Roberta Tagalog Large
A Filipino RoBERTa model trained on the TLUnified corpus, improved from previous versions with case-sensitive processing support.
Downloads 534
Release Time : 3/2/2022
Model Overview
This model is a RoBERTa-based language model optimized for Filipino, suitable for various natural language processing tasks, aiming to promote the development of the Filipino NLP community.
Model Features
Improved Filipino Language Processing
Trained on an updated TLUnified corpus with larger data scale and more diverse topics.
Case-sensitive Design
Specifically designed as a case-sensitive version, suitable for applications requiring case preservation.
Academic Research-oriented
Open-sourced as a result of a large-scale research project, aiming to advance NLP for low-resource languages.
Model Capabilities
Text Understanding
Language Modeling
Text Classification
Use Cases
Academic Research
Filipino NLP Research
Used for research related to Filipino language models
Improves performance benchmarks for Filipino tasks
Commercial Applications
Filipino Text Processing
Suitable for Filipino content analysis and processing
Featured Recommended AI Models
Š 2025AIbase