A collection of chat models to explore the differences between three alignment techniques: DPO, IPO, and KTO.
AI & ML interests
None defined yet.
models
75
trl-lib/Qwen2-0.5B-Reward
Text Classification
•
Updated
•
252
trl-lib/pythia-1b-deduped-tldr-rm
Updated
•
1.69k
trl-lib/pythia-2.8b-deduped-tldr-online-dpo
Text Generation
•
Updated
•
1
trl-lib/pythia-6.9b-deduped-tldr-offline-dpo
Text Generation
•
Updated
•
2
trl-lib/pythia-2.8b-deduped-tldr-offline-dpo
Text Generation
•
Updated
•
2
trl-lib/pythia-1b-deduped-tldr-offline-dpo
Text Generation
•
Updated
•
1
trl-lib/pythia-6.9b-deduped-tldr-rm
Updated
•
72
trl-lib/pythia-6.9b-deduped-tldr-sft
Updated
•
142
trl-lib/pythia-2.8b-deduped-tldr-rm
Updated
•
82
trl-lib/pythia-2.8b-deduped-tldr-sft
Updated
•
185
datasets
14
trl-lib/Capybara-Preferences
Viewer
•
Updated
•
15.4k
trl-lib/Capybara
Viewer
•
Updated
•
16k
trl-lib/ultrafeedback-prompt
Viewer
•
Updated
•
39.8k
•
8
trl-lib/zen
Viewer
•
Updated
•
228
trl-lib/tldr
Viewer
•
Updated
•
130k
•
1.45k
trl-lib/ultrafeedback_binarized
Viewer
•
Updated
•
63.1k
•
2.03k
trl-lib/lm-human-preferences-sentiment
Viewer
•
Updated
•
6.26k
•
13
trl-lib/lm-human-preferences-descriptiveness
Viewer
•
Updated
•
6.26k
•
3
trl-lib/tldr-preference
Viewer
•
Updated
•
179k
•
3
trl-lib/ultrafeedback-gpt-3.5-turbo-helpfulness
Viewer
•
Updated
•
16.6k
•
2