Dahoas/rm-static
Viewer • Updated • 81.4k • 1.2k • 124
Preference_datasets
datasets for preference tuning
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 28.4k • 1.8k -
Dahoas/full-hh-rlhf
Viewer • Updated • 125k • 689 • 88 -
yitingxie/rlhf-reward-datasets
Viewer • Updated • 81.4k • 65 • 65 -
stanfordnlp/SHP
Viewer • Updated • 386k • 3.13k • 322 -
argilla/ultrafeedback-binarized-preferences-cleaned-kto
Viewer • Updated • 231k • 7.34k • 10 -
argilla/ultrafeedback-binarized-preferences-cleaned
Viewer • Updated • 60.9k • 12.3k • 162 -
manishiitg/argilla-ultrafeedback-binarized-preferences-cleaned
Viewer • Updated • 43k • 15 -
PJMixers/argilla_ultrafeedback-binarized-preferences-cleaned-PreferenceShareGPT
Viewer • Updated • 60.9k • 16 • 1 -
AI4Chem/ChemPref-DPO-for-Chemistry-data-en
Viewer • Updated • 10.7k • 25 • 22 -
trl-lib/capybara-preferencces-7k
Viewer • Updated • 7.56k • 10 -
mlabonne/FineTome-100k
Viewer • Updated • 100k • 9.53k • 276 -
argilla/dpo-mix-7k
Viewer • Updated • 7.5k • 1.12k • 175 -
olivermolenschot/alpaca_messages_dpo_test
Viewer • Updated • 291 • 7 • 1 -
mlabonne/orpo-dpo-mix-40k
Viewer • Updated • 44.2k • 1.04k • 303 -
HumanLLMs/Human-Like-DPO-Dataset
Viewer • Updated • 10.9k • 551 • 257