AIbase
EN
Home
Sinhalaberto
S

Sinhalaberto

Developed by keshan
This is a relatively small model trained on the deduplicated OSCAR Sinhala dataset, providing foundational support for the low-resource Sinhala language.
Large Language Model Other#Sinhala pretraining#Low-resource language model#Masked language modeling
Downloads 34
Release Time : 3/2/2022

Model Overview

This model is a Sinhala language model trained based on the Roberta architecture, primarily used for masked language modeling tasks to provide a pretraining foundation for downstream tasks.

Model Features

Low-resource language support
Specially optimized for the resource-scarce Sinhala language.
Lightweight architecture
Utilizes a streamlined Roberta architecture with 6 hidden layers, suitable for resource-constrained environments.
Large-scale pretraining data
Trained on the deduplicated OSCAR dataset, covering a wide range of linguistic features.

Model Capabilities

Text infilling
Language modeling
Context prediction

Use Cases

Natural Language Processing
Text completion
Automatically completes missing parts in Sinhala sentences.
Accurately predicts masked vocabulary in sentences.
Language model fine-tuning
Serves as a pretrained base model for downstream NLP tasks.
Provides a transfer learning foundation for various Sinhala NLP applications.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase