data2vec/README.md

Text Embedding with data2vec

author: David Wang

Description

This operator extracts features for text with data2vec. The core idea is to predict latent representations of the full input data based on a masked view of the input in a self-distillation setup using a standard Transformer architecture.

Code Example

Use the pre-trained model to generate a text embedding for the sentence "Hello, world.".

*Write a pipeline with explicit inputs/outputs name specifications:

from towhee.dc2 import pipe, ops, DataCollection

p = (
    pipe.input('text')
        .map('text', 'vec', ops.text_embedding.data2vec(model_name='facebook/data2vec-text-base'))
        .output('text', 'vec')
)

DataCollection(p('Hello, world.')).show()

Factory Constructor

Create the operator via the following factory method

data2vec(model_name='facebook/data2vec-text-base')

Parameters:

​ model_name: str

The model name in string. The default value is "facebook/data2vec-text-base".

Supported model name:

• facebook/data2vec-text-base

Interface

Parameters:

​ text: str

​ The text in string.

Returns: numpy.ndarray

​ The text embedding extracted by model.