Pietro Lesci

pietrolesci

AI & ML interests

I like developing and applying causal methods to study the effect of training choices on models’ behaviour, including memorisation, shortcut learning, and tokenisation.

Recent Activity

updated a dataset about 15 hours ago
pietrolesci/pile-deduped-pythia-preshuffled
updated a dataset about 16 hours ago
pietrolesci/pile-deduped-pythia-preshuffled
updated a dataset about 17 hours ago
pietrolesci/pile-deduped-pythia-preshuffled
View all activity

Organizations

EleutherAI's profile picture MilaNLP's profile picture Social Post Explorers's profile picture Training Dynamics's profile picture Hugging Face Discord Community's profile picture

pietrolesci's activity