# BERT Architecture

Burmese-Bert is a bilingual masked language model based on bert-large-uncased, supporting both English and Burmese.

M2-BERT-8K is an 80-million-parameter long-context retrieval model based on the architecture proposed in the paper 'Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT'.

GGUF format version of the General Text Embedding (GTE) model, suitable for tasks like information retrieval and semantic text similarity.

A sentiment analysis model based on BETO (Spanish version of BERT), supporting sentiment classification for Spanish text.

Erya4FT is a fine-tuned Classical Chinese translation model based on the Erya model, specializing in translating Classical Chinese into Modern Chinese.

This is a model based on sentence-transformers that maps sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as sentence similarity calculation and semantic search.

This is a sentence embedding model based on sentence-transformers, which can map text to a 312-dimensional vector space and is suitable for tasks such as semantic search and text similarity calculation.

A question-answering model fine-tuned on the SQuAD dataset based on bert-base-multilingual-cased

A BERT model trained on publicly available monolingual Tamil datasets, suitable for Tamil natural language processing tasks.

This is a model based on sentence-transformers, capable of mapping sentences and paragraphs into a 768-dimensional vector space for sentence similarity calculation and semantic search tasks.

This is a model based on sentence-transformers that can map sentences and paragraphs to a 768-dimensional dense vector space, suitable for tasks such as sentence similarity calculation and semantic search.

This is a sentence similarity model based on sentence-transformers, which maps text to a 384-dimensional vector space, suitable for semantic search and clustering tasks.

This model provides word segmentation functionality for classical Chinese, with training datasets covering four historical periods of Chinese language development.

This is a model based on sentence-transformers that can map sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

A language model based on BERT architecture, using first character prediction as the pre-training objective

A BERT-based Chinese named entity recognition model, achieving near state-of-the-art performance on the People's Daily dataset

A BERT-based masked language model for Buddhist Sanskrit text processing, specifically designed for handling Buddhist Sanskrit texts

BERT-base based named entity recognition model, capable of identifying four types of entities including locations, organizations, and person names

This is a model based on sentence-transformers, capable of mapping sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as sentence similarity calculation and semantic search.

A BERT-based encoder-decoder model specifically designed for German-to-English machine translation tasks.

A pre-trained language model based on the Transformer architecture, suitable for various natural language processing tasks.

A Russian natural language inference model fine-tuned from DeepPavlov/rubert-base-cased, capable of predicting logical relationships (entailment/contradiction/neutral) between two texts

PERT is a Chinese pre-trained model based on BERT, focusing on improving Chinese text processing capabilities.

A text classification model fine-tuned on the GLUE MNLI dataset based on bert-base-cased, designed for natural language inference tasks

This is a paraphrase detector developed based on DeepPavlov, migrated to the Transformers format, used to detect whether Russian texts are paraphrases.

This is a model based on sentence-transformers that can map sentences and paragraphs to a 384-dimensional dense vector space, suitable for tasks such as clustering and semantic search.

KoBERT-LM is a pre-trained language model optimized for Korean, based on the BERT architecture and further pre-trained specifically for Korean text.

Pretrained Arabic BERT base language model supporting Modern Standard Arabic and some dialects

A BERT-based pre-trained language model for the scientific domain, trained using a scientific literature vocabulary

This model is a branch version based on the bert-based-uncased-hatespeech-movies model, used to classify text as normal, offensive, or hate speech.

This is a BERT-based Turkish question-answering model, specifically designed for handling Turkish Q&A tasks.

A BERT-based spelling correction model for detecting and correcting spelling errors in text.

HebEMO is a tool designed to detect sentiment polarity and extract emotions from modern Hebrew user-generated content, trained on a unique COVID-19 related dataset with superior performance.

A question-answering model fine-tuned on biomedical text based on PubMedBERT, focused on PubMedQA tasks

A multilingual QA model based on bert-base-multilingual-uncased, fine-tuned on the XQuAD dataset

A BERT-based sentiment classifier for classical poetry, specialized in analyzing emotional tendencies in ancient texts.

A named entity recognition tool specifically designed for classical Chinese texts, capable of identifying named entities in ancient writings.

This is a sentence embedding model based on sentence-transformers, which can map text to a 256-dimensional vector space and is suitable for semantic search and clustering tasks.

This is a BERT-based Turkish named entity recognition model, suitable for entity recognition tasks in Turkish texts.

A question-answering model fine-tuned on the SQuAD dataset based on the BERT base model, suitable for few-shot learning scenarios