# DeBERTa architecture

A zero-shot text classification model based on DeBERTa-v3-base, used to determine the logical relationship (entailment, neutral, or contradiction) between premises and hypotheses.

A German zero-shot classification model fine-tuned on DeBERTa-v3-base, suitable for multi-label classification tasks

A model fine-tuned based on microsoft/deberta-v3-large for evaluation tasks. The specific task type is unknown.

This is a sentence transformer model based on the DeBERTa architecture, capable of mapping sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as semantic search and clustering.

A Q&A model based on DeBERTa-base architecture, jointly fine-tuned on SQuAD1, AQA, and NewsQA datasets

A cross-encoder model trained on microsoft/deberta-v3-xsmall for natural language inference tasks, supporting contradiction, entailment, and neutral relationship judgments.

A natural language inference model based on the DeBERTa-v3-large architecture, trained on SNLI and MultiNLI datasets for determining the relationship between sentence pairs.

Cross-encoder model trained on microsoft/deberta-v3-xsmall for natural language inference tasks

Named Entity Recognition (NER) model fine-tuned on the conll2003 dataset based on DeBERTa-base

A cross-encoder model trained on microsoft/deberta-v3-small for natural language inference tasks, supporting contradiction, entailment, and neutral relationship judgments