QLoRA fine-tune of
McGill-NLP/AfriqueLlama-8B
on Tanzanian business, tax, company registration, and financial regulation data.
Base model: AfriqueLlama-8B (Llama 3.1 8B, 20 African languages incl. Swahili)
Languages: Swahili (sw), English (en)
Training: QLoRA r=16 on Tesla T4 (sm_75)
Training pairs: 2,267 (adapter-v6 trained from AfriqueLlama-8B base)
Validation loss: 0.4317
Gate result: PASSED
LoRA-only checkpoint: prospAprospA007/africa-giants-adapter-v6-lora
