Faeze Brahman

faezeb's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a dataset 1 day ago

ai2-adapt-dev/real_political_prompts_all

Viewer • Updated 1 day ago • 636k • 63

updated a dataset 7 days ago

ai2-adapt-dev/personahub_personas

Viewer • Updated 7 days ago • 243k • 52

updated 3 models 29 days ago

allenai/Llama-3.1-Tulu-3-8B-DPO

Text Generation • Updated 23 days ago • 11.4k • 15

allenai/Llama-3.1-Tulu-3-70B-SFT

Text Generation • Updated 23 days ago • 2.28k • 4

allenai/Llama-3.1-Tulu-3-8B-SFT

Text Generation • Updated 29 days ago • 10.8k • 16

liked a dataset 29 days ago

allenai/tulu-3-sft-mixture

Viewer • Updated 23 days ago • 939k • 6.81k • 88

updated 2 models 29 days ago

allenai/Llama-3.1-Tulu-3-8B

Text Generation • Updated 29 days ago • 11.8k • 108

allenai/Llama-3.1-Tulu-3-70B

Text Generation • Updated 29 days ago • 3k • 44

updated a dataset 30 days ago

allenai/tulu-3-sft-olmo-2-mixture

Viewer • Updated 23 days ago • 939k • 571 • 5

authored a paper 30 days ago

TÜLU 3: Pushing Frontiers in Open Language Model Post-Training

Paper • 2411.15124 • Published Nov 22 • 56

updated 9 datasets about 1 month ago

allenai/tulu-3-ultrafeedback-cleaned-on-policy-70b

Viewer • Updated Nov 21 • 41.6k • 93

allenai/tulu-3-wildchat-if-on-policy-8b

Viewer • Updated Nov 21 • 10.8k • 115

allenai/tulu-3-sft-personas-instruction-following

Viewer • Updated Nov 21 • 30k • 701 • 15

allenai/tulu-3-sft-personas-math

Viewer • Updated 23 days ago • 150k • 495 • 9

allenai/tulu-3-sft-personas-math-grade

Viewer • Updated Nov 21 • 50k • 298 • 6

allenai/tulu-3-wildchat-ultrafeedback

Viewer • Updated Nov 21 • 139k • 162

allenai/tulu-3-sft-personas-algebra

Viewer • Updated 23 days ago • 20k • 327 • 4

allenai/tulu-3-pref-personas-instruction-following

Viewer • Updated Nov 21 • 19.9k • 180 • 6

allenai/tulu-3-sft-mixture

Viewer • Updated 23 days ago • 939k • 6.81k • 88

updated a collection about 1 month ago

Tulu 3 Datasets

Collection

All datasets released with Tulu 3 -- state of the art open post-training recipes. • 32 items • Updated 28 days ago • 62