TRL

trl-lib's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts

qgallouedec 

updated 5 datasets 3 days ago

trl-lib/rlaif-v

Viewer • Updated 3 days ago • 83.1k • 143 • 3

trl-lib/ultrafeedback-gpt-3.5-turbo-helpfulness

Viewer • Updated 3 days ago • 16.6k • 117

trl-lib/ultrafeedback-prompt

Viewer • Updated 3 days ago • 39.8k • 627 • 3

trl-lib/tldr-preference

Viewer • Updated 3 days ago • 179k • 258

trl-lib/tldr

Viewer • Updated 3 days ago • 130k • 492

qgallouedec 

updated 5 collections 3 days ago

Unpaired preference datasets

Collection

2 items • Updated 3 days ago

Prompt-completion datasets

Collection

1 item • Updated 3 days ago

Stepwise supervision datasets

Collection

2 items • Updated 3 days ago

Prompt-only datasets

Collection

1 item • Updated 3 days ago

Preference datasets

Collection

6 items • Updated 3 days ago

qgallouedec 

updated 2 datasets 3 days ago

trl-lib/prm800k

Viewer • Updated 3 days ago • 41.2k • 116 • 1

trl-lib/math_shepherd

Viewer • Updated 3 days ago • 445k • 345 • 1

qgallouedec 

updated a collection 3 days ago

Preference datasets

Collection

6 items • Updated 3 days ago

qgallouedec 

updated 3 datasets 3 days ago

trl-lib/lm-human-preferences-sentiment

Viewer • Updated 3 days ago • 6.26k • 29

trl-lib/lm-human-preferences-descriptiveness

Viewer • Updated 3 days ago • 6.26k • 32 • 1

trl-lib/hh-rlhf-helpful-base

Viewer • Updated 3 days ago • 46.2k • 63