# Low-resource language models

A 4-bit quantized version fine-tuned based on the Qwen2.5-1.5B model, focusing on Turkish text generation and summarization tasks

This is a BERT base model pretrained specifically for Tigrinya, trained for 40 epochs on a dataset of 40 million tokens.

A token classification model for Wolof named entity recognition (NER) tasks, fine-tuned on the Wolof portion of the MasakhaNER dataset based on xlm-roberta-base

This model is fine-tuned on the Swahili portion of the MasakhaNER dataset for named entity recognition tasks in Swahili text.

A Yoruba automatic tone restoration model fine-tuned on mT5-base, trained on JW300 and Menyo-20k datasets