BULaMU-Dream: The First Text-to-Image Model Trained from Scratch for an African Language

Domain:

natural language processing

Record type:

modelpaper

Creator:

Mwe

Publisher:

Host:

This paper introduces BULaMU Dream, the first text-to-image, conditional diffusion model in the world trained from scratch to generate images from prompts in an African Language, Luganda.

mwebazarick/BULaMU-Dream

This is the repository for BULaMU-Dream and is the first text-to-image model to be trained from scra

From Scratch vs Pre-trained: A Dataset Size Analysis for Small-Scale Language Model Training

This research presents an empirical comparison of from-scratch versus pre-trained language model tra

BULaMU: An Open Foundation Model for Luganda

Uganda, colloquially referred to as the “pearl of Africa”, is home to

A Complete Guide to Constructing and Implementing an EF5 Model from Scratch.

Building an EF5 Model: A Step-by-Step Guide A complete guide to constructing and implementing

How Far Can Multilingual Text Embeddings Be Trained From Scratch? A Compute-Efficient Study of Arabic, English, and Urdu

We investigate how much useful multilingual embedding capability can be obtained when the s

AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text

Language models built from various sources are the foundation of today's NLP progress. However, for

BULaMU-Dream: The First Text-to-Image Model Trained from Scratch for an African Language

Domain:

Record type:

Visit

Languages

Licenses

Similar