# Lightweight BERT

NeuroBERT Professional is a lightweight natural language processing model based on BERT, designed specifically for resource-constrained devices, offering accuracy close to BERT-base.

NeuroBERT-Mini is a lightweight natural language processing model derived from google/bert-base-uncased, optimized for real-time inference on edge and IoT devices.

A text classification model fine-tuned on distilbert-base-uncased, trained on the AG News dataset with an accuracy of 89.06%

A multilingual sentiment analysis model based on DistilBERT, suitable for text sentiment classification tasks in multiple languages.

OpenBioNER is a lightweight BERT model specifically designed for open-domain biomedical named entity recognition (NER). It can identify unseen entity types using only natural language descriptions of target entity types, without requiring retraining.

A Russian emotion classification model fine-tuned based on lightweight RuBERT-tiny2, capable of recognizing five emotions

A fine-tuned DistilBERT-base-uncased food/non-food text classifier achieving 100% accuracy on the evaluation set

This is a pre-trained DistilBERT model fine-tuned on the SST-2 dataset for sentiment analysis. It can predict whether a given text expresses positive or negative sentiment.

A sentiment analysis model fine-tuned based on distilbert-base-uncased for text sentiment classification tasks

This is a sentiment analysis model fine-tuned on distilbert-base-uncased, achieving 93.2% accuracy on the evaluation set.

bert-lite is a lightweight natural language processing model optimized based on the BERT framework, designed for low-resource environments and suitable for tasks like MNLI and NLI.

A text classification model fine-tuned based on DistilBERT for analyzing sentiment tendencies in Amazon cosmetics product reviews

A lightweight BERT model, specifically fine-tuned for URL classification tasks, capable of categorizing URLs into four types: benign, phishing, malware, and tampered.

A lightweight text classification model based on DistilBERT for location classification tasks

A DistilBERT fine-tuned model for malicious URL detection, capable of accurately identifying harmful links such as phishing or malware

A text classification model fine-tuned based on distilbert-base-uncased, achieving an F1 score of 0.6147

Ruri is a Japanese universal text embedding model based on ModernBERT-Ja, offering versions with different parameter scales suitable for various text processing tasks.

A sentiment analysis model based on DistilBERT for classifying product reviews as positive, negative, or neutral

A text classification model based on DistilBERT for detecting whether input text qualifies as a tarot divination question.

A text classification model fine-tuned based on distilbert-base-uncased, trained for specific tasks.

A lightweight sentiment analysis model based on DistilBERT, suitable for text sentiment classification tasks

This model is a fine-tuned version of DistilBERT-base-uncased on the CoLA (Corpus of Linguistic Acceptability) dataset, designed for grammatical acceptability judgment tasks.

This is a BERT-tiny fine-tuned cross-encoder model for computing similarity scores between text pairs, suitable for tasks like semantic search and text classification.

This is a cross-encoder model fine-tuned from bert-tiny for computing similarity scores between text pairs, suitable for tasks like semantic textual similarity and semantic search.

This is a cross-encoder model fine-tuned from bert-tiny for calculating similarity scores between text pairs, suitable for various tasks such as semantic textual similarity and semantic search.

A text classification model fine-tuned on the IMDB dataset based on the distilbert-base-uncased model

Lightweight BERT model fine-tuned specifically for URL classification tasks, capable of categorizing URLs as benign, phishing, malware, or defacement

This model is a text classification model optimized based on the DistilBert architecture, specifically designed for classifying IMDB movie reviews as positive or negative sentiment.

A question-answering model fine-tuned on distilbert-base-uncased-distilled-squad, achieving an F1 score of 81.33 on the evaluation set

This is a fake news detection model based on DistilBERT, capable of classifying news articles as real or fake based on their textual content.

A network intrusion detection model optimized based on the DistilBERT architecture, used to identify and analyze anomalous behaviors in network traffic

A lightweight sentence embedding model based on DistilBERT, suitable for various text processing tasks

An 8-layer embedding model distilled from BAAI/bge-m3, achieving 2.5x speed improvement while maintaining retrieval performance

DistilBERT is a lightweight distilled version of BERT, retaining 97% of BERT's performance while being 40% smaller and 60% faster in inference.

A sentiment analysis model based on DistilBERT, fine-tuned on an unknown dataset with an accuracy of 56.16%

A sentiment analysis model based on DistilBERT that classifies English texts into positive, negative, or neutral sentiments.

Turkish sentence similarity calculation model based on DistilBERT architecture

DistilBERT is a lightweight distilled version of BERT, retaining 97% of BERT's performance while being 40% smaller in size.

A sentiment analysis model fine-tuned on DistilBERT-base-uncased, trained on the IMDB dataset with an accuracy of 93.1%

This model is a financial sentiment analysis model fine-tuned based on DistilBERT, specifically designed for sentiment classification of financial texts.