# OSCAR dataset

This is a Mongolian text generation model based on the GPT2 architecture, designed to generate fluent Mongolian text.

A Hebrew BERT-style masked language model based on character operations, pre-trained by masking character fragments, similar to SpanBERT.

This is a relatively small model trained on the deduplicated OSCAR Sinhala dataset, providing foundational support for the low-resource Sinhala language.

This model is based on the base variant of XLM-RoBERTa, fine-tuned using Gujarati language and OSCAR monolingual datasets, suitable for Gujarati natural language processing tasks.