Risultati della ricerca - Tissue, Howe

Scaling Law with Learning Rate Annealing di Tissue, Howe, Wang, Venus, Wang, Lu

Testo

Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training di Zhang, Mozhi, Tissue, Howe, Wang, Lu, Qiu, Xipeng

Testo

Learning Dynamics in Continual Pre-Training for Large Language Models di Wang, Xingjin, Tissue, Howe, Wang, Lu, Li, Linjing, Zeng, Daniel Dajun

Testo