> For the complete documentation index, see [llms.txt](https://boinc-ai.gitbook.io/transformers/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://boinc-ai.gitbook.io/transformers/api/models/multimodal-models/data2vec.md).

# Data2Vec

## Data2Vec

### Overview

The Data2Vec model was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli. Data2Vec proposes a unified framework for self-supervised learning across different data modalities - text, audio and images. Importantly, predicted targets for pre-training are contextualized latent representations of the inputs, rather than modality-specific, context-independent targets.

The abstract from the paper is the following:

*While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised learning, we present data2vec, a framework that uses the same learning method for either speech, NLP or computer vision. The core idea is to predict latent representations of the full input data based on a masked view of the input in a selfdistillation setup using a standard Transformer architecture. Instead of predicting modality-specific targets such as words, visual tokens or units of human speech which are local in nature, data2vec predicts contextualized latent representations that contain information from the entire input. Experiments on the major benchmarks of speech recognition, image classification, and natural language understanding demonstrate a new state of the art or competitive performance to predominant approaches. Models and code are available at* [*www.github.com/pytorch/fairseq/tree/master/examples/data2vec*](http://www.github.com/pytorch/fairseq/tree/master/examples/data2vec)*.*

Tips:

* Data2VecAudio, Data2VecText, and Data2VecVision have all been trained using the same self-supervised learning method.
* For Data2VecAudio, preprocessing is identical to [Wav2Vec2Model](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Model), including feature extraction
* For Data2VecText, preprocessing is identical to [RobertaModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/roberta#transformers.RobertaModel), including tokenization.
* For Data2VecVision, preprocessing is identical to [BeitModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/beit#transformers.BeitModel), including feature extraction.

This model was contributed by [edugp](https://huggingface.co/edugp) and [patrickvonplaten](https://huggingface.co/patrickvonplaten). [sayakpaul](https://github.com/sayakpaul) and [Rocketknight1](https://github.com/Rocketknight1) contributed Data2Vec for vision in TensorFlow.

The original code (for NLP and Speech) can be found [here](https://github.com/pytorch/fairseq/tree/main/examples/data2vec). The original code for vision can be found [here](https://github.com/facebookresearch/data2vec_vision/tree/main/beit).

### Resources

A list of official BOINC AI and community (indicated by 🌎) resources to help you get started with Data2Vec.

Image Classification

* [Data2VecVisionForImageClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionForImageClassification) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/image-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb).
* To fine-tune [TFData2VecVisionForImageClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.TFData2VecVisionForImageClassification) on a custom dataset, see [this notebook](https://colab.research.google.com/github/sayakpaul/TF-2.0-Hacks/blob/master/data2vec_vision_image_classification.ipynb).

**Data2VecText documentation resources**

* [Text classification task guide](https://huggingface.co/docs/transformers/tasks/sequence_classification)
* [Token classification task guide](https://huggingface.co/docs/transformers/tasks/token_classification)
* [Question answering task guide](https://huggingface.co/docs/transformers/tasks/question_answering)
* [Causal language modeling task guide](https://huggingface.co/docs/transformers/tasks/language_modeling)
* [Masked language modeling task guide](https://huggingface.co/docs/transformers/tasks/masked_language_modeling)
* [Multiple choice task guide](https://huggingface.co/docs/transformers/tasks/multiple_choice)

**Data2VecAudio documentation resources**

* [Audio classification task guide](https://huggingface.co/docs/transformers/tasks/audio_classification)
* [Automatic speech recognition task guide](https://huggingface.co/docs/transformers/tasks/asr)

**Data2VecVision documentation resources**

* [Image classification](https://huggingface.co/docs/transformers/tasks/image_classification)
* [Semantic segmentation](https://huggingface.co/docs/transformers/tasks/semantic_segmentation)

If you’re interested in submitting a resource to be included here, please feel free to open a Pull Request and we’ll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

### Data2VecTextConfig

#### class transformers.Data2VecTextConfig

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/configuration_data2vec_text.py#L31)

( vocab\_size = 30522hidden\_size = 768num\_hidden\_layers = 12num\_attention\_heads = 12intermediate\_size = 3072hidden\_act = 'gelu'hidden\_dropout\_prob = 0.1attention\_probs\_dropout\_prob = 0.1max\_position\_embeddings = 512type\_vocab\_size = 2initializer\_range = 0.02layer\_norm\_eps = 1e-12pad\_token\_id = 1bos\_token\_id = 0eos\_token\_id = 2position\_embedding\_type = 'absolute'use\_cache = Trueclassifier\_dropout = None\*\*kwargs )

Parameters

* **vocab\_size** (`int`, *optional*, defaults to 30522) — Vocabulary size of the DATA2VEC model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling `Data2VecModel`.
* **hidden\_size** (`int`, *optional*, defaults to 768) — Dimensionality of the encoder layers and the pooler layer.
* **num\_hidden\_layers** (`int`, *optional*, defaults to 12) — Number of hidden layers in the Transformer encoder.
* **num\_attention\_heads** (`int`, *optional*, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder.
* **intermediate\_size** (`int`, *optional*, defaults to 3072) — Dimensionality of the “intermediate” (often named feed-forward) layer in the Transformer encoder.
* **hidden\_act** (`str` or `Callable`, *optional*, defaults to `"gelu"`) — The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported.
* **hidden\_dropout\_prob** (`float`, *optional*, defaults to 0.1) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
* **attention\_probs\_dropout\_prob** (`float`, *optional*, defaults to 0.1) — The dropout ratio for the attention probabilities.
* **max\_position\_embeddings** (`int`, *optional*, defaults to 512) — The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
* **type\_vocab\_size** (`int`, *optional*, defaults to 2) — The vocabulary size of the `token_type_ids` passed when calling `Data2VecModel`.
* **initializer\_range** (`float`, *optional*, defaults to 0.02) — The standard deviation of the truncated\_normal\_initializer for initializing all weight matrices.
* **layer\_norm\_eps** (`float`, *optional*, defaults to 1e-12) — The epsilon used by the layer normalization layers.
* **position\_embedding\_type** (`str`, *optional*, defaults to `"absolute"`) — Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
* **is\_decoder** (`bool`, *optional*, defaults to `False`) — Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.
* **use\_cache** (`bool`, *optional*, defaults to `True`) — Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`.
* **classifier\_dropout** (`float`, *optional*) — The dropout ratio for the classification head.

This is the configuration class to store the configuration of a [Data2VecTextModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextModel) and [Data2VecTextModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextModel). It is used to instantiate a Data2VecText model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Data2VecText [facebook/data2vec-text-base](https://huggingface.co/facebook/data2vec-text-base) architecture.

Configuration objects inherit from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) for more information.

Examples:

Copied

```
>>> from transformers import Data2VecTextConfig, Data2VecTextModel

>>> # Initializing a Data2VecText facebook/data2vec-text-base style configuration
>>> configuration = Data2VecTextConfig()

>>> # Initializing a model (with random weights) from the facebook/data2vec-text-base style configuration
>>> model = Data2VecTextModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```

### Data2VecAudioConfig

#### class transformers.Data2VecAudioConfig

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/configuration_data2vec_audio.py#L31)

( vocab\_size = 32hidden\_size = 768num\_hidden\_layers = 12num\_attention\_heads = 12intermediate\_size = 3072hidden\_act = 'gelu'hidden\_dropout = 0.1activation\_dropout = 0.1attention\_dropout = 0.1feat\_proj\_dropout = 0.0final\_dropout = 0.1layerdrop = 0.1initializer\_range = 0.02layer\_norm\_eps = 1e-05feat\_extract\_activation = 'gelu'conv\_dim = (512, 512, 512, 512, 512, 512, 512)conv\_stride = (5, 2, 2, 2, 2, 2, 2)conv\_kernel = (10, 3, 3, 3, 3, 2, 2)conv\_bias = Falsenum\_conv\_pos\_embedding\_groups = 16conv\_pos\_kernel\_size = 19num\_conv\_pos\_embeddings = 5mask\_time\_prob = 0.05mask\_time\_length = 10mask\_time\_min\_masks = 2mask\_feature\_prob = 0.0mask\_feature\_length = 10mask\_feature\_min\_masks = 0ctc\_loss\_reduction = 'sum'ctc\_zero\_infinity = Falseuse\_weighted\_layer\_sum = Falseclassifier\_proj\_size = 256tdnn\_dim = (512, 512, 512, 512, 1500)tdnn\_kernel = (5, 3, 3, 1, 1)tdnn\_dilation = (1, 2, 3, 1, 1)xvector\_output\_dim = 512pad\_token\_id = 0bos\_token\_id = 1eos\_token\_id = 2add\_adapter = Falseadapter\_kernel\_size = 3adapter\_stride = 2num\_adapter\_layers = 3output\_hidden\_size = None\*\*kwargs )

Parameters

* **vocab\_size** (`int`, *optional*, defaults to 32) — Vocabulary size of the Data2VecAudio model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [Data2VecAudioModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioModel) or `TFData2VecAudioModel`. Vocabulary size of the model. Defines the different tokens that can be represented by the *inputs\_ids* passed to the forward method of [Data2VecAudioModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioModel).
* **hidden\_size** (`int`, *optional*, defaults to 768) — Dimensionality of the encoder layers and the pooler layer.
* **num\_hidden\_layers** (`int`, *optional*, defaults to 12) — Number of hidden layers in the Transformer encoder.
* **num\_attention\_heads** (`int`, *optional*, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder.
* **intermediate\_size** (`int`, *optional*, defaults to 3072) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
* **hidden\_act** (`str` or `function`, *optional*, defaults to `"gelu"`) — The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported.
* **hidden\_dropout** (`float`, *optional*, defaults to 0.1) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
* **activation\_dropout** (`float`, *optional*, defaults to 0.1) — The dropout ratio for activations inside the fully connected layer.
* **attention\_dropout** (`float`, *optional*, defaults to 0.1) — The dropout ratio for the attention probabilities.
* **final\_dropout** (`float`, *optional*, defaults to 0.1) — The dropout probability for the final projection layer of [Data2VecAudioForCTC](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioForCTC).
* **layerdrop** (`float`, *optional*, defaults to 0.1) — The LayerDrop probability. See the \[LayerDrop paper]\(see <https://arxiv.org/abs/1909.11556>) for more details.
* **initializer\_range** (`float`, *optional*, defaults to 0.02) — The standard deviation of the truncated\_normal\_initializer for initializing all weight matrices.
* **layer\_norm\_eps** (`float`, *optional*, defaults to 1e-12) — The epsilon used by the layer normalization layers.
* **feat\_proj\_dropout** (`float`, *optional*, defaults to 0.0) — The dropout probability for output of the feature encoder.
* **feat\_extract\_activation** (`str,` optional`, defaults to` “gelu”`) -- The non-linear activation function (function or string) in the 1D convolutional layers of the feature extractor. If string,` “gelu”`,` “relu”`,` “selu”`and`“gelu\_new”\` are supported.
* **conv\_dim** (`Tuple[int]` or `List[int]`, *optional*, defaults to `(512, 512, 512, 512, 512, 512, 512)`) — A tuple of integers defining the number of input and output channels of each 1D convolutional layer in the feature encoder. The length of *conv\_dim* defines the number of 1D convolutional layers.
* **conv\_stride** (`Tuple[int]` or `List[int]`, *optional*, defaults to `(5, 2, 2, 2, 2, 2, 2)`) — A tuple of integers defining the stride of each 1D convolutional layer in the feature encoder. The length of *conv\_stride* defines the number of convolutional layers and has to match the length of *conv\_dim*.
* **conv\_kernel** (`Tuple[int]` or `List[int]`, *optional*, defaults to `(10, 3, 3, 3, 3, 3, 3)`) — A tuple of integers defining the kernel size of each 1D convolutional layer in the feature encoder. The length of *conv\_kernel* defines the number of convolutional layers and has to match the length of *conv\_dim*.
* **conv\_bias** (`bool`, *optional*, defaults to `False`) — Whether the 1D convolutional layers have a bias.
* **num\_conv\_pos\_embeddings** (`int`, *optional*, defaults to 128) — Number of convolutional positional embeddings. Defines the kernel size of 1D convolutional positional embeddings layer.
* **num\_conv\_pos\_embedding\_groups** (`int`, *optional*, defaults to 16) — Number of groups of 1D convolutional positional embeddings layer.
* **mask\_time\_prob** (`float`, *optional*, defaults to 0.05) — Percentage (between 0 and 1) of all feature vectors along the time axis which will be masked. The masking procecure generates ”mask\_time\_prob*len(time\_axis)/mask\_time\_length” independent masks over the axis. If reasoning from the propability of each feature vector to be chosen as the start of the vector span to be masked,* mask\_time\_prob *should be \`prob\_vector\_start*mask\_time\_length\`. Note that overlap may decrease the
* **mask\_time\_length** (`int`, *optional*, defaults to 10) — Length of vector span along the time axis.
* **mask\_time\_min\_masks** (`int`, *optional*, defaults to 2), — The minimum number of masks of length `mask_feature_length` generated along the time axis, each time step, irrespectively of `mask_feature_prob`. Only relevant if ”mask\_time\_prob\*len(time\_axis)/mask\_time\_length < mask\_time\_min\_masks”
* **mask\_feature\_prob** (`float`, *optional*, defaults to 0.0) — Percentage (between 0 and 1) of all feature vectors along the feature axis which will be masked. The masking procecure generates ”mask\_feature\_prob*len(feature\_axis)/mask\_time\_length” independent masks over the axis. If reasoning from the propability of each feature vector to be chosen as the start of the vector span to be masked,* mask\_feature\_prob *should be \`prob\_vector\_start*mask\_feature\_length`. Note that overlap may decrease the actual percentage of masked vectors. This is only relevant if` apply\_spec\_augment is True\`.
* **mask\_feature\_length** (`int`, *optional*, defaults to 10) — Length of vector span along the feature axis.
* **mask\_feature\_min\_masks** (`int`, *optional*, defaults to 0), — The minimum number of masks of length `mask_feature_length` generated along the feature axis, each time step, irrespectively of `mask_feature_prob`. Only relevant if ”mask\_feature\_prob\*len(feature\_axis)/mask\_feature\_length < mask\_feature\_min\_masks”
* **ctc\_loss\_reduction** (`str`, *optional*, defaults to `"sum"`) — Specifies the reduction to apply to the output of `torch.nn.CTCLoss`. Only relevant when training an instance of [Data2VecAudioForCTC](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioForCTC).
* **ctc\_zero\_infinity** (`bool`, *optional*, defaults to `False`) — Whether to zero infinite losses and the associated gradients of `torch.nn.CTCLoss`. Infinite losses mainly occur when the inputs are too short to be aligned to the targets. Only relevant when training an instance of [Data2VecAudioForCTC](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioForCTC).
* **use\_weighted\_layer\_sum** (`bool`, *optional*, defaults to `False`) — Whether to use a weighted average of layer outputs with learned weights. Only relevant when using an instance of [Data2VecAudioForSequenceClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioForSequenceClassification).
* **classifier\_proj\_size** (`int`, *optional*, defaults to 256) — Dimensionality of the projection before token mean-pooling for classification.
* **tdnn\_dim** (`Tuple[int]` or `List[int]`, *optional*, defaults to `(512, 512, 512, 512, 1500)`) — A tuple of integers defining the number of output channels of each 1D convolutional layer in the *TDNN* module of the *XVector* model. The length of *tdnn\_dim* defines the number of *TDNN* layers.
* **tdnn\_kernel** (`Tuple[int]` or `List[int]`, *optional*, defaults to `(5, 3, 3, 1, 1)`) — A tuple of integers defining the kernel size of each 1D convolutional layer in the *TDNN* module of the *XVector* model. The length of *tdnn\_kernel* has to match the length of *tdnn\_dim*.
* **tdnn\_dilation** (`Tuple[int]` or `List[int]`, *optional*, defaults to `(1, 2, 3, 1, 1)`) — A tuple of integers defining the dilation factor of each 1D convolutional layer in *TDNN* module of the *XVector* model. The length of *tdnn\_dilation* has to match the length of *tdnn\_dim*.
* **xvector\_output\_dim** (`int`, *optional*, defaults to 512) — Dimensionality of the *XVector* embedding vectors.
* **add\_adapter** (`bool`, *optional*, defaults to `False`) — Whether a convolutional network should be stacked on top of the Data2VecAudio Encoder. Can be very useful for warm-starting Data2VecAudio for SpeechEncoderDecoder models.
* **adapter\_kernel\_size** (`int`, *optional*, defaults to 3) — Kernel size of the convolutional layers in the adapter network. Only relevant if `add_adapter is True`.
* **adapter\_stride** (`int`, *optional*, defaults to 2) — Stride of the convolutional layers in the adapter network. Only relevant if `add_adapter is True`.
* **num\_adapter\_layers** (`int`, *optional*, defaults to 3) — Number of convolutional layers that should be used in the adapter network. Only relevant if `add_adapter is True`.
* **output\_hidden\_size** (`int`, *optional*) — Dimensionality of the encoder output layer. If not defined, this defaults to *hidden-size*. Only relevant if `add_adapter is True`.

This is the configuration class to store the configuration of a [Data2VecAudioModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioModel). It is used to instantiate an Data2VecAudio model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Data2VecAudio [facebook/data2vec-audio-base-960h](https://huggingface.co/facebook/data2vec-audio-base-960h) architecture.

Configuration objects inherit from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) for more information.

Example:

Copied

```
>>> from transformers import Data2VecAudioConfig, Data2VecAudioModel

>>> # Initializing a Data2VecAudio facebook/data2vec-audio-base-960h style configuration
>>> configuration = Data2VecAudioConfig()

>>> # Initializing a model (with random weights) from the facebook/data2vec-audio-base-960h style configuration
>>> model = Data2VecAudioModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```

### Data2VecVisionConfig

#### class transformers.Data2VecVisionConfig

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/configuration_data2vec_vision.py#L35)

( hidden\_size = 768num\_hidden\_layers = 12num\_attention\_heads = 12intermediate\_size = 3072hidden\_act = 'gelu'hidden\_dropout\_prob = 0.0attention\_probs\_dropout\_prob = 0.0initializer\_range = 0.02layer\_norm\_eps = 1e-12image\_size = 224patch\_size = 16num\_channels = 3use\_mask\_token = Falseuse\_absolute\_position\_embeddings = Falseuse\_relative\_position\_bias = Falseuse\_shared\_relative\_position\_bias = Falselayer\_scale\_init\_value = 0.1drop\_path\_rate = 0.1use\_mean\_pooling = Trueout\_indices = \[3, 5, 7, 11]pool\_scales = \[1, 2, 3, 6]use\_auxiliary\_head = Trueauxiliary\_loss\_weight = 0.4auxiliary\_channels = 256auxiliary\_num\_convs = 1auxiliary\_concat\_input = Falsesemantic\_loss\_ignore\_index = 255\*\*kwargs )

Parameters

* **hidden\_size** (`int`, *optional*, defaults to 768) — Dimensionality of the encoder layers and the pooler layer.
* **num\_hidden\_layers** (`int`, *optional*, defaults to 12) — Number of hidden layers in the Transformer encoder.
* **num\_attention\_heads** (`int`, *optional*, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder.
* **intermediate\_size** (`int`, *optional*, defaults to 3072) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
* **hidden\_act** (`str` or `function`, *optional*, defaults to `"gelu"`) — The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported.
* **hidden\_dropout\_prob** (`float`, *optional*, defaults to 0.0) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
* **attention\_probs\_dropout\_prob** (`float`, *optional*, defaults to 0.0) — The dropout ratio for the attention probabilities.
* **initializer\_range** (`float`, *optional*, defaults to 0.02) — The standard deviation of the truncated\_normal\_initializer for initializing all weight matrices.
* **layer\_norm\_eps** (`float`, *optional*, defaults to 1e-12) — The epsilon used by the layer normalization layers.
* **image\_size** (`int`, *optional*, defaults to 224) — The size (resolution) of each image.
* **patch\_size** (`int`, *optional*, defaults to 16) — The size (resolution) of each patch.
* **num\_channels** (`int`, *optional*, defaults to 3) — The number of input channels.
* **use\_mask\_token** (`bool`, *optional*, defaults to `False`) — Whether to use a mask token for masked image modeling.
* **use\_absolute\_position\_embeddings** (`bool`, *optional*, defaults to `False`) — Whether to use BERT-style absolute position embeddings.
* **use\_relative\_position\_bias** (`bool`, *optional*, defaults to `False`) — Whether to use T5-style relative position embeddings in the self-attention layers.
* **use\_shared\_relative\_position\_bias** (`bool`, *optional*, defaults to `False`) — Whether to use the same relative position embeddings across all self-attention layers of the Transformer.
* **layer\_scale\_init\_value** (`float`, *optional*, defaults to 0.1) — Scale to use in the self-attention layers. 0.1 for base, 1e-5 for large. Set 0 to disable layer scale.
* **drop\_path\_rate** (`float`, *optional*, defaults to 0.1) — Stochastic depth rate per sample (when applied in the main path of residual layers).
* **use\_mean\_pooling** (`bool`, *optional*, defaults to `True`) — Whether to mean pool the final hidden states of the patches instead of using the final hidden state of the CLS token, before applying the classification head.
* **out\_indices** (`List[int]`, *optional*, defaults to `[3, 5, 7, 11]`) — Indices of the feature maps to use for semantic segmentation.
* **pool\_scales** (`Tuple[int]`, *optional*, defaults to `[1, 2, 3, 6]`) — Pooling scales used in Pooling Pyramid Module applied on the last feature map.
* **use\_auxiliary\_head** (`bool`, *optional*, defaults to `True`) — Whether to use an auxiliary head during training.
* **auxiliary\_loss\_weight** (`float`, *optional*, defaults to 0.4) — Weight of the cross-entropy loss of the auxiliary head.
* **auxiliary\_channels** (`int`, *optional*, defaults to 256) — Number of channels to use in the auxiliary head.
* **auxiliary\_num\_convs** (`int`, *optional*, defaults to 1) — Number of convolutional layers to use in the auxiliary head.
* **auxiliary\_concat\_input** (`bool`, *optional*, defaults to `False`) — Whether to concatenate the output of the auxiliary head with the input before the classification layer.
* **semantic\_loss\_ignore\_index** (`int`, *optional*, defaults to 255) — The index that is ignored by the loss function of the semantic segmentation model.

This is the configuration class to store the configuration of a [Data2VecVisionModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionModel). It is used to instantiate an Data2VecVision model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Data2VecVision [facebook/data2vec-vision-base](https://huggingface.co/facebook/data2vec-vision-base) architecture.

Example:

Copied

```
>>> from transformers import Data2VecVisionConfig, Data2VecVisionModel

>>> # Initializing a Data2VecVision data2vec_vision-base-patch16-224-in22k style configuration
>>> configuration = Data2VecVisionConfig()

>>> # Initializing a model (with random weights) from the data2vec_vision-base-patch16-224-in22k style configuration
>>> model = Data2VecVisionModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```

### Data2VecAudioModel

#### class transformers.Data2VecAudioModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_audio.py#L830)

( config: Data2VecAudioConfig )

Parameters

* **config** ([Data2VecAudioConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

The bare Data2VecAudio Model transformer outputting raw hidden-states without any specific head on top. Data2VecAudio was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving etc.).

This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_audio.py#L901)

( input\_values: typing.Optional\[torch.Tensor]attention\_mask: typing.Optional\[torch.Tensor] = Nonemask\_time\_indices: typing.Optional\[torch.FloatTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.Wav2Vec2BaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.modeling_outputs.Wav2Vec2BaseModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_values** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) — Float values of input raw speech waveform. Values can be obtained by loading a *.flac* or *.wav* audio file into an array of type *List\[float]* or a *numpy.ndarray*, *e.g.* via the soundfile library (*pip install soundfile*). To prepare the array into *input\_values*, the [AutoProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoProcessor) should be used for padding and conversion into a tensor of type *torch.FloatTensor*. See [Wav2Vec2Processor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor.__call__) for details.
* **attention\_mask** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing convolution and attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)

  `attention_mask` should only be passed if the corresponding processor has `config.return_attention_mask == True`. For all models whose processor has `config.return_attention_mask == False`, such as [data2vec-audio-base](https://huggingface.co/facebook/data2vec-audio-base-960h), `attention_mask` should **not** be passed to avoid degraded performance when doing batched inference. For such models `input_values` should simply be padded with 0 and passed without `attention_mask`. Be aware that these models also yield slightly different results depending on whether `input_values` is padded or not.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_outputs.Wav2Vec2BaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.modeling_outputs.Wav2Vec2BaseModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.Wav2Vec2BaseModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.modeling_outputs.Wav2Vec2BaseModelOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecAudioConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioConfig)) and inputs.

* **last\_hidden\_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model.
* **extract\_features** (`torch.FloatTensor` of shape `(batch_size, sequence_length, conv_dim[-1])`) — Sequence of extracted feature vectors of the last convolutional layer of the model.
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecAudioModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoProcessor, Data2VecAudioModel
>>> import torch
>>> from datasets import load_dataset

>>> dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
>>> dataset = dataset.sort("id")
>>> sampling_rate = dataset.features["audio"].sampling_rate

>>> processor = AutoProcessor.from_pretrained("facebook/data2vec-audio-base-960h")
>>> model = Data2VecAudioModel.from_pretrained("facebook/data2vec-audio-base-960h")

>>> # audio file is decoded on the fly
>>> inputs = processor(dataset[0]["audio"]["array"], sampling_rate=sampling_rate, return_tensors="pt")
>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 292, 768]
```

### Data2VecAudioForAudioFrameClassification

#### class transformers.Data2VecAudioForAudioFrameClassification

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_audio.py#L1216)

( config )

Parameters

* **config** ([Data2VecAudioConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecAudio Model with a frame classification head on top for tasks like Speaker Diarization.

Data2VecAudio was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving etc.).

This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_audio.py#L1261)

( input\_values: typing.Optional\[torch.Tensor]attention\_mask: typing.Optional\[torch.Tensor] = Nonelabels: typing.Optional\[torch.Tensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.TokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_values** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) — Float values of input raw speech waveform. Values can be obtained by loading a *.flac* or *.wav* audio file into an array of type *List\[float]* or a *numpy.ndarray*, *e.g.* via the soundfile library (*pip install soundfile*). To prepare the array into *input\_values*, the [AutoProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoProcessor) should be used for padding and conversion into a tensor of type *torch.FloatTensor*. See [Wav2Vec2Processor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor.__call__) for details.
* **attention\_mask** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing convolution and attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)

  `attention_mask` should only be passed if the corresponding processor has `config.return_attention_mask == True`. For all models whose processor has `config.return_attention_mask == False`, such as [data2vec-audio-base](https://huggingface.co/facebook/data2vec-audio-base-960h), `attention_mask` should **not** be passed to avoid degraded performance when doing batched inference. For such models `input_values` should simply be padded with 0 and passed without `attention_mask`. Be aware that these models also yield slightly different results depending on whether `input_values` is padded or not.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) — Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy).

Returns

[transformers.modeling\_outputs.TokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.TokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecAudioConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Classification loss.
* **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.num_labels)`) — Classification scores (before SoftMax).
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecAudioForAudioFrameClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioForAudioFrameClassification) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoFeatureExtractor, Data2VecAudioForAudioFrameClassification
>>> from datasets import load_dataset
>>> import torch

>>> dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
>>> dataset = dataset.sort("id")
>>> sampling_rate = dataset.features["audio"].sampling_rate

>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/data2vec-audio-base-960h")
>>> model = Data2VecAudioForAudioFrameClassification.from_pretrained("facebook/data2vec-audio-base-960h")

>>> # audio file is decoded on the fly
>>> inputs = feature_extractor(dataset[0]["audio"]["array"], return_tensors="pt", sampling_rate=sampling_rate)
>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> probabilities = torch.sigmoid(logits[0])
>>> # labels is a one-hot array of shape (num_frames, num_speakers)
>>> labels = (probabilities > 0.5).long()
```

### Data2VecAudioForCTC

#### class transformers.Data2VecAudioForCTC

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_audio.py#L966)

( config )

Parameters

* **config** ([Data2VecAudioConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecAudio Model with a `language modeling` head on top for Connectionist Temporal Classification (CTC). Data2VecAudio was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving etc.).

This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_audio.py#L1007)

( input\_values: typing.Optional\[torch.Tensor]attention\_mask: typing.Optional\[torch.Tensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonelabels: typing.Optional\[torch.Tensor] = None ) → [transformers.modeling\_outputs.CausalLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_values** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) — Float values of input raw speech waveform. Values can be obtained by loading a *.flac* or *.wav* audio file into an array of type *List\[float]* or a *numpy.ndarray*, *e.g.* via the soundfile library (*pip install soundfile*). To prepare the array into *input\_values*, the [AutoProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoProcessor) should be used for padding and conversion into a tensor of type *torch.FloatTensor*. See [Wav2Vec2Processor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor.__call__) for details.
* **attention\_mask** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing convolution and attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)

  `attention_mask` should only be passed if the corresponding processor has `config.return_attention_mask == True`. For all models whose processor has `config.return_attention_mask == False`, such as [data2vec-audio-base](https://huggingface.co/facebook/data2vec-audio-base-960h), `attention_mask` should **not** be passed to avoid degraded performance when doing batched inference. For such models `input_values` should simply be padded with 0 and passed without `attention_mask`. Be aware that these models also yield slightly different results depending on whether `input_values` is padded or not.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size, target_length)`, *optional*) — Labels for connectionist temporal classification. Note that `target_length` has to be smaller or equal to the sequence length of the output logits. Indices are selected in `[-100, 0, ..., config.vocab_size - 1]`. All labels set to `-100` are ignored (masked), the loss is only computed for labels in `[0, ..., config.vocab_size - 1]`.

Returns

[transformers.modeling\_outputs.CausalLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.CausalLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecAudioConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Language modeling loss (for next-token prediction).
* **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecAudioForCTC](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioForCTC) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoProcessor, Data2VecAudioForCTC
>>> from datasets import load_dataset
>>> import torch

>>> dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
>>> dataset = dataset.sort("id")
>>> sampling_rate = dataset.features["audio"].sampling_rate

>>> processor = AutoProcessor.from_pretrained("facebook/data2vec-audio-base-960h")
>>> model = Data2VecAudioForCTC.from_pretrained("facebook/data2vec-audio-base-960h")

>>> # audio file is decoded on the fly
>>> inputs = processor(dataset[0]["audio"]["array"], sampling_rate=sampling_rate, return_tensors="pt")
>>> with torch.no_grad():
...     logits = model(**inputs).logits
>>> predicted_ids = torch.argmax(logits, dim=-1)

>>> # transcribe speech
>>> transcription = processor.batch_decode(predicted_ids)
>>> transcription[0]
'MISTER QUILTER IS THE APOSTLE OF THE MIDDLE CLASSES AND WE ARE GLAD TO WELCOME HIS GOSPEL'

>>> inputs["labels"] = processor(text=dataset[0]["text"], return_tensors="pt").input_ids

>>> # compute loss
>>> loss = model(**inputs).loss
>>> round(loss.item(), 2)
66.95
```

### Data2VecAudioForSequenceClassification

#### class transformers.Data2VecAudioForSequenceClassification

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_audio.py#L1095)

( config )

Parameters

* **config** ([Data2VecAudioConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecAudio Model with a sequence classification head on top (a linear layer over the pooled output) for tasks like SUPERB Keyword Spotting.

Data2VecAudio was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving etc.).

This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_audio.py#L1140)

( input\_values: typing.Optional\[torch.Tensor]attention\_mask: typing.Optional\[torch.Tensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonelabels: typing.Optional\[torch.Tensor] = None ) → [transformers.modeling\_outputs.SequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_values** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) — Float values of input raw speech waveform. Values can be obtained by loading a *.flac* or *.wav* audio file into an array of type *List\[float]* or a *numpy.ndarray*, *e.g.* via the soundfile library (*pip install soundfile*). To prepare the array into *input\_values*, the [AutoProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoProcessor) should be used for padding and conversion into a tensor of type *torch.FloatTensor*. See [Wav2Vec2Processor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor.__call__) for details.
* **attention\_mask** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing convolution and attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)

  `attention_mask` should only be passed if the corresponding processor has `config.return_attention_mask == True`. For all models whose processor has `config.return_attention_mask == False`, such as [data2vec-audio-base](https://huggingface.co/facebook/data2vec-audio-base-960h), `attention_mask` should **not** be passed to avoid degraded performance when doing batched inference. For such models `input_values` should simply be padded with 0 and passed without `attention_mask`. Be aware that these models also yield slightly different results depending on whether `input_values` is padded or not.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) — Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy).

Returns

[transformers.modeling\_outputs.SequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.SequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecAudioConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Classification (or regression if config.num\_labels==1) loss.
* **logits** (`torch.FloatTensor` of shape `(batch_size, config.num_labels)`) — Classification (or regression if config.num\_labels==1) scores (before SoftMax).
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecAudioForSequenceClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioForSequenceClassification) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoFeatureExtractor, Data2VecAudioForSequenceClassification
>>> from datasets import load_dataset
>>> import torch

>>> dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
>>> dataset = dataset.sort("id")
>>> sampling_rate = dataset.features["audio"].sampling_rate

>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/data2vec-audio-base-960h")
>>> model = Data2VecAudioForSequenceClassification.from_pretrained("facebook/data2vec-audio-base-960h")

>>> # audio file is decoded on the fly
>>> inputs = feature_extractor(dataset[0]["audio"]["array"], sampling_rate=sampling_rate, return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_ids = torch.argmax(logits, dim=-1).item()
>>> predicted_label = model.config.id2label[predicted_class_ids]

>>> # compute loss - target_label is e.g. "down"
>>> target_label = model.config.id2label[0]
>>> inputs["labels"] = torch.tensor([model.config.label2id[target_label]])
>>> loss = model(**inputs).loss
```

### Data2VecAudioForXVector

#### class transformers.Data2VecAudioForXVector

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_audio.py#L1380)

( config )

Parameters

* **config** ([Data2VecAudioConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecAudio Model with an XVector feature extraction head on top for tasks like Speaker Verification.

Data2VecAudio was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving etc.).

This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_audio.py#L1442)

( input\_values: typing.Optional\[torch.Tensor]attention\_mask: typing.Optional\[torch.Tensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = Nonelabels: typing.Optional\[torch.Tensor] = None ) → [transformers.modeling\_outputs.XVectorOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.XVectorOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_values** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) — Float values of input raw speech waveform. Values can be obtained by loading a *.flac* or *.wav* audio file into an array of type *List\[float]* or a *numpy.ndarray*, *e.g.* via the soundfile library (*pip install soundfile*). To prepare the array into *input\_values*, the [AutoProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoProcessor) should be used for padding and conversion into a tensor of type *torch.FloatTensor*. See [Wav2Vec2Processor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor.__call__) for details.
* **attention\_mask** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing convolution and attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)

  `attention_mask` should only be passed if the corresponding processor has `config.return_attention_mask == True`. For all models whose processor has `config.return_attention_mask == False`, such as [data2vec-audio-base](https://huggingface.co/facebook/data2vec-audio-base-960h), `attention_mask` should **not** be passed to avoid degraded performance when doing batched inference. For such models `input_values` should simply be padded with 0 and passed without `attention_mask`. Be aware that these models also yield slightly different results depending on whether `input_values` is padded or not.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) — Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy).

Returns

[transformers.modeling\_outputs.XVectorOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.XVectorOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.XVectorOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.XVectorOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecAudioConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Classification loss.
* **logits** (`torch.FloatTensor` of shape `(batch_size, config.xvector_output_dim)`) — Classification hidden states before AMSoftmax.
* **embeddings** (`torch.FloatTensor` of shape `(batch_size, config.xvector_output_dim)`) — Utterance embeddings used for vector similarity-based retrieval.
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecAudioForXVector](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecAudioForXVector) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoFeatureExtractor, Data2VecAudioForXVector
>>> from datasets import load_dataset
>>> import torch

>>> dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
>>> dataset = dataset.sort("id")
>>> sampling_rate = dataset.features["audio"].sampling_rate

>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/data2vec-audio-base-960h")
>>> model = Data2VecAudioForXVector.from_pretrained("facebook/data2vec-audio-base-960h")

>>> # audio file is decoded on the fly
>>> inputs = feature_extractor(
...     [d["array"] for d in dataset[:2]["audio"]], sampling_rate=sampling_rate, return_tensors="pt", padding=True
... )
>>> with torch.no_grad():
...     embeddings = model(**inputs).embeddings

>>> embeddings = torch.nn.functional.normalize(embeddings, dim=-1).cpu()

>>> # the resulting embeddings can be used for cosine similarity-based retrieval
>>> cosine_sim = torch.nn.CosineSimilarity(dim=-1)
>>> similarity = cosine_sim(embeddings[0], embeddings[1])
>>> threshold = 0.7  # the optimal threshold is dataset-dependent
>>> if similarity < threshold:
...     print("Speakers are not the same!")
```

### Data2VecTextModel

#### class transformers.Data2VecTextModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L694)

( configadd\_pooling\_layer = True )

Parameters

* **config** ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

The bare Data2VecText Model for text transformer outputting raw hidden-states without any specific head on top. Data2VecText was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of cross-attention is added between the self-attention layers, following the architecture described in *Attention is all you need*\_ by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin.

To behave as an decoder the model needs to be initialized with the `is_decoder` argument of the configuration set to `True`. To be used in a Seq2Seq model, the model needs to initialized with both `is_decoder` argument and `add_cross_attention` set to `True`; an `encoder_hidden_states` is then expected as an input to the forward pass.

.. \_*Attention is all you need*: <https://arxiv.org/abs/1706.03762>

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L736)

( input\_ids: typing.Optional\[torch.Tensor] = Noneattention\_mask: typing.Optional\[torch.Tensor] = Nonetoken\_type\_ids: typing.Optional\[torch.Tensor] = Noneposition\_ids: typing.Optional\[torch.Tensor] = Nonehead\_mask: typing.Optional\[torch.Tensor] = Noneinputs\_embeds: typing.Optional\[torch.Tensor] = Noneencoder\_hidden\_states: typing.Optional\[torch.Tensor] = Noneencoder\_attention\_mask: typing.Optional\[torch.Tensor] = Nonepast\_key\_values: typing.Optional\[typing.List\[torch.FloatTensor]] = Noneuse\_cache: typing.Optional\[bool] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.BaseModelOutputWithPoolingAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **token\_type\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  * 0 corresponds to a *sentence A* token,
  * 1 corresponds to a *sentence B* token.

  [What are token type IDs?](https://huggingface.co/docs/transformers/glossary#token-type-ids)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids)
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **inputs\_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model’s internal embedding lookup matrix.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **encoder\_hidden\_states** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.
* **encoder\_attention\_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:
  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.
* **past\_key\_values** (`tuple(tuple(torch.FloatTensor))` of length `config.n_layers` with each tuple having 4 tensors of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`) — Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.

  If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
* **use\_cache** (`bool`, *optional*) — If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).

Returns

[transformers.modeling\_outputs.BaseModelOutputWithPoolingAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.BaseModelOutputWithPoolingAndCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) and inputs.

* **last\_hidden\_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model.
* **pooler\_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) — Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining.
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
* **cross\_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
* **past\_key\_values** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and optionally if `config.is_encoder_decoder=True` 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if `config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.

The [Data2VecTextModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, Data2VecTextModel
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/data2vec-text-base")
>>> model = Data2VecTextModel.from_pretrained("facebook/data2vec-text-base")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
```

### Data2VecTextForCausalLM

#### class transformers.Data2VecTextForCausalLM

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L877)

( config )

Parameters

* **config** ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecText Model with a `language modeling` head on top for CLM fine-tuning. Data2VecText was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L898)

( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Nonetoken\_type\_ids: typing.Optional\[torch.LongTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Noneencoder\_hidden\_states: typing.Optional\[torch.FloatTensor] = Noneencoder\_attention\_mask: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Nonepast\_key\_values: typing.Optional\[typing.Tuple\[typing.Tuple\[torch.FloatTensor]]] = Noneuse\_cache: typing.Optional\[bool] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.CausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **token\_type\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  * 0 corresponds to a *sentence A* token,
  * 1 corresponds to a *sentence B* token.

  [What are token type IDs?](https://huggingface.co/docs/transformers/glossary#token-type-ids)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids)
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **inputs\_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model’s internal embedding lookup matrix.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **encoder\_hidden\_states** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.
* **encoder\_attention\_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:
  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.
* **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
* **past\_key\_values** (`tuple(tuple(torch.FloatTensor))` of length `config.n_layers` with each tuple having 4 tensors of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`) — Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.

  If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
* **use\_cache** (`bool`, *optional*) — If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).

Returns

[transformers.modeling\_outputs.CausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.CausalLMOutputWithCrossAttentions](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Language modeling loss (for next-token prediction).
* **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
* **cross\_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Cross attentions weights after the attention softmax, used to compute the weighted average in the cross-attention heads.
* **past\_key\_values** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `torch.FloatTensor` tuples of length `config.n_layers`, with each tuple containing the cached key, value states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting. Only relevant if `config.is_decoder = True`.

  Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.

The [Data2VecTextForCausalLM](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextForCausalLM) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, Data2VecTextForCausalLM, Data2VecTextConfig
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/data2vec-text-base")
>>> config = Data2VecTextConfig.from_pretrained("facebook/data2vec-text-base")
>>> config.is_decoder = True
>>> model = Data2VecTextForCausalLM.from_pretrained("facebook/data2vec-text-base", config=config)

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)

>>> prediction_logits = outputs.logits
```

### Data2VecTextForMaskedLM

#### class transformers.Data2VecTextForMaskedLM

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L1028)

( config )

Parameters

* **config** ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

data2vec Model with a `language modeling` head on top. Data2VecText was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L1052)

( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Nonetoken\_type\_ids: typing.Optional\[torch.LongTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Noneencoder\_hidden\_states: typing.Optional\[torch.FloatTensor] = Noneencoder\_attention\_mask: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.MaskedLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **token\_type\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  * 0 corresponds to a *sentence A* token,
  * 1 corresponds to a *sentence B* token.

  [What are token type IDs?](https://huggingface.co/docs/transformers/glossary#token-type-ids)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids)
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **inputs\_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model’s internal embedding lookup matrix.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
* **kwargs** (`Dict[str, any]`, optional, defaults to *{}*) — Used to hide legacy arguments that have been deprecated.

Returns

[transformers.modeling\_outputs.MaskedLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.MaskedLMOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Masked language modeling (MLM) loss.
* **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecTextForMaskedLM](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextForMaskedLM) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, Data2VecTextForMaskedLM
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/data2vec-text-base")
>>> model = Data2VecTextForMaskedLM.from_pretrained("facebook/data2vec-text-base")

>>> inputs = tokenizer("The capital of France is <mask>.", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> # retrieve index of <mask>
>>> mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0]

>>> predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)

>>> labels = tokenizer("The capital of France is Paris.", return_tensors="pt")["input_ids"]
>>> # mask labels of non-<mask> tokens
>>> labels = torch.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100)

>>> outputs = model(**inputs, labels=labels)
```

### Data2VecTextForSequenceClassification

#### class transformers.Data2VecTextForSequenceClassification

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L1158)

( config )

Parameters

* **config** ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecText Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.

Data2VecText was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L1170)

( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Nonetoken\_type\_ids: typing.Optional\[torch.LongTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.SequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **token\_type\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  * 0 corresponds to a *sentence A* token,
  * 1 corresponds to a *sentence B* token.

  [What are token type IDs?](https://huggingface.co/docs/transformers/glossary#token-type-ids)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids)
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **inputs\_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model’s internal embedding lookup matrix.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) — Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy).

Returns

[transformers.modeling\_outputs.SequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.SequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Classification (or regression if config.num\_labels==1) loss.
* **logits** (`torch.FloatTensor` of shape `(batch_size, config.num_labels)`) — Classification (or regression if config.num\_labels==1) scores (before SoftMax).
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecTextForSequenceClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextForSequenceClassification) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example of single-label classification:

Copied

```
>>> import torch
>>> from transformers import AutoTokenizer, Data2VecTextForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/data2vec-text-base")
>>> model = Data2VecTextForSequenceClassification.from_pretrained("facebook/data2vec-text-base")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_id = logits.argmax().item()

>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = Data2VecTextForSequenceClassification.from_pretrained("facebook/data2vec-text-base", num_labels=num_labels)

>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).loss
```

Example of multi-label classification:

Copied

```
>>> import torch
>>> from transformers import AutoTokenizer, Data2VecTextForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/data2vec-text-base")
>>> model = Data2VecTextForSequenceClassification.from_pretrained("facebook/data2vec-text-base", problem_type="multi_label_classification")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]

>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = Data2VecTextForSequenceClassification.from_pretrained(
...     "facebook/data2vec-text-base", num_labels=num_labels, problem_type="multi_label_classification"
... )

>>> labels = torch.sum(
...     torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
... ).to(torch.float)
>>> loss = model(**inputs, labels=labels).loss
```

### Data2VecTextForMultipleChoice

#### class transformers.Data2VecTextForMultipleChoice

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L1255)

( config )

Parameters

* **config** ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecText Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks.

Data2VecText was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L1266)

( input\_ids: typing.Optional\[torch.LongTensor] = Nonetoken\_type\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.MultipleChoiceModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`torch.FloatTensor` of shape `(batch_size, num_choices, sequence_length)`, *optional*) — Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **token\_type\_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`, *optional*) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  * 0 corresponds to a *sentence A* token,
  * 1 corresponds to a *sentence B* token.

  [What are token type IDs?](https://huggingface.co/docs/transformers/glossary#token-type-ids)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids)
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **inputs\_embeds** (`torch.FloatTensor` of shape `(batch_size, num_choices, sequence_length, hidden_size)`, *optional*) — Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model’s internal embedding lookup matrix.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) — Labels for computing the multiple choice classification loss. Indices should be in `[0, ..., num_choices-1]` where `num_choices` is the size of the second dimension of the input tensors. (See `input_ids` above)

Returns

[transformers.modeling\_outputs.MultipleChoiceModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.MultipleChoiceModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape *(1,)*, *optional*, returned when `labels` is provided) — Classification loss.
* **logits** (`torch.FloatTensor` of shape `(batch_size, num_choices)`) — *num\_choices* is the second dimension of the input tensors. (see *input\_ids* above).

  Classification scores (before SoftMax).
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecTextForMultipleChoice](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextForMultipleChoice) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, Data2VecTextForMultipleChoice
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/data2vec-text-base")
>>> model = Data2VecTextForMultipleChoice.from_pretrained("facebook/data2vec-text-base")

>>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced."
>>> choice0 = "It is eaten with a fork and a knife."
>>> choice1 = "It is eaten while held in the hand."
>>> labels = torch.tensor(0).unsqueeze(0)  # choice0 is correct (according to Wikipedia ;)), batch size 1

>>> encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors="pt", padding=True)
>>> outputs = model(**{k: v.unsqueeze(0) for k, v in encoding.items()}, labels=labels)  # batch size is 1

>>> # the linear classifier still needs to be trained
>>> loss = outputs.loss
>>> logits = outputs.logits
```

### Data2VecTextForTokenClassification

#### class transformers.Data2VecTextForTokenClassification

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L1349)

( config )

Parameters

* **config** ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecText Model with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks.

Data2VecText was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L1364)

( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Nonetoken\_type\_ids: typing.Optional\[torch.LongTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.TokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **token\_type\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  * 0 corresponds to a *sentence A* token,
  * 1 corresponds to a *sentence B* token.

  [What are token type IDs?](https://huggingface.co/docs/transformers/glossary#token-type-ids)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids)
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **inputs\_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model’s internal embedding lookup matrix.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.

Returns

[transformers.modeling\_outputs.TokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.TokenClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Classification loss.
* **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.num_labels)`) — Classification scores (before SoftMax).
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecTextForTokenClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextForTokenClassification) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, Data2VecTextForTokenClassification
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/data2vec-text-base")
>>> model = Data2VecTextForTokenClassification.from_pretrained("facebook/data2vec-text-base")

>>> inputs = tokenizer(
...     "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt"
... )

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_token_class_ids = logits.argmax(-1)

>>> # Note that tokens are classified rather then input words which means that
>>> # there might be more predicted token classes than words.
>>> # Multiple token classes might account for the same word
>>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]

>>> labels = predicted_token_class_ids
>>> loss = model(**inputs, labels=labels).loss
```

### Data2VecTextForQuestionAnswering

#### class transformers.Data2VecTextForQuestionAnswering

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L1455)

( config )

Parameters

* **config** ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecText Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers on top of the hidden-states output to compute `span start logits` and `span end logits`).

Data2VecText was proposed in [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://arxiv.org/pdf/2202.03555) by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli.

This model inherits from [PreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_text.py#L1466)

( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Nonetoken\_type\_ids: typing.Optional\[torch.LongTensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonestart\_positions: typing.Optional\[torch.LongTensor] = Noneend\_positions: typing.Optional\[torch.LongTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.QuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/glossary#input-ids)
* **attention\_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) — Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  * 1 for tokens that are **not masked**,
  * 0 for tokens that are **masked**.

  [What are attention masks?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **token\_type\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  * 0 corresponds to a *sentence A* token,
  * 1 corresponds to a *sentence B* token.

  [What are token type IDs?](https://huggingface.co/docs/transformers/glossary#token-type-ids)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#position-ids)
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **inputs\_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) — Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model’s internal embedding lookup matrix.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **start\_positions** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) — Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence are not taken into account for computing the loss.
* **end\_positions** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) — Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence are not taken into account for computing the loss.

Returns

[transformers.modeling\_outputs.QuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.QuestionAnsweringModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.
* **start\_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) — Span-start scores (before SoftMax).
* **end\_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) — Span-end scores (before SoftMax).
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecTextForQuestionAnswering](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecTextForQuestionAnswering) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoTokenizer, Data2VecTextForQuestionAnswering
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/data2vec-text-base")
>>> model = Data2VecTextForQuestionAnswering.from_pretrained("facebook/data2vec-text-base")

>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"

>>> inputs = tokenizer(question, text, return_tensors="pt")
>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> answer_start_index = outputs.start_logits.argmax()
>>> answer_end_index = outputs.end_logits.argmax()

>>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]

>>> # target is "nice puppet"
>>> target_start_index = torch.tensor([14])
>>> target_end_index = torch.tensor([15])

>>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index)
>>> loss = outputs.loss
```

### Data2VecVisionModel

#### class transformers.Data2VecVisionModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_vision.py#L632)

( config: Data2VecVisionConfigadd\_pooling\_layer: bool = False )

Parameters

* **config** ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

The bare Data2VecVision Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_vision.py#L659)

( pixel\_values: typing.Optional\[torch.Tensor] = Nonebool\_masked\_pos: typing.Optional\[torch.BoolTensor] = Nonehead\_mask: typing.Optional\[torch.Tensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → `transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionModelOutputWithPooling` or `tuple(torch.FloatTensor)`

Parameters

* **pixel\_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`) — Pixel values. Pixel values can be obtained using [AutoImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoImageProcessor). See [BeitImageProcessor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/beit#transformers.BeitFeatureExtractor.__call__) for details.
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **bool\_masked\_pos** (`torch.BoolTensor` of shape `(batch_size, num_patches)`, *optional*) — Boolean masked positions. Indicates which patches are masked (1) and which aren’t (0).

Returns

`transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionModelOutputWithPooling` or `tuple(torch.FloatTensor)`

A `transformers.models.data2vec.modeling_data2vec_vision.Data2VecVisionModelOutputWithPooling` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) and inputs.

* **last\_hidden\_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model.
* **pooler\_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) — Average of the last layer hidden states of the patch tokens (excluding the *\[CLS]* token) if *config.use\_mean\_pooling* is set to True. If set to False, then the final hidden state of the *\[CLS]* token will be returned.
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecVisionModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoImageProcessor, Data2VecVisionModel
>>> import torch
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/data2vec-vision-base")
>>> model = Data2VecVisionModel.from_pretrained("facebook/data2vec-vision-base")

>>> inputs = image_processor(image, return_tensors="pt")

>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 197, 768]
```

### Data2VecVisionForImageClassification

#### class transformers.Data2VecVisionForImageClassification

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_vision.py#L749)

( config: Data2VecVisionConfig )

Parameters

* **config** ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecVision Model transformer with an image classification head on top (a linear layer on top of the average of the final hidden states of the patch tokens) e.g. for ImageNet.

This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_vision.py#L762)

( pixel\_values: typing.Optional\[torch.Tensor] = Nonehead\_mask: typing.Optional\[torch.Tensor] = Nonelabels: typing.Optional\[torch.Tensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.ImageClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutput) or `tuple(torch.FloatTensor)`

Parameters

* **pixel\_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`) — Pixel values. Pixel values can be obtained using [AutoImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoImageProcessor). See [BeitImageProcessor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/beit#transformers.BeitFeatureExtractor.__call__) for details.
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) — Labels for computing the image classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy).

Returns

[transformers.modeling\_outputs.ImageClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.ImageClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Classification (or regression if config.num\_labels==1) loss.
* **logits** (`torch.FloatTensor` of shape `(batch_size, config.num_labels)`) — Classification (or regression if config.num\_labels==1) scores (before SoftMax).
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each stage) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states (also called feature maps) of the model at the output of each stage.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, patch_size, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecVisionForImageClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionForImageClassification) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoImageProcessor, Data2VecVisionForImageClassification
>>> import torch
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/data2vec-vision-base-ft1k")
>>> model = Data2VecVisionForImageClassification.from_pretrained("facebook/data2vec-vision-base-ft1k")

>>> inputs = image_processor(image, return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_label = logits.argmax(-1).item()
>>> print(model.config.id2label[predicted_label])
remote control, remote
```

### Data2VecVisionForSemanticSegmentation

#### class transformers.Data2VecVisionForSemanticSegmentation

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_vision.py#L1084)

( config: Data2VecVisionConfig )

Parameters

* **config** ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

Data2VecVision Model transformer with a semantic segmentation head on top e.g. for ADE20k, CityScapes.

This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_data2vec_vision.py#L1130)

( pixel\_values: typing.Optional\[torch.Tensor] = Nonehead\_mask: typing.Optional\[torch.Tensor] = Nonelabels: typing.Optional\[torch.Tensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.SemanticSegmenterOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SemanticSegmenterOutput) or `tuple(torch.FloatTensor)`

Parameters

* **pixel\_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`) — Pixel values. Pixel values can be obtained using [AutoImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoImageProcessor). See [BeitImageProcessor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/beit#transformers.BeitFeatureExtractor.__call__) for details.
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size, height, width)`, *optional*) — Ground truth semantic segmentation maps for computing the loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels > 1`, a classification loss is computed (Cross-Entropy).

Returns

[transformers.modeling\_outputs.SemanticSegmenterOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SemanticSegmenterOutput) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.SemanticSegmenterOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.SemanticSegmenterOutput) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Classification (or regression if config.num\_labels==1) loss.
* **logits** (`torch.FloatTensor` of shape `(batch_size, config.num_labels, logits_height, logits_width)`) — Classification scores for each pixel.

  The logits returned do not necessarily have the same size as the `pixel_values` passed as inputs. This is to avoid doing two interpolations and lose some quality when a user needs to resize the logits to the original image size as post-processing. You should always check your logits shape and resize as needed.
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, patch_size, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, patch_size, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [Data2VecVisionForSemanticSegmentation](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionForSemanticSegmentation) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Examples:

Copied

```
>>> from transformers import AutoImageProcessor, Data2VecVisionForSemanticSegmentation
>>> from PIL import Image
>>> import requests

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/data2vec-vision-base")
>>> model = Data2VecVisionForSemanticSegmentation.from_pretrained("facebook/data2vec-vision-base")

>>> inputs = image_processor(images=image, return_tensors="pt")
>>> outputs = model(**inputs)
>>> # logits are of shape (batch_size, num_labels, height, width)
>>> logits = outputs.logits
```

### TFData2VecVisionModel

#### class transformers.TFData2VecVisionModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_tf_data2vec_vision.py#L852)

( \*args\*\*kwargs )

Parameters

* **config** ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel.from_pretrained) method to load the model weights.

The bare Data2VecVision Model transformer outputting raw hidden-states without any specific head on top. This model inherits from [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.).

This model is also a [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in `transformers` accept two formats as input:

* having all inputs as keyword arguments (like PyTorch models), or
* having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

* a single Tensor with `pixel_values` only and nothing else: `model(pixel_values)`
* a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([pixel_values, attention_mask])` or `model([pixel_values, attention_mask, token_type_ids])`
* a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"pixel_values": pixel_values, "token_type_ids": token_type_ids})`

Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

**call**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_tf_data2vec_vision.py#L864)

( pixel\_values: TFModelInputType | None = Nonebool\_masked\_pos: tf.Tensor | None = Nonehead\_mask: np.ndarray | tf.Tensor | None = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonetraining: bool = False ) → `transformers.models.data2vec.modeling_tf_data2vec_vision.TFData2VecVisionModelOutputWithPooling` or `tuple(tf.Tensor)`

Parameters

* **pixel\_values** (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` `Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `(batch_size, num_channels, height, width)`) — Pixel values. Pixel values can be obtained using [AutoImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoImageProcessor). See [BeitImageProcessor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/beit#transformers.BeitFeatureExtractor.__call__) for details.
* **head\_mask** (`np.ndarray` or `tf.Tensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
* **training** (`bool`, *optional*, defaults to \`False“) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
* **bool\_masked\_pos** (`tf.Tensor` of shape `(batch_size, num_patches)`, *optional*) — Boolean masked positions. Indicates which patches are masked (1) and which aren’t (0).

Returns

`transformers.models.data2vec.modeling_tf_data2vec_vision.TFData2VecVisionModelOutputWithPooling` or `tuple(tf.Tensor)`

A `transformers.models.data2vec.modeling_tf_data2vec_vision.TFData2VecVisionModelOutputWithPooling` or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) and inputs.

* **last\_hidden\_state** (`tf.Tensor` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model.
* **pooler\_output** (`tf.Tensor` of shape `(batch_size, hidden_size)`) — Average of the last layer hidden states of the patch tokens (excluding the *\[CLS]* token) if *config.use\_mean\_pooling* is set to True. If set to False, then the final hidden state of the *\[CLS]* token will be returned.
* **hidden\_states** (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [TFData2VecVisionModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.TFData2VecVisionModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoImageProcessor, TFData2VecVisionModel
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/data2vec-vision-base")
>>> model = TFData2VecVisionModel.from_pretrained("facebook/data2vec-vision-base")

>>> inputs = image_processor(image, return_tensors="tf")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 197, 768]
```

### TFData2VecVisionForImageClassification

#### class transformers.TFData2VecVisionForImageClassification

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_tf_data2vec_vision.py#L907)

( \*args\*\*kwargs )

Parameters

* **config** ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel.from_pretrained) method to load the model weights.

Data2VecVision Model transformer with an image classification head on top (a linear layer on top of the average of the final hidden states of the patch tokens) e.g. for ImageNet.

This model inherits from [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.).

This model is also a [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in `transformers` accept two formats as input:

* having all inputs as keyword arguments (like PyTorch models), or
* having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

* a single Tensor with `pixel_values` only and nothing else: `model(pixel_values)`
* a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([pixel_values, attention_mask])` or `model([pixel_values, attention_mask, token_type_ids])`
* a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"pixel_values": pixel_values, "token_type_ids": token_type_ids})`

Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

**call**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_tf_data2vec_vision.py#L921)

( pixel\_values: TFModelInputType | None = Nonehead\_mask: np.ndarray | tf.Tensor | None = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = Nonelabels: np.ndarray | tf.Tensor | None = Nonetraining: Optional\[bool] = False ) → [transformers.modeling\_tf\_outputs.TFSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSequenceClassifierOutput) or `tuple(tf.Tensor)`

Parameters

* **pixel\_values** (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` `Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `(batch_size, num_channels, height, width)`) — Pixel values. Pixel values can be obtained using [AutoImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoImageProcessor). See [BeitImageProcessor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/beit#transformers.BeitFeatureExtractor.__call__) for details.
* **head\_mask** (`np.ndarray` or `tf.Tensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
* **training** (`bool`, *optional*, defaults to \`False“) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
* **labels** (`tf.Tensor` or `np.ndarray` of shape `(batch_size,)`, *optional*) — Labels for computing the image classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy).

Returns

[transformers.modeling\_tf\_outputs.TFSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSequenceClassifierOutput) or `tuple(tf.Tensor)`

A [transformers.modeling\_tf\_outputs.TFSequenceClassifierOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_tf_outputs.TFSequenceClassifierOutput) or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) and inputs.

* **loss** (`tf.Tensor` of shape `(batch_size, )`, *optional*, returned when `labels` is provided) — Classification (or regression if config.num\_labels==1) loss.
* **logits** (`tf.Tensor` of shape `(batch_size, config.num_labels)`) — Classification (or regression if config.num\_labels==1) scores (before SoftMax).
* **hidden\_states** (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the initial embedding outputs.
* **attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [TFData2VecVisionForImageClassification](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.TFData2VecVisionForImageClassification) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

Copied

```
>>> from transformers import AutoImageProcessor, TFData2VecVisionForImageClassification
>>> import tensorflow as tf
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/data2vec-vision-base-ft1k")
>>> model = TFData2VecVisionForImageClassification.from_pretrained("facebook/data2vec-vision-base-ft1k")

>>> inputs = image_processor(image, return_tensors="tf")
>>> logits = model(**inputs).logits

>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_label = int(tf.math.argmax(logits, axis=-1))
>>> print(model.config.id2label[predicted_label])
remote control, remote
```

### TFData2VecVisionForSemanticSegmentation

#### class transformers.TFData2VecVisionForSemanticSegmentation

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_tf_data2vec_vision.py#L1279)

( \*args\*\*kwargs )

Parameters

* **config** ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel.from_pretrained) method to load the model weights.

Data2VecVision Model transformer with a semantic segmentation head on top e.g. for ADE20k, CityScapes.

This model inherits from [TFPreTrainedModel](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.TFPreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.).

This model is also a [tf.keras.Model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

TensorFlow models and layers in `transformers` accept two formats as input:

* having all inputs as keyword arguments (like PyTorch models), or
* having all inputs as a list, tuple or dict in the first positional argument.

The reason the second format is supported is that Keras methods prefer this format when passing inputs to models and layers. Because of this support, when using methods like `model.fit()` things should “just work” for you - just pass your inputs and labels in any format that `model.fit()` supports! If, however, you want to use the second format outside of Keras methods like `fit()` and `predict()`, such as when creating your own layers or models with the Keras `Functional` API, there are three possibilities you can use to gather all the input Tensors in the first positional argument:

* a single Tensor with `pixel_values` only and nothing else: `model(pixel_values)`
* a list of varying length with one or several input Tensors IN THE ORDER given in the docstring: `model([pixel_values, attention_mask])` or `model([pixel_values, attention_mask, token_type_ids])`
* a dictionary with one or several input Tensors associated to the input names given in the docstring: `model({"pixel_values": pixel_values, "token_type_ids": token_type_ids})`

Note that when creating models and layers with [subclassing](https://keras.io/guides/making_new_layers_and_models_via_subclassing/) then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!

**call**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/data2vec/modeling_tf_data2vec_vision.py#L1332)

( pixel\_values: tf.Tensor | None = Nonehead\_mask: tf.Tensor | None = Nonelabels: tf.Tensor | None = Noneoutput\_attentions: Optional\[bool] = Noneoutput\_hidden\_states: Optional\[bool] = Nonereturn\_dict: Optional\[bool] = None ) → `transformers.modeling_tf_outputs.TFSemanticSegmenterOutput` or `tuple(tf.Tensor)`

Parameters

* **pixel\_values** (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` `Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `(batch_size, num_channels, height, width)`) — Pixel values. Pixel values can be obtained using [AutoImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoImageProcessor). See [BeitImageProcessor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/beit#transformers.BeitFeatureExtractor.__call__) for details.
* **head\_mask** (`np.ndarray` or `tf.Tensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **output\_attentions** (`bool`, *optional*) — Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail.
* **output\_hidden\_states** (`bool`, *optional*) — Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail.
* **return\_dict** (`bool`, *optional*) — Whether or not to return a [ModelOutput](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
* **training** (`bool`, *optional*, defaults to \`False“) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
* **labels** (`tf.Tensor` of shape `(batch_size, height, width)`, *optional*) — Ground truth semantic segmentation maps for computing the loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels > 1`, a classification loss is computed (Cross-Entropy).

Returns

`transformers.modeling_tf_outputs.TFSemanticSegmenterOutput` or `tuple(tf.Tensor)`

A `transformers.modeling_tf_outputs.TFSemanticSegmenterOutput` or a tuple of `tf.Tensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Data2VecVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.Data2VecVisionConfig)) and inputs.

* **loss** (`tf.Tensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Classification (or regression if config.num\_labels==1) loss.
* **logits** (`tf.Tensor` of shape `(batch_size, config.num_labels, logits_height, logits_width)`) — Classification scores for each pixel.

  The logits returned do not necessarily have the same size as the `pixel_values` passed as inputs. This is to avoid doing two interpolations and lose some quality when a user needs to resize the logits to the original image size as post-processing. You should always check your logits shape and resize as needed.
* **hidden\_states** (`tuple(tf.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `tf.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, patch_size, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(tf.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `tf.Tensor` (one for each layer) of shape `(batch_size, num_heads, patch_size, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [TFData2VecVisionForSemanticSegmentation](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/data2vec#transformers.TFData2VecVisionForSemanticSegmentation) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Examples:

Copied

```
>>> from transformers import AutoImageProcessor, TFData2VecVisionForSemanticSegmentation
>>> from PIL import Image
>>> import requests

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/data2vec-vision-base")
>>> model = TFData2VecVisionForSemanticSegmentation.from_pretrained("facebook/data2vec-vision-base")

>>> inputs = image_processor(images=image, return_tensors="pt")
>>> outputs = model(**inputs)
>>> # logits are of shape (batch_size, num_labels, height, width)
>>> logits = outputs.logits
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://boinc-ai.gitbook.io/transformers/api/models/multimodal-models/data2vec.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.