 | Monter d'un niveau |
Kaddour, J., Key, O., Nawrot, P., Minervini, P., & Kusner, M. J. (décembre 2023). No train no gain: revisiting efficient training algorithms for transformer-based language models [Communication écrite]. 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, LA, USA. Lien externe
