# DeBERTa Optimization

The CNER model is a named entity recognition model based on the DeBERTa-v3-base architecture, capable of jointly identifying and classifying concepts and named entities with fine-grained labels.

The first publicly available medical language model trained on real European Portuguese data

Financial news sentiment analysis model fine-tuned on DeBERTa-v3-small, achieving an F1 score of 0.9940 on the evaluation set

This model is a question-answering model based on the DeBERTa architecture, fine-tuned on the SQuAD1, AQA, and NewsQA datasets.

A fine-tuned aspect-level sentiment analysis model based on DeBERTa-v3-large, supporting sentiment polarity classification across multiple domains

A DeBERTa-v3-base-based aspect-based sentiment analysis model, specifically designed to identify the sentiment polarity of specific aspects in text.

DeBERTa-v3 model trained on the MultiNLI dataset for natural language inference tasks, excelling in zero-shot classification scenarios.