Mixed and Merged models for "On The Limits of Model Merging for Multilinguality in Pre-Training". Repository here: https://github.com/Sethjsa/PT-MERGE
Seth Aycock
sethjsa
AI & ML interests
NLP
Organizations
None yet
datasets 43
sethjsa/wmt24-all_r_r-prefs
Viewer • Updated • 5.45k • 127
sethjsa/wmt24-all_m_w-prefs
Viewer • Updated • 5.48k • 612
sethjsa/wmt24-all_nb_m-prefs
Viewer • Updated • 5.45k • 25
sethjsa/wmt24-all_nb_b-prefs
Viewer • Updated • 5.44k • 131
sethjsa/wmt24-all_b_r-prefs
Viewer • Updated • 5.45k • 416
sethjsa/wmt24-all_b_nb-prefs
Viewer • Updated • 5.44k • 24
sethjsa/wmt24-all_b_m-prefs
Viewer • Updated • 5.48k • 24
sethjsa/wmt24-all_b_w-prefs
Viewer • Updated • 5.47k • 33
sethjsa/wmt24-COMET-22_bw_prefs
Updated • 15
sethjsa/wmt24-MetaMetrics-mt_bw_prefs
Viewer • Updated • 5.5k • 17