allenai/tulu-3-sft-mixture
Viewer
•
Updated
•
939k
•
8
Tulu 3 Datasets
All datasets released with Tulu 3 -- state of the art open post-training recipes.
Note Our main SFT mixture.
allenai/llama-3.1-tulu-3-8b-preference-mixture
Preview • Updated • 1Note The full preference mixture used for DPO on our 8B SFT checkpoint.
allenai/llama-3.1-tulu-3-70b-preference-mixture
Viewer • Updated • 334k • 3 • 2Note The full preference mixture used for DPO on our 70B SFT checkpoint.
allenai/tulu-3-sft-personas-math
Viewer • Updated • 150kNote The rest from here are individual new SFT or preference datasets we created!
-
allenai/tulu-3-sft-personas-instruction-following
Viewer • Updated • 30k • 1 -
allenai/tulu-3-sft-personas-math-grade
Viewer • Updated • 50k • 34 -
allenai/tulu-3-sft-personas-algebra
Viewer • Updated • 20k -
allenai/tulu-3-sft-personas-code
Viewer • Updated • 35k -
allenai/coconot
Viewer • Updated • 13.8k • 248 • 4 -
allenai/wildjailbreak
Viewer • Updated • 2.21k • 1.02k • 23 -
allenai/tulu-3-hard-coded
Viewer • Updated • 240 • 6 • 1 -
allenai/tulu-3-pref-personas-instruction-following
Viewer • Updated • 19.9k -
allenai/tulu-3-wildchat-ultrafeedback
Viewer • Updated • 139k -
allenai/tulu-3-sft-prompts-ultrafeedback
Viewer • Updated • 267k -
allenai/tulu-3-sft-reused-off-policy
Viewer • Updated • 96.9k • 3 -
allenai/tulu-3-sft-reused-on-policy-8b
Viewer • Updated • 19.4k • 2 -
allenai/tulu-3-wildchat-if-on-policy-8b
Viewer • Updated • 10.8k • 2 -
allenai/tulu-3-IF-augmented-on-policy-8b
Viewer • Updated • 65.5k • 1 -
allenai/tulu-3-wildchat-reused-on-policy-8b
Viewer • Updated • 17.2k • 3 -
allenai/tulu-3-ultrafeedback-cleaned-on-policy-8b
Viewer • Updated • 41.6k • 1 -
allenai/tulu-3-sft-reused-on-policy-70b
Viewer • Updated • 19.5k • 2 -
allenai/tulu-3-wildchat-if-on-policy-70b
Viewer • Updated • 10.8k • 2 -
allenai/tulu-3-IF-augmented-on-policy-70b
Viewer • Updated • 65.6k • 1 -
allenai/tulu-3-wildchat-unused
Viewer • Updated • 82.8k • 2 -
allenai/tulu-3-wildchat-reused-on-policy-70b
Viewer • Updated • 17.2k • 2 -
allenai/tulu-3-ultrafeedback-cleaned-on-policy-70b
Preview • Updated -
allenai/RLVR-GSM-MATH-IF-Mixed-Constraints
Viewer • Updated • 29.9k • 1 -
allenai/RLVR-GSM
Viewer • Updated • 8.79k -
allenai/RLVR-MATH
Viewer • Updated • 7.5k -
allenai/RLVR-IFeval
Viewer • Updated • 15k -
allenai/wildguardmix
Viewer • Updated • 88.5k • 3.17k • 13