Columbia-NLP/DPO-Nectar
Viewer • Updated • 183k • 25
LION-datasets
Datasets used to train the LION pipeline. Paper: https://arxiv.org/abs/2407.06542; Code: https://github.com/Columbia-NLP-Lab/LionAlignment
-
-
Columbia-NLP/DPO-distilabel-capybara-dpo-7k-binarized
Viewer • Updated • 7.56k • 43 -
Columbia-NLP/DPO-distilabel-intel-orca-dpo-pairs_cleaned
Viewer • Updated • 12.8k • 14 -
Columbia-NLP/DPO-UltraFeedback_binarized
Viewer • Updated • 62.7k • 46 -
Columbia-NLP/DPO-py-dpo-v0.1
Viewer • Updated • 9.47k • 27 -
Columbia-NLP/DPO-tldr-summarisation-preferences
Viewer • Updated • 177k • 153 • 1 -
Columbia-NLP/DPO-HelpSteer
Viewer • Updated • 9.17k • 37 -
Columbia-NLP/DPO-PKU-SafeRLHF
Viewer • Updated • 136k • 24 • 2 -
Columbia-NLP/DPO-hh-rlhf
Viewer • Updated • 169k • 96