transformers/docs/source/en/model_doc/data2vec.md

This model was published in HF papers on 2022-02-07 and contributed to Hugging Face Transformers on 2022-03-01.

Data2Vec

Overview

The Data2Vec model was proposed in data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language 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.

This model was contributed by edugp and patrickvonplaten.

The original code (for NLP and Speech) can be found here. The original code for vision can be found here.

Usage tips

• Data2VecAudio, Data2VecText, and Data2VecVision have all been trained using the same self-supervised learning method.
• For Data2VecAudio, preprocessing is identical to [Wav2Vec2Model], including feature extraction
• For Data2VecText, preprocessing is identical to [RobertaModel], including tokenization.
• For Data2VecVision, preprocessing is identical to [BeitModel], including feature extraction.

Using Scaled Dot Product Attention (SDPA)

PyTorch includes a native scaled dot-product attention (SDPA) operator as part of torch.nn.functional. This function encompasses several implementations that can be applied depending on the inputs and the hardware in use. See the official documentation or the GPU Inference page for more information.

SDPA is used by default for torch>=2.1.1 when an implementation is available, but you may also set attn_implementation="sdpa" in from_pretrained() to explicitly request SDPA to be used.

The SDPA implementation is currently available for the Data2VecAudio and Data2VecVision models.

from transformers import Data2VecVisionForImageClassification


model = Data2VecVisionForImageClassification.from_pretrained("facebook/data2vec-vision-base", attn_implementation="sdpa", device_map="auto")
...

For the best speedups, we recommend loading the model in half-precision (e.g. torch.float16 or torch.bfloat16).

For the Data2VecVision model, on a local benchmark (NVIDIA GeForce RTX 2060-8GB, PyTorch 2.5.1, OS Ubuntu 20.04) with float16 and facebook/data2vec-vision-base model, we saw the following improvements during training and inference:

Training

num_training_steps	batch_size	image_size	is_cuda	Time per batch (eager - s)	Time per batch (sdpa - s)	Speedup (%)	Eager peak mem (MB)	SDPA peak mem (MB)	Mem saving (%)
50	2	(1048, 640)	True	0.996	0.754	32.147	6722.198	4264.653	57.626

Inference

Image batch size	Eager (s/iter)	Eager CI, %	Eager memory (MB)	SDPA (s/iter)	SDPA CI, %	SDPA memory (MB)	SDPA speedup	SDPA memory saved
1	0.011	±0.3%	3.76143e+08	0.01	±0.3%	3.74397e+08	1.101	0.466
4	0.014	±0.1%	4.02756e+08	0.012	±0.2%	3.91373e+08	1.219	2.909
16	0.046	±0.3%	4.96482e+08	0.035	±0.2%	4.51017e+08	1.314	10.081
32	0.088	±0.1%	6.23903e+08	0.067	±0.1%	5.32974e+08	1.33	17.061

Resources

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

• [Data2VecVisionForImageClassification] is supported by this example script and notebook.

Data2VecText documentation resources

• Text classification task guide
• Token classification task guide
• Question answering task guide
• Causal language modeling task guide
• Masked language modeling task guide
• Multiple choice task guide

Data2VecAudio documentation resources

• Audio classification task guide
• Automatic speech recognition task guide

Data2VecVision documentation resources

• Image classification
• 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

autodoc Data2VecTextConfig

Data2VecAudioConfig

autodoc Data2VecAudioConfig

Data2VecVisionConfig

autodoc Data2VecVisionConfig

Data2VecAudioModel

autodoc Data2VecAudioModel - forward

Data2VecAudioForAudioFrameClassification

autodoc Data2VecAudioForAudioFrameClassification - forward

Data2VecAudioForCTC

autodoc Data2VecAudioForCTC - forward

Data2VecAudioForSequenceClassification

autodoc Data2VecAudioForSequenceClassification - forward

Data2VecAudioForXVector

autodoc Data2VecAudioForXVector - forward

Data2VecTextModel

autodoc Data2VecTextModel - forward

Data2VecTextForCausalLM

autodoc Data2VecTextForCausalLM - forward

Data2VecTextForMaskedLM

autodoc Data2VecTextForMaskedLM - forward

Data2VecTextForSequenceClassification

autodoc Data2VecTextForSequenceClassification - forward

Data2VecTextForMultipleChoice

autodoc Data2VecTextForMultipleChoice - forward

Data2VecTextForTokenClassification

autodoc Data2VecTextForTokenClassification - forward

Data2VecTextForQuestionAnswering

autodoc Data2VecTextForQuestionAnswering - forward

Data2VecVisionModel

autodoc Data2VecVisionModel - forward

Data2VecVisionForImageClassification

autodoc Data2VecVisionForImageClassification - forward

Data2VecVisionForSemanticSegmentation

autodoc Data2VecVisionForSemanticSegmentation - forward