# RoBERTa architecture

This is a Polish text ranking model trained using Mean Squared Error (MSE) distillation method, with a training dataset containing 1.4 million queries and 10 million document text pairs.

SimCSE(sup) is a model for Chinese sentence similarity tasks. It can encode sentences into embedding vectors and calculate the cosine similarity between sentences.

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 clustering and semantic search.

This is a sentence-transformers model that maps sentences and paragraphs to a 768-dimensional dense vector space, suitable for tasks like clustering or semantic search.

This is a sentence transformer model based on IndoRoberta, capable of mapping Indonesian sentences and paragraphs into a 768-dimensional vector space, suitable for sentence similarity computation and semantic search tasks.

Dutch legal domain base model based on RoBERTa architecture

A multilingual XLM-RoBERTa model pre-trained on legal data, supporting legal text processing in 24 European languages

This is a Thai sentence similarity model based on the RoBERTa architecture, capable of mapping sentences into a 768-dimensional vector space, suitable for tasks like semantic search.

MaltBERTa is a large-scale pretrained language model based on Maltese text, using the RoBERTa architecture, developed by the MaCoCu project.

Spanish/English POS tagging model based on RoBERTuito, optimized for Twitter text

Catalan named entity recognition model based on RoBERTa architecture, fine-tuned on the AnCora-Ca-NER dataset

Named entity recognition model fine-tuned on multilingual datasets based on xlm-roberta-base

RoBERTa-based model for Coptic POS tagging and dependency parsing

This is a Tibetan pre-trained causal language model based on the RoBERTa architecture, primarily designed for Tibetan text generation tasks.

RoBERTa base model pre-trained on Turkish, trained with 38GB of Turkish corpus

Pre-trained language model specifically designed for the Spanish biomedical domain, suitable for clinical NLP tasks

A Russian model fine-tuned on an unspecified dataset based on roberta-retrained_ru_covid, potentially related to processing COVID-19 research papers

RobBERT is the current state-of-the-art Dutch BERT model, optimized based on the RoBERTa architecture, suitable for various text classification and tagging tasks

Monolingual RoBERTa-base model for Slovak, pretrained on a 4.5GB cleaned Slovak news corpus

This is a masked language model focused on the Tswana language, aiming to enhance the performance of low-resource South African languages in the field of NLP.

QA model fine-tuned on the SQuAD dataset based on roberta-base

Persian (ZWNJ) sentence embedding model based on RoBERTa architecture for generating sentence-level feature representations

This model is part of the event extraction system from the ACL2021 paper, based on the RoBERTa-large architecture, fine-tuned using the QAMR dataset for zero-shot event extraction tasks.

A RoBERTa-like language model trained on Esperanto, suitable for fill-in-the-blank tasks

A question-answering model developed based on the roberta-large architecture, specifically trained for the SQuAD 2.0 dataset

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

An Indonesian pretrained model based on RoBERTa-base architecture, trained on Indonesian Wikipedia data, case insensitive.

FERNET-News is a monolingual base model based on Czech RoBERTa, pre-trained on a thoroughly cleaned 20.5GB Czech news corpus.

A Vietnamese sentence embedding model based on sentence-transformers, mapping text to a 768-dimensional vector space, suitable for semantic search and clustering tasks.

Icelandic masked language model trained on RoBERTa-base architecture using 16GB of Icelandic text data

A RoBERTa model pre-trained on Korean, suitable for Korean understanding tasks.

This is a Q&A model based on the RoBERTa architecture, specifically trained on the SQuAD 2.0 dataset, suitable for English Q&A tasks.

Spanish pre-trained model based on RoBERTa architecture, specialized in masked language modeling tasks

An encoder-decoder model based on RoBERTa architecture, specifically designed for extreme summarization tasks, fine-tuned on the BBC XSum dataset.

tunbert_zied is a language model based on the Tunisian dialect, with an architecture similar to RoBERTa, trained on over 600,000 Tunisian dialect phrases.

BERTweet is the first large-scale publicly available language model pretrained specifically for English tweets, optimized based on the RoBERTa architecture for social media text processing.

Natural language inference model fine-tuned on MNLI task based on Catalan RoBERTa model

This is a RoBERTa model pre-trained on Thai Wikipedia text, using character-level embeddings to adapt to BertTokenizerFast.

SinBERT is a Sinhala pre-trained language model based on the RoBERTa architecture, trained on a large Sinhala monolingual corpus (sin-cc-15M).

SinBERT is a model pretrained on a large Sinhala monolingual corpus (sin-cc-15M) based on the RoBERTa architecture, suitable for Sinhala text processing tasks.