AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
Paper • 2601.06395 • Published • 5
AfriqueLLM
Best open African LLM
-
-
McGill-NLP/AfriqueQwen-14B
Text Generation • 15B • Updated • 1.38k • • 4 -
McGill-NLP/AfriqueQwen3.5-9B-50Langs
Text Generation • 9B • Updated • 110 -
McGill-NLP/AfriqueQwen-8B
Text Generation • 8B • Updated • 451 • • 2 -
McGill-NLP/AfriqueQwen3.5-4B-50Langs
Text Generation • 5B • Updated • 1.91k • 7 -
McGill-NLP/AfriqueQwen3.5-4B-ExtendedCM
Text Generation • 5B • Updated • 110 -
McGill-NLP/AfriqueQwen3.5-4B
Text Generation • 5B • Updated • 988 -
McGill-NLP/AfriqueQwen-4B
Text Generation • 4B • Updated • 473 • -
McGill-NLP/AfriqueGemma-12B
Text Generation • 12B • Updated • 337 • • 1 -
McGill-NLP/AfriqueLlama-8B
Text Generation • 8B • Updated • 149 • -
McGill-NLP/AfriqueGemma-4B
Text Generation • 4B • Updated • 316 • -
McGill-NLP/AfriqueQwen3.5-0.8B-50Langs
Text Generation • 1B • Updated • 181 • 2 -
McGill-NLP/AfriqueQwen3.5-4B-Instruct-v1
Text Generation • 5B • Updated • 688 -
McGill-NLP/AfriqueQwen3.5-4B-Instruct-v2
Text Generation • 4B • Updated • 695 -
McGill-NLP/AfriqueQwen3.5-4B-50Langs-Instruct-v1
Text Generation • 4B • Updated • 2.36k • 1 -
McGill-NLP/AfriqueQwen3.5-9B-50Langs-Instruct-v1
Text Generation • 9B • Updated • 1.96k • 3