r-three

community

r-three

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

gsaltintas updated a dataset about 4 hours ago

r-three/tokenizer_training

gsaltintas authored a paper 4 days ago

The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions

craffel authored a paper about 1 month ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

View all activity

models 8

r-three/P3_AverageActivation

Updated Mar 19, 2024

r-three/FLAN_AverageActivation

Updated Mar 19, 2024

r-three/P3_Retrieval

Updated Feb 10, 2024

r-three/FLAN_Retrieval

Updated Feb 9, 2024

r-three/P3_MergedExperts

Updated Feb 8, 2024

r-three/FLAN_MergedExperts

Updated Feb 8, 2024

r-three/P3_Phatgoose

Updated Feb 8, 2024 • 1

r-three/FLAN_Phatgoose

Updated Feb 8, 2024 • 2

datasets 11

r-three/tokenizer_training

Viewer • Updated about 4 hours ago • 95.9M • 306

r-three/tokenizer_training_4_chunks

Viewer • Updated 6 days ago • 40k • 9

r-three/tokenization_robustness

Viewer • Updated about 1 month ago • 883 • 419

r-three/tiny-xquad

Viewer • Updated May 8 • 1.43k • 22

r-three/tiny-mlqa

Viewer • Updated May 8 • 78.1k • 89

r-three/tiny-mgsm

Viewer • Updated May 8 • 1.19k • 20

r-three/tiny-belebele

Viewer • Updated May 7 • 12.2k • 52

r-three/tiny-m-hellaswag

Viewer • Updated May 7 • 30.3k • 4

r-three/Phatgoose_storycloze_offline

Preview • Updated Apr 16, 2024 • 5

r-three/Phatgoose_flanv2_offline

Viewer • Updated Apr 16, 2024 • 1.7M • 26

View 11 datasets