Alexandre Ramé
Home
Publications
Talks/Posts
Teaching
Books
WARM: On the Benefits of Weight Averaged Reward Models
**Alexandre Ramé**
,
Nino Vieillard
,
Léonard Hussenot
,
Robert Dadashi
,
Geoffrey Cideron
,
Olivier Bachem
,
Johan Ferret
29 January, 2024
WARM: On the Benefits of Weight Averaged Reward Models
**Alexandre Ramé**
,
Nino Vieillard
,
Léonard Hussenot
,
Robert Dadashi
,
Geoffrey Cideron
,
Olivier Bachem
,
Johan Ferret
29 January, 2024
Date
January, 2024
Links
PDF
Cite
Slides
Previous
Diverse and Efficient Ensembling of Deep Networks
Cite
×
