AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojiepropallprefix Viewer • Updated Apr 27 • 130k • 3
AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojieallprefix Viewer • Updated Apr 27 • 130k • 2
AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_trained_allprefix Viewer • Updated Apr 27 • 300 • 1
AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_trained Viewer • Updated Apr 27 • 300 • 1
AdversarialRLHF/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1706381144_allprefix Viewer • Updated Apr 27 • 130k • 2
AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojieboth Viewer • Updated Apr 26 • 130k • 2
AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojieprefix Viewer • Updated Apr 26 • 130k • 1
AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojiesuffix Viewer • Updated Apr 26 • 130k • 3
AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_3emojieprefix_randomize Viewer • Updated Apr 24 • 130k • 2
AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_relabel_pythia6.9b_logprobs Viewer • Updated Apr 24 • 130k • 3
AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_relabel_pythia6.9b Viewer • Updated Apr 23 • 130k • 2
AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_relabel_pythia6.9b_3emojieprefix_chosen Viewer • Updated Apr 22 • 177k • 3
AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft Viewer • Updated Apr 22 • 130k • 3