# Wikipedia pretraining

This is a Japanese BART base model pretrained on Japanese Wikipedia, suitable for natural language processing tasks.

A T5 (Text-to-Text Transfer Transformer) model pretrained on Japanese corpus, suitable for various text generation tasks.

A multilingual RoBERTa-style model trained on Hindi, Sanskrit, and Gujarati Wikipedia articles, supporting processing for three Indo-Aryan languages.

A small ELECTRA model pretrained on Japanese Wikipedia, suitable for Japanese text generation and infilling tasks

This is a sentence-transformers model based on XLM-R, specifically optimized for Thai language, capable of mapping sentences and paragraphs into a 768-dimensional dense vector space.

A GPT-2 model pretrained on Hungarian Wikipedia and fine-tuned on Hungarian news corpus, specifically designed for Hungarian news text generation

This is a lightweight version of distilbert-base-multilingual-cased, supporting English, French, Spanish, Portuguese, and Italian language processing.

A RoBERTa model pretrained on Thai Wikipedia text for POS tagging and dependency parsing

This is a lightweight version of distilbert-base-multilingual-cased, specifically optimized for English and Danish, while maintaining the original model's representational capabilities and accuracy.