July 12, 2022 – We are releasing the 176B parameters multilingual BLOOM model in full open access
June 21, 2022 – Data gathering, governance, and disposition of an AI model as a public resource for multiple jurisdictions [PDF]
June 9, 2022 – Formalizing BigScience core values
June 9, 2022 – Collecting and annotating more than 200 Arabic NLP datasets
May 20, 2022 – Developing a Responsible AI License ("RAIL") for the use the BigScience LLM
March 15, 2022 – Lancement de l’entrainement du modèle multilingue de BigScience
March 15, 2022 – Kicking off the BigScience Large Language Model training
March 15, 2022 – Training a massive-scale language model
March 15, 2022 – Developing a 350 billion token (1.5 TB of text data) multilingual dataset
March 14, 2022 – Deciding on the final model size, shape, and pretraining duration
December 20, 2021 – Using T0 for cooking recommendation and answering world knowledge.