UlizaLlama

Jacaranda Health launched UlizaLlama (AskLlama), an open-access Large Language Model (LLM) set to improve AI-driven support for Swahili speakers. The launch represents the first ever Swahili LLM that's both free to use and modify, meaning other organizations across Africa can ‘plug and play’ the model into their own systems to develop and scale Swahili-based services.

UlizaLlama is a 7B Parameters language model that builds upon the foundation of Jacaranda/kiswallama-pretrained. Jacaranda/kiswallama-pretrained is a large language model continually-pretrained with 321,530,045 swahili tokens and a customized tokenizer with a swahili vocabulary of 20,000 tokens to extend the capabilities of Meta/Llama2. It offers significant improvements in both encoding and decoding for Swahili text, surpassing the Swahili performance of Meta/Llama2. Moreover, Jacaranda/kiswallama-pretrained excels in providing accurate next-word completions in Swahili, a capability which Meta/Llama2 falls short of.