# Cross-lingual Transfer

mBART-large-50 is a multilingual sequence-to-sequence model supporting text summarization and generation tasks in 50 languages.

EriBERTa is a bilingual domain-specific language model pre-trained on a massive corpus of clinical medical texts. It surpasses all previous Spanish-language models in the clinical domain, demonstrating exceptional medical text comprehension and information extraction capabilities.

A multilingual Holocaust-related named entity recognition model fine-tuned based on XLM-RoBERTa, supporting 9 languages with an F1 score of 81.5%.

Inference information: This is an open-source model based on the Apache-2.0 license, specific functionalities need to be elaborated

A multilingual text generation model pretrained on the mC4 multilingual corpus, supporting 107 languages

A unified multilingual T5 model pre-trained on the mC4 multilingual corpus, covering 107 languages

This is a multilingual sentiment analysis model trained using zero-shot distillation technology, supporting sentiment classification in 12 languages.

This is a pruned version of facebook/mbart-large-50, retaining only Russian and English embedding vectors, with the vocabulary reduced from 250k to 25k.

This is a multilingual model supporting 100 languages, specifically designed for natural language inference (NLI) and zero-shot classification tasks. It is based on the Baidu ERNIE-M architecture and fine-tuned on the XNLI and MNLI datasets.

A multilingual Q&A model fine-tuned on the xquad dataset based on bert-base-multilingual-cased

A QA model fine-tuned on the Persian QA dataset PQuAD based on the XLM-RoBERTA multilingual pretrained model

A fine-tuned version based on the XLM-RoBERTa-base model on a specific dataset, primarily used for sequence labeling tasks, with an evaluated F1 score of 0.8561.

A German token classification model fine-tuned on the xtreme dataset based on xlm-roberta-base

A German token classification model fine-tuned on the xtreme dataset based on XLM-RoBERTa-base

A German token classification model fine-tuned on the xtreme dataset based on XLM-RoBERTa-base, designed for named entity recognition tasks.

A fine-tuned version of the XLM-RoBERTa-base model on German and French datasets, primarily used for named entity recognition tasks.

A multilingual POS tagging model based on XLM-RoBERTa, fine-tuned on Universal Dependencies v2.8, supporting POS tagging tasks in Swedish and multiple other languages.

A multilingual text formality classification model based on XLM-Roberta, supporting English, French, Italian, and Portuguese

XLM-RoBERTa is a multilingual pre-trained model based on the RoBERTa architecture, supporting 100 languages and suitable for cross-lingual understanding tasks.

This model is a fine-tuned version of xlm-roberta-base on the xtreme dataset for German token classification tasks.

This is a test model fine-tuned using the Spanish dataset from stsb_multi_mt for semantic text similarity tasks.

This is a named entity recognition model based on the XLM-RoBERTa model, fine-tuned on the Swahili portion of the MasakhaNER dataset.

XLM-RoBERTa-large is a multilingual pretrained language model based on the RoBERTa architecture, supporting various natural language processing tasks in multiple languages.

This is a multilingual text sentiment analysis model based on DistilBERT, fine-tuned on the amazon_reviews_multi dataset, supporting sentiment classification tasks in multiple languages.

A multilingual text classification model fine-tuned on the amazon_reviews_multi dataset based on XLM-RoBERTa-base

A named entity recognition model fine-tuned on XLM-RoBERTa, supporting token classification tasks in English text.

A named entity recognition model fine-tuned based on XLM-RoBERTa, supporting entity recognition tasks in English text.

XLM-RoBERTa is a multilingual pretrained model based on the RoBERTa architecture, supporting 100 languages and excelling in cross-lingual understanding tasks.

A speech recognition model based on Microsoft's UniSpeech architecture, specifically fine-tuned for the Kyrgyz language

This is a Turkish text classification model fine-tuned based on the BERT architecture, capable of classifying Turkish texts into 7 predefined categories.

A Hindi pre-trained language model based on the ELECTRA architecture, outperforming multilingual BERT on various Hindi NLP tasks

A multilingual POS tagging model based on XLM-RoBERTa, fine-tuned on Universal Dependencies v2.8 with special optimization for Welsh

This model is a bert-base-multilingual-cased model fine-tuned on English CoNLL-formatted OntoNotes v5.0 semantic role labeling data, primarily used for semantic role labeling tasks.

LitLat BERT is a trilingual model based on the xlm-roberta-base architecture, focusing on Lithuanian, Latvian, and English performance.

XLM-RoBERTa is a multilingual model pretrained on 2.5TB of filtered CommonCrawl data across 100 languages, trained with a masked language modeling objective.

FinEst BERT is a trilingual model based on the bert-base architecture, specializing in Finnish, Estonian, and English processing. It outperforms multilingual BERT models while retaining cross-lingual knowledge transfer capabilities.

XLM-RoBERTa is a multilingual model pretrained on 2.5TB of filtered CommonCrawl data across 100 languages, using masked language modeling as the training objective.

KE-T5 is a Korean-English bilingual text generation model based on the T5 architecture, developed by the Korea Electronics Technology Institute, supporting cross-lingual knowledge transfer for dialogue generation tasks.

This is a versatile large language model capable of handling various natural language processing tasks