Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

NaolBM/africa-extended

Domaine:

natural language processing

Type de record:

dataset
Créateur:
Nao
Hôte:
This document details the complete training process for creating NaolBM/LFM2.5-1.2B-AfriBase - a 1.2B parameter model optimized for African languages through vocabulary extension and continued pre-training (CPT). The model extends the LFM2.5-1.2B base model with an Africa-optimized tokenizer and continued pre-training on a massive multilingual African corpus. Key Stats:

Visit

huggingface.co

Tasks

language modeling

Languages

AmharicHausaOromoSwahiliTigrignaYoruba

Tags

tokenizerafrican-languagesbyte-level-bpemultilingual

Licenses

apache-2.0

Similaires

NaolBM/Africa-BBPENaolBM/african-corpusNaolBM/amharic-corpusNaolBM/amharic-audioNaolBM/Oromo-BBPENaolBM/qwen3-vlm-4b-amharic-cpt

NaolBM/Africa-BBPE

NaolBM/african-corpus

Total rows: 35,344,339 Languages: 7 African languages + English Features: text | language Language

NaolBM/amharic-corpus

NaolBM/amharic-audio

This dataset contains 59K audio chunks derived from Amharic Bible readings, split into 5-second segm

NaolBM/Oromo-BBPE

NaolBM/qwen3-vlm-4b-amharic-cpt