About
The Aquila family of large language models (LLMs), developed by the Beijing Academy of Artificial Intelligence (BAAI), includes open-source models that cater to both Chinese and English language requirements 35. These models adhere to Chinese domestic data regulations, offering commercial licenses that are crucial for wide adoption 35. The Aquila series features base models such as Aquila-7B and Aquila-33B, along with specialized versions like AquilaChat-7B for dialogue and AquilaCode-7B for coding tasks 35. With a significant focus on Chinese data, the models are trained to ensure native-level comprehension. BAAI also integrates advanced architectures from GPT-3 and LLaMA, employing efficient operators and a redesigned bilingual tokenizer for enhanced performance 1. The AquilaChat models excel in text dialogue and versatile language generation, while the AquilaCode models are recognized as leading open-source solutions for code generation in Chinese and English 5.