformer import (
TrajectoryTransformerConfig, TrajectoryTransformerConfig,
...@@ -4910,9 +4941,19 @@ if TYPE_CHECKING: ...@@ -4910,9 +4941,19 @@ if TYPE_CHECKING:
TransfoXLCorpus, TransfoXLCorpus,
TransfoXLTokenizer, TransfoXLTokenizer,
) )
from .models.deprecated.tvlt import (
TvltConfig,
TvltFeatureExtractor,
TvltProcessor,
)
from .models.deprecated.van import VanConfig from .models.deprecated.van import VanConfig
from .models.deprecated.vit_hybrid import (
ViTHybridConfig,
)
from .models.deprecated.xlm_prophetnet import (
XLMProphetNetConfig,
)
from .models.depth_anything import DepthAnythingConfig from .models.depth_anything import DepthAnythingConfig
from .models.deta import DetaConfig
from .models.detr import DetrConfig from .models.detr import DetrConfig
from .models.dinat import DinatConfig from .models.dinat import DinatConfig
from .models.dinov2 import Dinov2Config from .models.dinov2 import Dinov2Config
...@@ -4932,9 +4973,6 @@ if TYPE_CHECKING: ...@@ -4932,9 +4973,6 @@ if TYPE_CHECKING:
DPRReaderTokenizer, DPRReaderTokenizer,
) )
from .models.dpt import DPTConfig from .models.dpt import DPTConfig
from .models.efficientformer import (
EfficientFormerConfig,
)
from .models.efficientnet import ( from .models.efficientnet import (
EfficientNetConfig, EfficientNetConfig,
) )
...@@ -4948,7 +4986,6 @@ if TYPE_CHECKING: ...@@ -4948,7 +4986,6 @@ if TYPE_CHECKING:
) )
from .models.encoder_decoder import EncoderDecoderConfig from .models.encoder_decoder import EncoderDecoderConfig
from .models.ernie import ErnieConfig from .models.ernie import ErnieConfig
from .models.ernie_m import ErnieMConfig
from .models.esm import EsmConfig, EsmTokenizer from .models.esm import EsmConfig, EsmTokenizer
from .models.falcon import FalconConfig from .models.falcon import FalconConfig
from .models.fastspeech2_conformer import ( from .models.fastspeech2_conformer import (
...@@ -4996,11 +5033,6 @@ if TYPE_CHECKING: ...@@ -4996,11 +5033,6 @@ if TYPE_CHECKING:
GPTNeoXJapaneseConfig, GPTNeoXJapaneseConfig,
) )
from .models.gptj import GPTJConfig from .models.gptj import GPTJConfig
from .models.gptsan_japanese import (
GPTSanJapaneseConfig,
GPTSanJapaneseTokenizer,
)
from .models.graphormer import GraphormerConfig
from .models.grounding_dino import ( from .models.grounding_dino import (
GroundingDinoConfig, GroundingDinoConfig,
GroundingDinoProcessor, GroundingDinoProcessor,
...@@ -5027,12 +5059,6 @@ if TYPE_CHECKING: ...@@ -5027,12 +5059,6 @@ if TYPE_CHECKING:
) )
from .models.jamba import JambaConfig from .models.jamba import JambaConfig
from .models.jetmoe import JetMoeConfig from .models.jetmoe import JetMoeConfig
from .models.jukebox import (
JukeboxConfig,
JukeboxPriorConfig,
JukeboxTokenizer,
JukeboxVQVAEConfig,
)
from .models.kosmos2 import ( from .models.kosmos2 import (
Kosmos2Config, Kosmos2Config,
Kosmos2Processor, Kosmos2Processor,
...@@ -5098,7 +5124,6 @@ if TYPE_CHECKING: ...@@ -5098,7 +5124,6 @@ if TYPE_CHECKING:
MaskFormerSwinConfig, MaskFormerSwinConfig,
) )
from .models.mbart import MBartConfig from .models.mbart import MBartConfig
from .models.mega import MegaConfig
from .models.megatron_bert import ( from .models.megatron_bert import (
MegatronBertConfig, MegatronBertConfig,
) )
...@@ -5141,8 +5166,6 @@ if TYPE_CHECKING: ...@@ -5141,8 +5166,6 @@ if TYPE_CHECKING:
MusicgenMelodyDecoderConfig, MusicgenMelodyDecoderConfig,
) )
from .models.mvp import MvpConfig, MvpTokenizer from .models.mvp import MvpConfig, MvpTokenizer
from .models.nat import NatConfig
from .models.nezha import NezhaConfig
from .models.nllb_moe import NllbMoeConfig from .models.nllb_moe import NllbMoeConfig
from .models.nougat import NougatProcessor from .models.nougat import NougatProcessor
from .models.nystromformer import ( from .models.nystromformer import (
...@@ -5213,14 +5236,9 @@ if TYPE_CHECKING: ...@@ -5213,14 +5236,9 @@ if TYPE_CHECKING:
) )
from .models.pvt import PvtConfig from .models.pvt import PvtConfig
from .models.pvt_v2 import PvtV2Config from .models.pvt_v2 import PvtV2Config
from .models.qdqbert import QDQBertConfig
from .models.qwen2 import Qwen2Config, Qwen2Tokenizer from .models.qwen2 import Qwen2Config, Qwen2Tokenizer
from .models.qwen2_moe import Qwen2MoeConfig from .models.qwen2_moe import Qwen2MoeConfig
from .models.rag import RagConfig, RagRetriever, RagTokenizer from .models.rag import RagConfig, RagRetriever, RagTokenizer
from .models.realm import (
RealmConfig,
RealmTokenizer,
)
from .models.recurrent_gemma import RecurrentGemmaConfig from .models.recurrent_gemma import RecurrentGemmaConfig
from .models.reformer import ReformerConfig from .models.reformer import ReformerConfig
from .models.regnet import RegNetConfig from .models.regnet import RegNetConfig
...@@ -5273,11 +5291,6 @@ if TYPE_CHECKING: ...@@ -5273,11 +5291,6 @@ if TYPE_CHECKING:
Speech2TextFeatureExtractor, Speech2TextFeatureExtractor,
Speech2TextProcessor, Speech2TextProcessor,
) )
from .models.speech_to_text_2 import (
Speech2Text2Config,
Speech2Text2Processor,
Speech2Text2Tokenizer,
)
from .models.speecht5 import ( from .models.speecht5 import (
SpeechT5Config, SpeechT5Config,
SpeechT5FeatureExtractor, SpeechT5FeatureExtractor,
...@@ -5323,11 +5336,6 @@ if TYPE_CHECKING: ...@@ -5323,11 +5336,6 @@ if TYPE_CHECKING:
TrOCRConfig, TrOCRConfig,
TrOCRProcessor, TrOCRProcessor,
) )
from .models.tvlt import (
TvltConfig,
TvltFeatureExtractor,
TvltProcessor,
)
from .models.tvp import ( from .models.tvp import (
TvpConfig, TvpConfig,
TvpProcessor, TvpProcessor,
...@@ -5365,9 +5373,6 @@ if TYPE_CHECKING: ...@@ -5365,9 +5373,6 @@ if TYPE_CHECKING:
VisualBertConfig, VisualBertConfig,
) )
from .models.vit import ViTConfig from .models.vit import ViTConfig
from .models.vit_hybrid import (
ViTHybridConfig,
)
from .models.vit_mae import ViTMAEConfig from .models.vit_mae import ViTMAEConfig
from .models.vit_msn import ViTMSNConfig from .models.vit_msn import ViTMSNConfig
from .models.vitdet import VitDetConfig from .models.vitdet import VitDetConfig
...@@ -5408,9 +5413,6 @@ if TYPE_CHECKING: ...@@ -5408,9 +5413,6 @@ if TYPE_CHECKING:
) )
from .models.xglm import XGLMConfig from .models.xglm import XGLMConfig
from .models.xlm import XLMConfig, XLMTokenizer from .models.xlm import XLMConfig, XLMTokenizer
from .models.xlm_prophetnet import (
XLMProphetNetConfig,
)
from .models.xlm_roberta import ( from .models.xlm_roberta import (
XLMRobertaConfig, XLMRobertaConfig,
) )
...@@ -5570,7 +5572,8 @@ if TYPE_CHECKING: ...@@ -5570,7 +5572,8 @@ if TYPE_CHECKING:
from .models.code_llama import CodeLlamaTokenizer from .models.code_llama import CodeLlamaTokenizer
from .models.cpm import CpmTokenizer from .models.cpm import CpmTokenizer
from .models.deberta_v2 import DebertaV2Tokenizer from .models.deberta_v2 import DebertaV2Tokenizer
from .models.ernie_m import ErnieMTokenizer from .models.deprecated.ernie_m import ErnieMTokenizer
from .models.deprecated.xlm_prophetnet import XLMProphetNetTokenizer
from .models.fnet import FNetTokenizer from .models.fnet import FNetTokenizer
from .models.gemma import GemmaTokenizer from .models.gemma import GemmaTokenizer
from .models.gpt_sw3 import GPTSw3Tokenizer from .models.gpt_sw3 import GPTSw3Tokenizer
...@@ -5593,7 +5596,6 @@ if TYPE_CHECKING: ...@@ -5593,7 +5596,6 @@ if TYPE_CHECKING:
from .models.t5 import T5Tokenizer from .models.t5 import T5Tokenizer
from .models.udop import UdopTokenizer from .models.udop import UdopTokenizer
from .models.xglm import XGLMTokenizer from .models.xglm import XGLMTokenizer
from .models.xlm_prophetnet import XLMProphetNetTokenizer
from .models.xlm_roberta import XLMRobertaTokenizer from .models.xlm_roberta import XLMRobertaTokenizer
from .models.xlnet import XLNetTokenizer from .models.xlnet import XLNetTokenizer
...@@ -5621,6 +5623,7 @@ if TYPE_CHECKING: ...@@ -5621,6 +5623,7 @@ if TYPE_CHECKING:
from .models.cpm import CpmTokenizerFast from .models.cpm import CpmTokenizerFast
from .models.deberta import DebertaTokenizerFast from .models.deberta import DebertaTokenizerFast
from .models.deberta_v2 import DebertaV2TokenizerFast from .models.deberta_v2 import DebertaV2TokenizerFast
from .models.deprecated.realm import RealmTokenizerFast
from .models.deprecated.retribert import RetriBertTokenizerFast from .models.deprecated.retribert import RetriBertTokenizerFast
from .models.distilbert import DistilBertTokenizerFast from .models.distilbert import DistilBertTokenizerFast
from .models.dpr import ( from .models.dpr import (
...@@ -5656,7 +5659,6 @@ if TYPE_CHECKING: ...@@ -5656,7 +5659,6 @@ if TYPE_CHECKING:
from .models.openai import OpenAIGPTTokenizerFast from .models.openai import OpenAIGPTTokenizerFast
from .models.pegasus import PegasusTokenizerFast from .models.pegasus import PegasusTokenizerFast
from .models.qwen2 import Qwen2TokenizerFast from .models.qwen2 import Qwen2TokenizerFast
from .models.realm import RealmTokenizerFast
from .models.reformer import ReformerTokenizerFast from .models.reformer import ReformerTokenizerFast
from .models.rembert import RemBertTokenizerFast from .models.rembert import RemBertTokenizerFast
from .models.roberta import RobertaTokenizerFast from .models.roberta import RobertaTokenizerFast
...@@ -5726,11 +5728,13 @@ if TYPE_CHECKING: ...@@ -5726,11 +5728,13 @@ if TYPE_CHECKING:
DeformableDetrImageProcessor, DeformableDetrImageProcessor,
) )
from .models.deit import DeiTFeatureExtractor, DeiTImageProcessor from .models.deit import DeiTFeatureExtractor, DeiTImageProcessor
from .models.deta import DetaImageProcessor from .models.deprecated.deta import DetaImageProcessor
from .models.deprecated.efficientformer import EfficientFormerImageProcessor
from .models.deprecated.tvlt import TvltImageProcessor
from .models.deprecated.vit_hybrid import ViTHybridImageProcessor
from .models.detr import DetrFeatureExtractor, DetrImageProcessor from .models.detr import DetrFeatureExtractor, DetrImageProcessor
from .models.donut import DonutFeatureExtractor, DonutImageProcessor from .models.donut import DonutFeatureExtractor, DonutImageProcessor
from .models.dpt import DPTFeatureExtractor, DPTImageProcessor from .models.dpt import DPTFeatureExtractor, DPTImageProcessor
from .models.efficientformer import EfficientFormerImageProcessor
from .models.efficientnet import EfficientNetImageProcessor from .models.efficientnet import EfficientNetImageProcessor
from .models.flava import ( from .models.flava import (
FlavaFeatureExtractor, FlavaFeatureExtractor,
...@@ -5784,13 +5788,11 @@ if TYPE_CHECKING: ...@@ -5784,13 +5788,11 @@ if TYPE_CHECKING:
from .models.siglip import SiglipImageProcessor from .models.siglip import SiglipImageProcessor
from .models.superpoint import SuperPointImageProcessor from .models.superpoint import SuperPointImageProcessor
from .models.swin2sr import Swin2SRImageProcessor from .models.swin2sr import Swin2SRImageProcessor
from .models.tvlt import TvltImageProcessor
from .models.tvp import TvpImageProcessor from .models.tvp import TvpImageProcessor
from .models.video_llava import VideoLlavaImageProcessor from .models.video_llava import VideoLlavaImageProcessor
from .models.videomae import VideoMAEFeatureExtractor, VideoMAEImageProcessor from .models.videomae import VideoMAEFeatureExtractor, VideoMAEImageProcessor
from .models.vilt import ViltFeatureExtractor, ViltImageProcessor, ViltProcessor from .models.vilt import ViltFeatureExtractor, ViltImageProcessor, ViltProcessor
from .models.vit import ViTFeatureExtractor, ViTImageProcessor from .models.vit import ViTFeatureExtractor, ViTImageProcessor
from .models.vit_hybrid import ViTHybridImageProcessor
from .models.vitmatte import VitMatteImageProcessor from .models.vitmatte import VitMatteImageProcessor
from .models.vivit import VivitImageProcessor from .models.vivit import VivitImageProcessor
from .models.yolos import YolosFeatureExtractor, YolosImageProcessor from .models.yolos import YolosFeatureExtractor, YolosImageProcessor
...@@ -6300,26 +6302,116 @@ if TYPE_CHECKING: ...@@ -6300,26 +6302,116 @@ if TYPE_CHECKING:
DeiTModel, DeiTModel,
DeiTPreTrainedModel, DeiTPreTrainedModel,
) )
from .models.deprecated.deta import (
DetaForObjectDetection,
DetaModel,
DetaPreTrainedModel,
)
from .models.deprecated.efficientformer import (
EfficientFormerForImageClassification,
EfficientFormerForImageClassificationWithTeacher,
EfficientFormerModel,
EfficientFormerPreTrainedModel,
)
from .models.deprecated.ernie_m import (
ErnieMForInformationExtraction,
ErnieMForMultipleChoice,
ErnieMForQuestionAnswering,
ErnieMForSequenceClassification,
ErnieMForTokenClassification,
ErnieMModel,
ErnieMPreTrainedModel,
)
from .models.deprecated.gptsan_japanese import (
GPTSanJapaneseForConditionalGeneration,
GPTSanJapaneseModel,
GPTSanJapanesePreTrainedModel,
)
from .models.deprecated.graphormer import (
GraphormerForGraphClassification,
GraphormerModel,
GraphormerPreTrainedModel,
)
from .models.deprecated.jukebox import (
JukeboxModel,
JukeboxPreTrainedModel,
JukeboxPrior,
JukeboxVQVAE,
)
from .models.deprecated.mctct import ( from .models.deprecated.mctct import (
MCTCTForCTC, MCTCTForCTC,
MCTCTModel, MCTCTModel,
MCTCTPreTrainedModel, MCTCTPreTrainedModel,
) )
from .models.deprecated.mega import (
MegaForCausalLM,
MegaForMaskedLM,
MegaForMultipleChoice,
MegaForQuestionAnswering,
MegaForSequenceClassification,
MegaForTokenClassification,
MegaModel,
MegaPreTrainedModel,
)
from .models.deprecated.mmbt import ( from .models.deprecated.mmbt import (
MMBTForClassification, MMBTForClassification,
MMBTModel, MMBTModel,
ModalEmbeddings, ModalEmbeddings,
) )
from .models.deprecated.nat import (
NatBackbone,
NatForImageClassification,
NatModel,
NatPreTrainedModel,
)
from .models.deprecated.nezha import (
NezhaForMaskedLM,
NezhaForMultipleChoice,
NezhaForNextSentencePrediction,
NezhaForPreTraining,
NezhaForQuestionAnswering,
NezhaForSequenceClassification,
NezhaForTokenClassification,
NezhaModel,
NezhaPreTrainedModel,
)
from .models.deprecated.open_llama import ( from .models.deprecated.open_llama import (
OpenLlamaForCausalLM, OpenLlamaForCausalLM,
OpenLlamaForSequenceClassification, OpenLlamaForSequenceClassification,
OpenLlamaModel, OpenLlamaModel,
OpenLlamaPreTrainedModel, OpenLlamaPreTrainedModel,
) )
from .models.deprecated.qdqbert import (
QDQBertForMaskedLM,
QDQBertForMultipleChoice,
QDQBertForNextSentencePrediction,
QDQBertForQuestionAnswering,
QDQBertForSequenceClassification,
QDQBertForTokenClassification,
QDQBertLayer,
QDQBertLMHeadModel,
QDQBertModel,
QDQBertPreTrainedModel,
load_tf_weights_in_qdqbert,
)
from .models.deprecated.realm import (
RealmEmbedder,
RealmForOpenQA,
RealmKnowledgeAugEncoder,
RealmPreTrainedModel,
RealmReader,
RealmRetriever,
RealmScorer,
load_tf_weights_in_realm,
)
from .models.deprecated.retribert import ( from .models.deprecated.retribert import (
RetriBertModel, RetriBertModel,
RetriBertPreTrainedModel, RetriBertPreTrainedModel,
) )
from .models.deprecated.speech_to_text_2 import (
Speech2Text2ForCausalLM,
Speech2Text2PreTrainedModel,
)
from .models.deprecated.trajectory_transformer import ( from .models.deprecated.trajectory_transformer import (
TrajectoryTransformerModel, TrajectoryTransformerModel,
TrajectoryTransformerPreTrainedModel, TrajectoryTransformerPreTrainedModel,
...@@ -6332,20 +6424,34 @@ if TYPE_CHECKING: ...@@ -6332,20 +6424,34 @@ if TYPE_CHECKING:
TransfoXLPreTrainedModel, TransfoXLPreTrainedModel,
load_tf_weights_in_transfo_xl, load_tf_weights_in_transfo_xl,
) )
from .models.deprecated.tvlt import (
TvltForAudioVisualClassification,
TvltForPreTraining,
TvltModel,
TvltPreTrainedModel,
)
from .models.deprecated.van import ( from .models.deprecated.van import (
VanForImageClassification, VanForImageClassification,
VanModel, VanModel,
VanPreTrainedModel, VanPreTrainedModel,
) )
from .models.deprecated.vit_hybrid import (
ViTHybridForImageClassification,
ViTHybridModel,
ViTHybridPreTrainedModel,
)
from .models.deprecated.xlm_prophetnet import (
XLMProphetNetDecoder,
XLMProphetNetEncoder,
XLMProphetNetForCausalLM,
XLMProphetNetForConditionalGeneration,
XLMProphetNetModel,
XLMProphetNetPreTrainedModel,
)
from .models.depth_anything import ( from .models.depth_anything import (
DepthAnythingForDepthEstimation, DepthAnythingForDepthEstimation,
DepthAnythingPreTrainedModel, DepthAnythingPreTrainedModel,
) )
from .models.deta import (
DetaForObjectDetection,
DetaModel,
DetaPreTrainedModel,
)
from .models.detr import ( from .models.detr import (
DetrForObjectDetection, DetrForObjectDetection,
DetrForSegmentation, DetrForSegmentation,
...@@ -6392,12 +6498,6 @@ if TYPE_CHECKING: ...@@ -6392,12 +6498,6 @@ if TYPE_CHECKING:
DPTModel, DPTModel,
DPTPreTrainedModel, DPTPreTrainedModel,
) )
from .models.efficientformer import (
EfficientFormerForImageClassification,
EfficientFormerForImageClassificationWithTeacher,
EfficientFormerModel,
EfficientFormerPreTrainedModel,
)
from .models.efficientnet import ( from .models.efficientnet import (
EfficientNetForImageClassification, EfficientNetForImageClassification,
EfficientNetModel, EfficientNetModel,
...@@ -6432,15 +6532,6 @@ if TYPE_CHECKING: ...@@ -6432,15 +6532,6 @@ if TYPE_CHECKING:
ErnieModel, ErnieModel,
ErniePreTrainedModel, ErniePreTrainedModel,
) )
from .models.ernie_m import (
ErnieMForInformationExtraction,
ErnieMForMultipleChoice,
ErnieMForQuestionAnswering,
ErnieMForSequenceClassification,
ErnieMForTokenClassification,
ErnieMModel,
ErnieMPreTrainedModel,
)
from .models.esm import ( from .models.esm import (
EsmFoldPreTrainedModel, EsmFoldPreTrainedModel,
EsmForMaskedLM, EsmForMaskedLM,
...@@ -6589,16 +6680,6 @@ if TYPE_CHECKING: ...@@ -6589,16 +6680,6 @@ if TYPE_CHECKING:
GPTJModel, GPTJModel,
GPTJPreTrainedModel, GPTJPreTrainedModel,
) )
from .models.gptsan_japanese import (
GPTSanJapaneseForConditionalGeneration,
GPTSanJapaneseModel,
GPTSanJapanesePreTrainedModel,
)
from .models.graphormer import (
GraphormerForGraphClassification,
GraphormerModel,
GraphormerPreTrainedModel,
)
from .models.grounding_dino import ( from .models.grounding_dino import (
GroundingDinoForObjectDetection, GroundingDinoForObjectDetection,
GroundingDinoModel, GroundingDinoModel,
...@@ -6667,12 +6748,6 @@ if TYPE_CHECKING: ...@@ -6667,12 +6748,6 @@ if TYPE_CHECKING:
JetMoeModel, JetMoeModel,
JetMoePreTrainedModel, JetMoePreTrainedModel,
) )
from .models.jukebox import (
JukeboxModel,
JukeboxPreTrainedModel,
JukeboxPrior,
JukeboxVQVAE,
)
from .models.kosmos2 import ( from .models.kosmos2 import (
Kosmos2ForConditionalGeneration, Kosmos2ForConditionalGeneration,
Kosmos2Model, Kosmos2Model,
...@@ -6810,16 +6885,6 @@ if TYPE_CHECKING: ...@@ -6810,16 +6885,6 @@ if TYPE_CHECKING:
MBartModel, MBartModel,
MBartPreTrainedModel, MBartPreTrainedModel,
) )
from .models.mega import (
MegaForCausalLM,
MegaForMaskedLM,
MegaForMultipleChoice,
MegaForQuestionAnswering,
MegaForSequenceClassification,
MegaForTokenClassification,
MegaModel,
MegaPreTrainedModel,
)
from .models.megatron_bert import ( from .models.megatron_bert import (
MegatronBertForCausalLM, MegatronBertForCausalLM,
MegatronBertForMaskedLM, MegatronBertForMaskedLM,
...@@ -6946,23 +7011,6 @@ if TYPE_CHECKING: ...@@ -6946,23 +7011,6 @@ if TYPE_CHECKING:
MvpModel, MvpModel,
MvpPreTrainedModel, MvpPreTrainedModel,
) )
from .models.nat import (
NatBackbone,
NatForImageClassification,
NatModel,
NatPreTrainedModel,
)
from .models.nezha import (
NezhaForMaskedLM,
NezhaForMultipleChoice,
NezhaForNextSentencePrediction,
NezhaForPreTraining,
NezhaForQuestionAnswering,
NezhaForSequenceClassification,
NezhaForTokenClassification,
NezhaModel,
NezhaPreTrainedModel,
)
from .models.nllb_moe import ( from .models.nllb_moe import (
NllbMoeForConditionalGeneration, NllbMoeForConditionalGeneration,
NllbMoeModel, NllbMoeModel,
...@@ -7125,19 +7173,6 @@ if TYPE_CHECKING: ...@@ -7125,19 +7173,6 @@ if TYPE_CHECKING:
PvtV2Model, PvtV2Model,
PvtV2PreTrainedModel, PvtV2PreTrainedModel,
) )
from .models.qdqbert import (
QDQBertForMaskedLM,
QDQBertForMultipleChoice,
QDQBertForNextSentencePrediction,
QDQBertForQuestionAnswering,
QDQBertForSequenceClassification,
QDQBertForTokenClassification,
QDQBertLayer,
QDQBertLMHeadModel,
QDQBertModel,
QDQBertPreTrainedModel,
load_tf_weights_in_qdqbert,
)
from .models.qwen2 import ( from .models.qwen2 import (
Qwen2ForCausalLM, Qwen2ForCausalLM,
Qwen2ForSequenceClassification, Qwen2ForSequenceClassification,
...@@ -7158,16 +7193,6 @@ if TYPE_CHECKING: ...@@ -7158,16 +7193,6 @@ if TYPE_CHECKING:
RagSequenceForGeneration, RagSequenceForGeneration,
RagTokenForGeneration, RagTokenForGeneration,
) )
from .models.realm import (
RealmEmbedder,
RealmForOpenQA,
RealmKnowledgeAugEncoder,
RealmPreTrainedModel,
RealmReader,
RealmRetriever,
RealmScorer,
load_tf_weights_in_realm,
)
from .models.recurrent_gemma import ( from .models.recurrent_gemma import (
RecurrentGemmaForCausalLM, RecurrentGemmaForCausalLM,
RecurrentGemmaModel, RecurrentGemmaModel,
...@@ -7318,10 +7343,6 @@ if TYPE_CHECKING: ...@@ -7318,10 +7343,6 @@ if TYPE_CHECKING:
Speech2TextModel, Speech2TextModel,
Speech2TextPreTrainedModel, Speech2TextPreTrainedModel,
) )
from .models.speech_to_text_2 import (
Speech2Text2ForCausalLM,
Speech2Text2PreTrainedModel,
)
from .models.speecht5 import ( from .models.speecht5 import (
SpeechT5ForSpeechToSpeech, SpeechT5ForSpeechToSpeech,
SpeechT5ForSpeechToText, SpeechT5ForSpeechToText,
...@@ -7435,12 +7456,6 @@ if TYPE_CHECKING: ...@@ -7435,12 +7456,6 @@ if TYPE_CHECKING:
TrOCRForCausalLM, TrOCRForCausalLM,
TrOCRPreTrainedModel, TrOCRPreTrainedModel,
) )
from .models.tvlt import (
TvltForAudioVisualClassification,
TvltForPreTraining,
TvltModel,
TvltPreTrainedModel,
)
from .models.tvp import ( from .models.tvp import (
TvpForVideoGrounding, TvpForVideoGrounding,
TvpModel, TvpModel,
...@@ -7525,11 +7540,6 @@ if TYPE_CHECKING: ...@@ -7525,11 +7540,6 @@ if TYPE_CHECKING:
ViTModel, ViTModel,
ViTPreTrainedModel, ViTPreTrainedModel,
) )
from .models.vit_hybrid import (
ViTHybridForImageClassification,
ViTHybridModel,
ViTHybridPreTrainedModel,
)
from .models.vit_mae import ( from .models.vit_mae import (
ViTMAEForPreTraining, ViTMAEForPreTraining,
ViTMAELayer, ViTMAELayer,
...@@ -7622,14 +7632,6 @@ if TYPE_CHECKING: ...@@ -7622,14 +7632,6 @@ if TYPE_CHECKING:
XLMPreTrainedModel, XLMPreTrainedModel,
XLMWithLMHeadModel, XLMWithLMHeadModel,
) )
from .models.xlm_prophetnet import (
XLMProphetNetDecoder,
XLMProphetNetEncoder,
XLMProphetNetForCausalLM,
XLMProphetNetForConditionalGeneration,
XLMProphetNetModel,
XLMProphetNetPreTrainedModel,
)
from .models.xlm_roberta import ( from .models.xlm_roberta import (
XLMRobertaForCausalLM, XLMRobertaForCausalLM,
XLMRobertaForMaskedLM, XLMRobertaForMaskedLM,
...@@ -7921,6 +7923,12 @@ if TYPE_CHECKING: ...@@ -7921,6 +7923,12 @@ if TYPE_CHECKING:
TFDeiTModel, TFDeiTModel,
TFDeiTPreTrainedModel, TFDeiTPreTrainedModel,
) )
from .models.deprecated.efficientformer import (
TFEfficientFormerForImageClassification,
TFEfficientFormerForImageClassificationWithTeacher,
TFEfficientFormerModel,
TFEfficientFormerPreTrainedModel,
)
from .models.deprecated.transfo_xl import ( from .models.deprecated.transfo_xl import (
TFAdaptiveEmbedding, TFAdaptiveEmbedding,
TFTransfoXLForSequenceClassification, TFTransfoXLForSequenceClassification,
...@@ -7947,12 +7955,6 @@ if TYPE_CHECKING: ...@@ -7947,12 +7955,6 @@ if TYPE_CHECKING:
TFDPRQuestionEncoder, TFDPRQuestionEncoder,
TFDPRReader, TFDPRReader,
) )
from .models.efficientformer import (
TFEfficientFormerForImageClassification,
TFEfficientFormerForImageClassificationWithTeacher,
TFEfficientFormerModel,
TFEfficientFormerPreTrainedModel,
)
from .models.electra import ( from .models.electra import (
TFElectraForMaskedLM, TFElectraForMaskedLM,
TFElectraForMultipleChoice, TFElectraForMultipleChoice,
......
src/transformers/models/__init__.py
View file @ a564d10a
...@@ -67,7 +67,6 @@ from . import ( ...@@ -67,7 +67,6 @@ from . import (
deit, deit,
deprecated, deprecated,
depth_anything, depth_anything,
deta,
detr, detr,
dialogpt, dialogpt,
dinat, dinat,
...@@ -77,13 +76,11 @@ from . import ( ...@@ -77,13 +76,11 @@ from . import (
donut, donut,
dpr, dpr,
dpt, dpt,
efficientformer,
efficientnet, efficientnet,
electra, electra,
encodec, encodec,
encoder_decoder, encoder_decoder,
ernie, ernie,
ernie_m,
esm, esm,
falcon, falcon,
fastspeech2_conformer, fastspeech2_conformer,
...@@ -104,8 +101,6 @@ from . import ( ...@@ -104,8 +101,6 @@ from . import (
gpt_neox_japanese, gpt_neox_japanese,
gpt_sw3, gpt_sw3,
gptj, gptj,
gptsan_japanese,
graphormer,
grounding_dino, grounding_dino,
groupvit, groupvit,
herbert, herbert,
...@@ -118,7 +113,6 @@ from . import ( ...@@ -118,7 +113,6 @@ from . import (
instructblip, instructblip,
jamba, jamba,
jetmoe, jetmoe,
jukebox,
kosmos2, kosmos2,
layoutlm, layoutlm,
layoutlmv2, layoutlmv2,
...@@ -142,7 +136,6 @@ from . import ( ...@@ -142,7 +136,6 @@ from . import (
maskformer, maskformer,
mbart, mbart,
mbart50, mbart50,
mega,
megatron_bert, megatron_bert,
megatron_gpt2, megatron_gpt2,
mgp_str, mgp_str,
...@@ -161,8 +154,6 @@ from . import ( ...@@ -161,8 +154,6 @@ from . import (
musicgen, musicgen,
musicgen_melody, musicgen_melody,
mvp, mvp,
nat,
nezha,
nllb, nllb,
nllb_moe, nllb_moe,
nougat, nougat,
...@@ -190,11 +181,9 @@ from . import ( ...@@ -190,11 +181,9 @@ from . import (
prophetnet, prophetnet,
pvt, pvt,
pvt_v2, pvt_v2,
qdqbert,
qwen2, qwen2,
qwen2_moe, qwen2_moe,
rag, rag,
realm,
recurrent_gemma, recurrent_gemma,
reformer, reformer,
regnet, regnet,
...@@ -215,7 +204,6 @@ from . import ( ...@@ -215,7 +204,6 @@ from . import (
siglip, siglip,
speech_encoder_decoder, speech_encoder_decoder,
speech_to_text, speech_to_text,
speech_to_text_2,
speecht5, speecht5,
splinter, splinter,
squeezebert, squeezebert,
...@@ -234,7 +222,6 @@ from . import ( ...@@ -234,7 +222,6 @@ from . import (
timesformer, timesformer,
timm_backbone, timm_backbone,
trocr, trocr,
tvlt,
tvp, tvp,
udop, udop,
umt5, umt5,
...@@ -250,7 +237,6 @@ from . import ( ...@@ -250,7 +237,6 @@ from . import (
vision_text_dual_encoder, vision_text_dual_encoder,
visual_bert, visual_bert,
vit, vit,
vit_hybrid,
vit_mae, vit_mae,
vit_msn, vit_msn,
vitdet, vitdet,
...@@ -267,7 +253,6 @@ from . import ( ...@@ -267,7 +253,6 @@ from . import (
x_clip, x_clip,
xglm, xglm,
xlm, xlm,
xlm_prophetnet,
xlm_roberta, xlm_roberta,
xlm_roberta_xl, xlm_roberta_xl,
xlnet, xlnet,
......
src/transformers/models/auto/configuration_auto.py
View file @ a564d10a
...@@ -585,14 +585,29 @@ MODEL_NAMES_MAPPING = OrderedDict( ...@@ -585,14 +585,29 @@ MODEL_NAMES_MAPPING = OrderedDict(
# `transfo-xl` (as in `CONFIG_MAPPING_NAMES`), we should use `transfo_xl`. # `transfo-xl` (as in `CONFIG_MAPPING_NAMES`), we should use `transfo_xl`.
DEPRECATED_MODELS = [ DEPRECATED_MODELS = [
"bort", "bort",
"deta",
"efficientformer",
"ernie_m",
"gptsan_japanese",
"graphormer",
"jukebox",
"mctct", "mctct",
"mega",
"mmbt", "mmbt",
"nat",
"nezha",
"open_llama", "open_llama",
"qdqbert",
"realm",
"retribert", "retribert",
"speech_to_text_2",
"tapex", "tapex",
"trajectory_transformer", "trajectory_transformer",
"transfo_xl", "transfo_xl",
"tvlt",
"van", "van",
"vit_hybrid",
"xlm_prophetnet",
] ]
SPECIAL_MODEL_TYPE_TO_MODULE_NAME = OrderedDict( SPECIAL_MODEL_TYPE_TO_MODULE_NAME = OrderedDict(
...@@ -616,7 +631,11 @@ def model_type_to_module_name(key): ...@@ -616,7 +631,11 @@ def model_type_to_module_name(key):
"""Converts a config key to the corresponding module.""" """Converts a config key to the corresponding module."""
# Special treatment # Special treatment
if key in SPECIAL_MODEL_TYPE_TO_MODULE_NAME: if key in SPECIAL_MODEL_TYPE_TO_MODULE_NAME:
return SPECIAL_MODEL_TYPE_TO_MODULE_NAME[key] key = SPECIAL_MODEL_TYPE_TO_MODULE_NAME[key]
if key in DEPRECATED_MODELS:
key = f"deprecated.{key}"
return key
key = key.replace("-", "_") key = key.replace("-", "_")
if key in DEPRECATED_MODELS: if key in DEPRECATED_MODELS:
......
src/transformers/models/deta/__init__.py → src/transformers/models/deprecated/deta/__init__.py
View file @ a564d10a
...@@ -14,7 +14,7 @@ ...@@ -14,7 +14,7 @@
from typing import TYPE_CHECKING from typing import TYPE_CHECKING
from ...utils import OptionalDependencyNotAvailable, _LazyModule, is_torch_available, is_vision_available from ....utils import OptionalDependencyNotAvailable, _LazyModule, is_torch_available, is_vision_available
_import_structure = { _import_structure = {
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment