# High-Precision Text Classification

A Japanese-English bilingual sentence feature extraction model based on modernbert-ja-310m, supporting sentence similarity computation and text classification tasks

A pre-trained model based on the RoBERTa architecture, specifically designed for sentiment analysis tasks on Twitter text.

This is a DistilBERT model fine-tuned on the SST-2 English dataset using AutoTrain for text classification tasks.

BGE Large English v1.5 is a high-performance sentence transformer model, focusing on sentence feature extraction and similarity computation.

A fine-tuned large language model optimized for central bank communications, including economic entity classifier and sentiment classifier

This model is a fine-tuned version of the LayoutXLM base model on the DocLayNet dataset, specifically designed for document layout analysis and paragraph-level content understanding.

This model is a fine-tuned version of BERTurk cased on the TREMO Turkish sentiment classification dataset, designed for Turkish sentiment analysis tasks.

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

Fine-tuned based on the BERTweet foundation model for detecting linguistic uncertainty (hedging) in social media texts.

A roberta-large model fine-tuned on the WANLI dataset for natural language inference tasks, outperforming roberta-large-mnli on multiple out-of-domain test sets.

BatteryBERT-cased is a pre-trained language model specifically designed for classifying battery-related paper abstracts. Based on the BERT architecture, it is optimized for battery domain texts.

This is a text classification model based on BatteryOnlyBERT-uncased, specifically designed for classifying abstracts of battery-related research papers.

This model is a financial text sentiment classification model fine-tuned on the financial_phrasebank dataset based on deepmind/language-perceiver.

A text classification model based on BatterySciBERT-uncased, specifically designed for classifying battery-related paper abstracts.

A multilingual text toxicity classification model trained on the JIGSAW Toxic Comment Classification Challenge dataset, supporting 10 languages.

DeBERTaV3 is an improved pre-trained language model based on DeBERTa, which enhances efficiency through gradient-disentangled embedding sharing in ELECTRA-style pretraining and excels in natural language understanding tasks.