Minerva AI is an advanced language model developed by the Sapienza NLP research group at Sapienza University of Rome, led by Professor Roberto Navigli. It represents Italy’s first family of large language models (LLMs) trained from scratch with a primary focus on the Italian language.
The Minerva project encompasses a range of models varying in size and computational capacity, with the most advanced being Minerva 7B. This model features 7 billion parameters and has been trained on approximately 2.5 trillion tokens, evenly split between Italian and English texts, along with an additional 200 billion tokens of code. This extensive training enables Minerva AI to proficiently handle both Italian and English languages, making it a valuable tool for various natural language processing tasks.
Developed within the Future Artificial Intelligence Research (FAIR) project, Minerva AI was created in collaboration with CINECA, which provided the Leonardo supercomputer for training. Additional contributions came from Babelscape and the CREATIVE PRIN Project. Notably, Minerva models are truly open, with both data and models accessible to the public.
Minerva AI represents a significant advancement in Italian AI research, offering a robust and open resource for the development of future chatbots and other AI applications.
See more details on: