# BERT Fine-Tuning

This model is a fine-tuned BERT-uncased model for functional/non-functional requirement prediction, trained on AWS g5 instances using the PROMISE dataset and custom data, achieving an overall accuracy of 97%.

A fine-tuned BERT model for accurately distinguishing between AI-generated and human-written text.

BERT-based phishing email/webpage classification model achieving 87.3% accuracy on validation set

This is a sentiment analysis model fine-tuned based on FinancialBERT, specifically designed to analyze the sentiment tendencies (bearish, bullish, neutral) of financial news tweets.

A prompt compression token classification model fine-tuned on the multilingual BERT base model, designed for task-agnostic prompt compression

A BERT-based text classification model for recognizing Ekman's six basic emotions

BERT-based English text sarcasm detection model for identifying sarcastic content in news headlines

A part-of-speech tagging model fine-tuned on the udpos28 dataset based on bert-base-cased, designed for token classification tasks

A BERT-based banking customer service text classification model trained on the BANKING77 dataset with an accuracy of 92.64%

This is a sentiment classification model based on the BERT pre-trained model, specifically designed to analyze emotional tendencies in text.

A question-answering model fine-tuned on the SQuAD v2 dataset based on BERT base uncased version