Pietro Lesci

pietrolesci

https://pietrolesci.github.io/

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.

Organizations

liked a dataset over 1 year ago

Zyphra/Zyda-2

Preview • Updated Aug 6, 2025 • 39.3k • 105

liked a Space over 1 year ago

The Ultra-Scale Playbook

🌌

4.1k

The ultimate guide to training LLM on large GPU Clusters

liked 2 models about 2 years ago

BEE-spoke-data/smol_llama-101M-GQA

Text Generation • 0.1B • Updated Dec 29, 2025 • 975 • 33

BEE-spoke-data/smol_llama-81M-tied

Text Generation • 81.3M • Updated Dec 29, 2025 • 108 • 10

liked a dataset almost 3 years ago

akjindal53244/Arithmo-Data

Viewer • Updated Jan 26, 2024 • 549k • 78 • 35

liked 2 datasets about 3 years ago

Muennighoff/natural-instructions

Updated Dec 23, 2022 • 6.1k • 87

JeanKaddour/minipile

Viewer • Updated Jun 20, 2023 • 1.01M • 2.44k • 155

liked 2 Spaces about 4 years ago

CodeFormer

🐼

2.44k

Enhance and restore faces in photos with optional upscaling

PromptSource

💩