Schu

Eehan

2

·

AI & ML interests

None yet

Recent Activity

upvoted an article 5 days ago

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

upvoted a paper about 1 year ago

Doubly Robust Alignment for Large Language Models

updated a model over 1 year ago

Eehan/Qwen2.5-1.5B-drdrpo-hh-754

View all activity

Organizations

Eehan 's datasets 23

Eehan/eval-tldr-others

Viewer • Updated Jul 30, 2025 • 43k • 10

Eehan/eval-tldr

Viewer • Updated Jul 30, 2025 • 15k • 19

Eehan/eval-hh-all

Viewer • Updated Jul 29, 2025 • 11.8k • 25

Eehan/eval-hh-flipped

Viewer • Updated Jul 28, 2025 • 11.8k • 17

Eehan/train_data_helpful

Viewer • Updated Jul 28, 2025 • 46.2k • 12

Eehan/train_data_tldr

Viewer • Updated Jul 28, 2025 • 101k • 4

Eehan/train_data_helpful_flipped-10

Viewer • Updated Jul 28, 2025 • 46.2k • 13

Eehan/train_data_tldr_flipped-10

Viewer • Updated Jul 28, 2025 • 101k • 16

Eehan/train_data_helpful_flipped-20

Viewer • Updated Jul 28, 2025 • 46.2k • 6

Eehan/train_data_tldr_flipped-20

Viewer • Updated Jul 28, 2025 • 101k • 22

Eehan/eval-hh

Viewer • Updated May 16, 2025 • 11.8k • 16

Eehan/eval-hh-temp1only

Viewer • Updated May 13, 2025 • 2.35k • 13

Eehan/eval-tldr-dpo-ppo-drpo-dm-sft-1000-cut2

Viewer • Updated Apr 26, 2025 • 5k • 7

Eehan/eval-tldr-dpo-ppo-drpo-dm-sft-1000-cut

Viewer • Updated Apr 24, 2025 • 5k • 4

Eehan/eval-tldr-dpo-ppo-drpo-dm-sft-1000

Viewer • Updated Apr 24, 2025 • 5k • 15

Eehan/eval-tldr-dpo-drpo-0.75tmp-sft-ppo-1000

Viewer • Updated Apr 24, 2025 • 15k • 8

Eehan/eval-13-checkpoints-0414_2137

Viewer • Updated Apr 14, 2025 • 4k • 1

Eehan/eval-tldr-dpo-drpo-0.9tmp-sft-1000

Viewer • Updated Apr 12, 2025 • 3k • 8

Eehan/eval-imdb-0408-1000

Viewer • Updated Apr 8, 2025 • 3k • 5

Eehan/eval-imdb-drpo-sft-dpo-5000

Viewer • Updated Apr 4, 2025 • 10k • 9

Eehan/eval-imdb-drpo-134567-dpo-5000

Viewer • Updated Apr 3, 2025 • 25k • 5

Eehan/eval-imdb-drpo-1-3-4-dpo-1000

Viewer • Updated Mar 30, 2025 • 5k • 12

Eehan/eval-imdb-drpo-3-drpo-4-1000

Viewer • Updated Mar 30, 2025 • 1k • 12