Auto Classes

In many cases, the architecture you want to use can be guessed from the name or the path of the pretrained model you are supplying to the from_pretrained() method. AutoClasses are here to do this job for you so that you automatically retrieve the relevant model given the name/path to the pretrained weights/config/vocabulary.

Instantiating one of AutoConfig, AutoModel, and AutoTokenizer will directly create a class of the relevant architecture. For instance

model = AutoModel.from_pretrained("google-bert/bert-base-cased")

will create a model that is an instance of BertModel.

There is one class of AutoModel for each task.

Extending the Auto Classes

Each of the auto classes has a method to be extended with your custom classes. For instance, if you have defined a custom class of model NewModel, make sure you have a NewModelConfig then you can add those to the auto classes like this:

from transformers import AutoConfig, AutoModel

AutoConfig.register("new-model", NewModelConfig)
AutoModel.register(NewModelConfig, NewModel)

You will then be able to use the auto classes like you would usually do!

If your NewModelConfig is a subclass of PreTrainedConfig, make sure its model_type attribute is set to the same key you use when registering the config (here "new-model").

Likewise, if your NewModel is a subclass of PreTrainedModel, make sure its config_class attribute is set to the same class you use when registering the model (here NewModelConfig).

AutoConfig

[[autodoc]] AutoConfig

AutoTokenizer

[[autodoc]] AutoTokenizer

AutoFeatureExtractor

[[autodoc]] AutoFeatureExtractor

AutoImageProcessor

[[autodoc]] AutoImageProcessor

AutoVideoProcessor

[[autodoc]] AutoVideoProcessor

AutoProcessor

[[autodoc]] AutoProcessor

Generic model classes

The following auto classes are available for instantiating a base model class without a specific head.

AutoModel

[[autodoc]] AutoModel

Generic pretraining classes

The following auto classes are available for instantiating a model with a pretraining head.

AutoModelForPreTraining

[[autodoc]] AutoModelForPreTraining

Natural Language Processing

The following auto classes are available for the following natural language processing tasks.

AutoModelForCausalLM

[[autodoc]] AutoModelForCausalLM

AutoModelForMaskedLM

[[autodoc]] AutoModelForMaskedLM

AutoModelForMaskGeneration

[[autodoc]] AutoModelForMaskGeneration

AutoModelForSeq2SeqLM

[[autodoc]] AutoModelForSeq2SeqLM

AutoModelForSequenceClassification

[[autodoc]] AutoModelForSequenceClassification

AutoModelForMultipleChoice

[[autodoc]] AutoModelForMultipleChoice

AutoModelForNextSentencePrediction

[[autodoc]] AutoModelForNextSentencePrediction

AutoModelForTokenClassification

[[autodoc]] AutoModelForTokenClassification

AutoModelForQuestionAnswering

[[autodoc]] AutoModelForQuestionAnswering

AutoModelForTextEncoding

[[autodoc]] AutoModelForTextEncoding

Computer vision

The following auto classes are available for the following computer vision tasks.

AutoModelForDepthEstimation

[[autodoc]] AutoModelForDepthEstimation

AutoModelForImageClassification

[[autodoc]] AutoModelForImageClassification

AutoModelForVideoClassification

[[autodoc]] AutoModelForVideoClassification

AutoModelForKeypointDetection

[[autodoc]] AutoModelForKeypointDetection

AutoModelForKeypointMatching

[[autodoc]] AutoModelForKeypointMatching

AutoModelForMaskedImageModeling

[[autodoc]] AutoModelForMaskedImageModeling

AutoModelForObjectDetection

[[autodoc]] AutoModelForObjectDetection

AutoModelForImageSegmentation

[[autodoc]] AutoModelForImageSegmentation

AutoModelForImageToImage

[[autodoc]] AutoModelForImageToImage

AutoModelForSemanticSegmentation

[[autodoc]] AutoModelForSemanticSegmentation

AutoModelForInstanceSegmentation

[[autodoc]] AutoModelForInstanceSegmentation

AutoModelForUniversalSegmentation

[[autodoc]] AutoModelForUniversalSegmentation

AutoModelForZeroShotImageClassification

[[autodoc]] AutoModelForZeroShotImageClassification

AutoModelForZeroShotObjectDetection

[[autodoc]] AutoModelForZeroShotObjectDetection

Audio

The following auto classes are available for the following audio tasks.

AutoModelForAudioClassification

[[autodoc]] AutoModelForAudioClassification

AutoModelForAudioFrameClassification

[[autodoc]] AutoModelForAudioFrameClassification

AutoModelForCTC

[[autodoc]] AutoModelForCTC

AutoModelForSpeechSeq2Seq

[[autodoc]] AutoModelForSpeechSeq2Seq

AutoModelForAudioXVector

[[autodoc]] AutoModelForAudioXVector

AutoModelForTextToSpectrogram

[[autodoc]] AutoModelForTextToSpectrogram

AutoModelForTextToWaveform

[[autodoc]] AutoModelForTextToWaveform

AutoModelForAudioTokenization

[[autodoc]] AutoModelForAudioTokenization

Multimodal

The following auto classes are available for the following multimodal tasks.

AutoModelForMultimodalLM

[[autodoc]] AutoModelForMultimodalLM

AutoModelForTableQuestionAnswering

[[autodoc]] AutoModelForTableQuestionAnswering

AutoModelForDocumentQuestionAnswering

[[autodoc]] AutoModelForDocumentQuestionAnswering

AutoModelForVisualQuestionAnswering

[[autodoc]] AutoModelForVisualQuestionAnswering

AutoModelForVision2Seq

[[autodoc]] AutoModelForVision2Seq

AutoModelForImageTextToText

[[autodoc]] AutoModelForImageTextToText

Time Series

AutoModelForTimeSeriesPrediction

[[autodoc]] AutoModelForTimeSeriesPrediction