AI registry
AI Resources
African language models, speech & text datasets, and AI infrastructure.
10 results in LLM
AfroLM
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.
InkubaLM
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.
N-ATLaS
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.
SERENGETI
A massively multilingual masked language model covering 517 African languages and varieties across five scripts, achieving state-of-the-art results on the AfroNLU benchmark. Developed by the UBC Deep Learning and NLP Lab as an Afrocentric resource.
UlizaLlama (Jacaranda Health)
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.
EthioLLM
EthioLLM is a family of multilingual language models (XLM-RoBERTa and mT5 based) for five Ethiopian languages: Amharic, Ge'ez, Afaan Oromoo, Somali and Tigrinya, plus English. The large variant EthioLLM-l-70K is a fine-tuned XLM-RoBERTa-Large used for masked language modeling and downstream tasks like classification, NER and sentiment. It was released by the EthioNLP collective alongside the Ethiobenchmark evaluation suite.
Lugha-Llama
Lugha-Llama is a Llama-3.1-8B model continually pretrained on the WURA African-language corpus to lift performance on low-resource African languages. It ships in three variants (wura, wura_edu, wura_math) and reaches leading results among similarly sized models on the IrokoBench and AfriQA African-language benchmarks. It was built by researchers at Princeton University.
NileChat-3B
NileChat-3B is a 3B-parameter LLM built on Qwen2.5-3B and adapted for Egyptian and Moroccan communities, handling Egyptian and Moroccan dialectal Arabic in both Arabic script and Arabizi alongside Modern Standard Arabic, French and English. It was trained with controlled synthetic data and translated corpora and outperforms its Qwen2.5-3B baseline on Arabic benchmarks. It was released by the UBC Deep Learning and NLP Lab and accepted at EMNLP 2025.
SabiYarn-125M
SabiYarn-125M is a 125M-parameter decoder-only foundation model pretrained on Nigerian-language text, the first in the SabiYarn series. It supports English, Yoruba, Hausa, Igbo and Nigerian Pidgin plus Fulfulde, Efik and Urhobo, with fine-tuned variants for translation, NER, sentiment and diacritization. It was built by Aletheia.ai Research Lab and presented at the AfricaNLP 2025 workshop.
Sunflower-14B
Sunflower-14B is a Qwen3-14B based multilingual LLM by Sunbird AI supporting translation and text generation across 31 Ugandan languages plus English. It achieves the highest translation accuracy in 24 of 31 evaluated language pairs and targets healthcare, agriculture, education and government use cases. It is released under Apache 2.0 with quantized GGUF and W8A8 variants available.