TRL

trl-lib's activity

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

qgallouedec 

updated a dataset about 18 hours ago

trl-lib/documentation-images

Viewer • Updated about 18 hours ago • 1 • 15.5k

lvwerra 

authored a paper 3 days ago

Towards Best Practices for Open Datasets for LLM Training

Paper • 2501.08365 • Published 5 days ago • 41

qgallouedec 

updated 5 datasets 11 days ago

trl-lib/rlaif-v

Viewer • Updated 11 days ago • 83.1k • 131 • 3

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

Viewer • Updated 11 days ago • 16.6k • 214

trl-lib/ultrafeedback-prompt

Viewer • Updated 11 days ago • 39.8k • 608 • 3

trl-lib/tldr-preference

Viewer • Updated 11 days ago • 179k • 223

trl-lib/tldr

Viewer • Updated 11 days ago • 130k • 798

qgallouedec 

updated 5 collections 11 days ago

Unpaired preference datasets

Collection

2 items • Updated 11 days ago

Prompt-completion datasets

Collection

1 item • Updated 11 days ago

Stepwise supervision datasets

Collection

2 items • Updated 11 days ago

Prompt-only datasets

Collection

1 item • Updated 11 days ago

Preference datasets

Collection

6 items • Updated 11 days ago

qgallouedec 

updated 2 datasets 11 days ago

trl-lib/prm800k

Viewer • Updated 11 days ago • 41.2k • 139 • 1

trl-lib/math_shepherd

Viewer • Updated 11 days ago • 445k • 542 • 1

qgallouedec 

updated a collection 11 days ago

Preference datasets

Collection

6 items • Updated 11 days ago

qgallouedec 

updated a dataset 11 days ago

trl-lib/lm-human-preferences-sentiment

Viewer • Updated 11 days ago • 6.26k • 42