Pietro Lesci

pietrolesci's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 3 days ago

EU20-Benchmarks

Collection

Evaluation Benchmarks for 20 European languages. • 5 items • Updated Oct 11, 2024 • 9

updated a collection 7 days ago

Tokenisation-Bias

Collection

21 items • Updated 7 days ago

updated a dataset 7 days ago

pietrolesci/me-minipile-evals

Viewer • Updated 7 days ago • 1.22M • 209

published a dataset 7 days ago

pietrolesci/me-minipile-evals

Viewer • Updated 7 days ago • 1.22M • 209

updated a collection 20 days ago

Tokenisation-Bias

Collection

21 items • Updated 7 days ago

updated a dataset about 1 month ago

pietrolesci/pile-deduped

Viewer • Updated May 5 • 748M • 1.38k

updated a collection about 2 months ago

The Pile Companion

Collection

4 items • Updated Apr 21

updated a dataset about 2 months ago

InfoTokenizers/finewebedu-20B

Viewer • Updated about 17 hours ago • 162M • 828

updated 10 datasets 2 months ago

pietrolesci/pythia-deduped-memorisation-profiles

Viewer • Updated Apr 9 • 2.13M • 57

pietrolesci/pile-validation

Viewer • Updated Apr 9 • 429k • 251

pietrolesci/pile-deduped-subset

Viewer • Updated Apr 9 • 16.3k • 30

pietrolesci/pythia-deduped-stats

Viewer • Updated Apr 9 • 16.3M • 60

pietrolesci/pythia-deduped-stats-raw

Viewer • Updated Apr 9 • 14.9M • 1.27k

pietrolesci/agnews

Viewer • Updated Apr 9 • 510k • 36

pietrolesci/amazoncat-13k

Viewer • Updated Apr 9 • 5.99M • 170 • 1

pietrolesci/wikitoxic

Viewer • Updated Apr 9 • 894k • 106 • 1

pietrolesci/multiwoz_all_versions

Viewer • Updated Apr 9 • 82k • 34 • 1

pietrolesci/anchoral-paper-artefacts

Viewer • Updated Apr 9 • 2.78M • 32

authored a paper 2 months ago

PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs

Paper • 2503.09543 • Published Mar 12