inference-providers/pr_2713/en/tasks/text-classification.md

Text Classification

Text Classification is the task of assigning a label or class to a given text. Some use cases are sentiment analysis, natural language inference, and assessing grammatical correctness.

For more details about the text-classification task, check out its dedicated page! You will find examples and related materials.

Recommended models

• distilbert/distilbert-base-uncased-finetuned-sst-2-english: A robust model trained for sentiment analysis.
• ProsusAI/finbert: A sentiment analysis model specialized in financial sentiment.
• cardiffnlp/twitter-roberta-base-sentiment-latest: A sentiment analysis model specialized in analyzing tweets.
• papluca/xlm-roberta-base-language-detection: A model that can classify languages.
• meta-llama/Prompt-Guard-86M: A model that can classify text generation attacks.

Explore all available models and find the one that suits you best here, or from the terminal with the hf CLI:

hf models ls --warm --pipeline-tag text-classification --sort trending_score

Using the API

<InferenceSnippet pipeline=text-classification providersMapping={ {"hf-inference":{"modelId":"BAAI/bge-reranker-v2-m3","providerModelId":"BAAI/bge-reranker-v2-m3"}} } />

API specification

Request

Headers
authorization	string	Authentication header in the form 'Bearer: hf_****' when hf_**** is a personal user access token with "Inference Providers" permission. You can generate one from your settings page.

Payload
inputs*	string	The text to classify
parameters	object
function_to_apply	enum	Possible values: sigmoid, softmax, none.
top_k	integer	When specified, limits the output to the top K most probable classes.

Response

| Body | | | :--- | :--- | :--- | | (array) | object[] | Output is an array of objects. | |         label | string | The predicted class label. | |         score | number | The corresponding probability. |