# DeBERTa Architecture

A fine-tuned AI-generated text detection model based on DeBERTa-v3-large, optimized for academic scenarios

CamemBERTav2 is a French language model pretrained on 275 billion French text tokens, utilizing the DebertaV2 architecture, and excels in multiple French NLP tasks.

A multilingual text sentiment classification model fine-tuned based on mDeBERTa-v3-base, supporting cross-language sentiment analysis

CyNER 2.0 is a named entity recognition model specifically designed for the cybersecurity domain, based on the DeBERTa architecture, capable of identifying various cybersecurity-related entities.

KF-DeBERTa is a financial domain-specific language model jointly released by KakaoBank and FNGuid, built on the DeBERTa-v2 architecture, demonstrating excellent performance in both general and financial domain downstream tasks.

A DeBERTa V3 model trained on Japanese resources, optimized for Japanese, and does not rely on a morphological analyzer during inference

Albertina 100M PTBR is a foundational large language model for Brazilian Portuguese, belonging to the BERT family of encoders, based on the Transformer neural network architecture, and developed on the DeBERTa model.

Albertina 100M PTPT is a foundational large language model for European Portuguese (Portugal), belonging to the BERT family of encoders. It is based on the Transformer neural network architecture and developed upon the DeBERTa model.

A Japanese Q&A model fine-tuned based on deberta-v2-base-japanese, using the DDQA dataset for fine-tuning, suitable for Q&A tasks.

A Japanese DeBERTa V2 base model pretrained on Japanese Wikipedia, CC-100, and OSCAR corpora, suitable for masked language modeling and downstream task fine-tuning.

DeBERTa(V2) model pretrained on Japanese Wikipedia and Aozora Bunko texts, suitable for Japanese text processing tasks

This model is a fine-tuned version of DeBERTa-base on the SQuAD question answering dataset, designed for automatic question answering tasks

A QA model fine-tuned on the adversarial_qa dataset based on microsoft/deberta-base

This model is a question-answering model based on DeBERTa-base, fine-tuned on the SQuAD1 dataset and further fine-tuned on the adversarial_qa dataset.

A model fine-tuned based on microsoft/deberta-large for specific task processing

A cross-encoder model based on microsoft/deberta-v3-large architecture, trained for natural language inference tasks on SNLI and MultiNLI datasets.

A text sentiment classification model fine-tuned based on microsoft/deberta-v3-base, trained on an unknown dataset with an evaluated F1 score of 0.4468

DeBERTa-v3-large model fine-tuned on GLUE MNLI dataset for natural language inference tasks, achieving 90% accuracy on the validation set

A sentiment analysis model fine-tuned on the SST-2 dataset based on microsoft/deberta-v3-large

A text classification model fine-tuned based on microsoft/deberta-v3-large, trained on the SST-2 dataset

A text classification model fine-tuned on the SST-2 dataset based on microsoft/deberta-v3-large

A sentiment analysis model fine-tuned on the SST-2 dataset based on microsoft/deberta-v3-large