# Text understanding

This is a transformers model for zero-shot classification tasks, which can classify text without a large amount of labeled data.

This is the ONNX format conversion of the MoritzLaurer/roberta-base-zeroshot-v2.0-c model, suitable for zero-shot classification tasks.

NorBERT 3 xs is a BERT model optimized for Norwegian, the smallest version in the new generation NorBERT language model series with 15M parameters.

A medium-scale BERT language model pretrained with the unique objective of predicting the sum of ASCII code values for masked tokens.

An Amharic language model trained based on the Roberta architecture, suitable for various natural language processing tasks.

A model fine-tuned based on microsoft/deberta-v3-base, achieving an accuracy of 75.76% on the evaluation set

DistilKoBERT is a lightweight version of the Korean BERT model, compressed through knowledge distillation technology, retaining most of the performance while reducing computational resource requirements.

RobBERTje is a shuffled version of the distilled Dutch model collection based on RobBERT, with 74M parameters, trained using shuffled OSCAR corpus

RobBERTje is a series of distilled Dutch BERT models based on RobBERT, offering various model sizes and training configurations.

An improved version based on XLM-RoBERTa, with the embedding layer and vocabulary streamlined to retain only the most common high-frequency words in English and Russian.