Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Fine-Tuned Large Language Model (LLM) on Nigerian Pidgin English with GGUF 4/5/8-bit Quantisation

Domain:

natural language processing

Record type:

model
Creator:
NwoIhiMacBir
Publisher:
Zenodo
Host:avatar
This model is a fine-tuned LLaMA 3.2B parameter model, trained on a curated Nigerian Pidgin English dataset collected via web scraping from multiple news and media sources. The dataset was cleaned and normalised to ensure linguistic consistency and suitability for downstream natural language processing tasks. The model has been quantised using GGUF in 4-bit, 5-bit, and 8-bit formats to balance language quality and computational efficiency. Higher-bit variants offer improved fluency and coherence, while lower-bit models remain efficient for deployment in resource-constrained settings. This model is suitable for research and applications in multilingual NLP, low-resource language modelling, and inclusive education.

Visit

doi.orgzenodo.org

Tasks

language modeling

Languages

Ghanaian Pidgin EnglishPidgin, Nigerian

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similar

Nigerian Pidgin English Dataset with 5 EmotionDhati+: Fine-tuned Large Language Models for Arabic Subjectivity EvaluationCross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on RomanianChapter 5. Sources of locative for in Nigerian Pidgin and Ghanaian Pidgin EnglishChapter 4. Meanings and functions of for in Nigerian Pidgin and Ghanaian Pidgin EnglishFinetuning Large Language Models for Automated Depression Screening in Nigerian Pidgin English: GENSCORE Pilot Study

Nigerian Pidgin English Dataset with 5 Emotion

Dhati+: Fine-tuned Large Language Models for Arabic Subjectivity Evaluation

Despite its significance, Arabic, a linguistically rich and morphologically complex language, faces

Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian

Relation extraction (RE) for low-resource languages is typically constrained by the lack of annotate

Chapter 5. Sources of locative for in Nigerian Pidgin and Ghanaian Pidgin English

Chapter 4. Meanings and functions of for in Nigerian Pidgin and Ghanaian Pidgin English

Finetuning Large Language Models for Automated Depression Screening in Nigerian Pidgin English: GENSCORE Pilot Study

Depression is a major contributor to the mental-health burden in Nigeria, yet screening coverage rem