This collection contains the pre-trained, fine-tuned and aligned models for the Direct Preference Heads paper.
-
Avelina/lovelace-medium-alpha1
Text Generation • 0.6B • Updated • 6 • 1 -
Avelina/lovelace-medium-alpha1-sft
Text Generation • 0.6B • Updated • 5 -
Avelina/lovelace-medium-alpha1-dph
0.6B • Updated • 4 • 1 -
Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads
Paper • 2405.20053 • Published • 2