Skip to content
Wycord
AI Resources

AfroLM

Verified
AI Resources
LLM
Docs live

A multilingual masked language model pretrained from scratch on 23 African languages using a self-active learning framework, outperforming AfriBERTa, mBERT and XLMR-base on NER and sentiment tasks. Created by Bonaventure Dossou and collaborators, published at SustaiNLP/EMNLP 2022.

Website Documentation GitHub
Category
AI Resources
Pricing
Free / open weights
Country
🌍 Pan-African
Last verified
25 Aug 2026
{
  "name": "AfroLM",
  "slug": "afrolm",
  "category": "AI",
  "country": "Pan-African",
  "docs_status": "LIVE",
  "licensing_required": "NONE",
  "verified": true,
  "last_verified": "2026-08-25",
  "website": "https://huggingface.co/bonadossou/afrolm_active_learning",
  "documentation_url": "https://huggingface.co/bonadossou/afrolm_active_learning"
}
get_resource("afrolm") — via the Wycord MCP server

Verification history

  • 25 Aug 2026 · live
  • 22 Aug 2026 · live
  • 19 Aug 2026 · live
  • 16 Aug 2026 · live
  • 13 Aug 2026 · live
  • 10 Aug 2026 · live
  • 7 Aug 2026 · live
  • 4 Aug 2026 · live

Automated checks run every few days. See all recent status changes

Tags

nlp
african-languages
masked-language-model
active-learning
data-efficient

Compare AfroLM

Side-by-side, verified specs against its closest llm alternatives.

AfroLM vs InkubaLMAfroLM vs N-ATLaSAfroLM vs SERENGETIAfroLM vs UlizaLlama (Jacaranda Health)

Related in AI Resources

N-ATLaS

AI

Nigeria's first government-backed multilingual LLM (Sep 2025): a Llama-3 8B fine-tuned on 400M+ tokens across 4 Nigerian languages. Produced by NCAIR/NITDA and Awarri.

Docs live
LLM
Verified Jun 2026Open (research)

UlizaLlama (Jacaranda Health)

AI

UlizaLlama is a 7B-parameter Swahili-and-English LLM fine-tuned from Meta's Llama 2 (continually pretrained on ~321M Swahili tokens) by Jacaranda Health in Kenya, built to power Swahili maternal-health SMS support for low-income expectant mothers in East Africa.

Docs live
Approval required
LLM
Verified Aug 2026Free for research/social good; commercial use requires contacting Jacaranda Health

InkubaLM

AI

InkubaLM-0.4B is a 400M-parameter open-weights small language model built from scratch by Lelapa AI for five low-resource African languages (isiZulu, Yoruba, Swahili, isiXhosa, Hausa, plus English/French), using a LLaMA-style architecture trained on 2.4B tokens.

Docs live
LLM
Verified Aug 2026Free / open weights (CC BY-NC 4.0)