s's picture

s

august66

·

AI & ML interests

None yet

Recent Activity

updated a dataset about 2 hours ago

august66/drpo_hh_qwen2.5_1.5b_with_ref_prob_sampled

published a dataset about 15 hours ago

august66/drpo_hh_qwen2.5_1.5b_with_ref_prob_sampled

updated a model 2 days ago

august66/hh_qwen1.5_drpo

View all activity

Organizations

august66 's datasets 27

august66/drpo_hh_qwen2.5_1.5b_with_ref_prob_sampled

Updated about 2 hours ago • 6

august66/drpo_hh_qwen2.5_1.5b_with_ref_btpref

Viewer • Updated Oct 8, 2025 • 48.8k • 191

august66/hh_qwen2.5_1.5b_with_bias_bt_pref

Viewer • Updated Oct 2, 2025 • 18k • 2

august66/hh_qwen2.5_1.5b_with_bias

Viewer • Updated Sep 27, 2025 • 18k • 27

august66/drpo_hh_qwen2.5_1.5b

Viewer • Updated Sep 8, 2025 • 43.8k • 3

august66/dpo_reward_dist_pi_theta_prompt_3

Viewer • Updated Sep 3, 2025 • 5k • 1

august66/dpo_reward_dist_pi_theta_prompt_2

Viewer • Updated Sep 3, 2025 • 5k • 1

august66/dpo_reward_dist_pi_theta

Viewer • Updated Aug 23, 2025 • 5k • 1

august66/reward_distribution_2_tldr_openassist_pi_ref

Viewer • Updated Aug 4, 2025 • 5k • 5

august66/reward_distribution_2_tldr_openassist_pi_theta

Viewer • Updated Aug 4, 2025 • 5k • 13

august66/reward_distribution_tldr_openassist_pi_theta

Viewer • Updated Jul 30, 2025 • 5k • 14

august66/reward_distribution_tldr_openassist_pi_ref

Viewer • Updated Jul 30, 2025 • 5k • 16

august66/drpo_ultrafeedback_qwen2.5-1.5b_first_iter_20k

Viewer • Updated Jul 8, 2025 • 20k

august66/drpo_ultrafeedback_qwen2.5-1.5b-7

Viewer • Updated Jul 8, 2025 • 2.5k • 2

august66/drpo_ultrafeedback_qwen2.5-1.5b-6

Viewer • Updated Jul 8, 2025 • 2.5k • 1

august66/drpo_ultrafeedback_qwen2.5-1.5b-5

Viewer • Updated Jul 8, 2025 • 1.5k • 1

august66/drpo_ultrafeedback_qwen2.5-1.5b-4

Viewer • Updated Jul 8, 2025 • 1k • 1

august66/drpo_ultrafeedback_qwen2.5-1.5b-3

Viewer • Updated Jul 8, 2025 • 2.5k • 1

august66/drpo_ultrafeedback_qwen2.5-1.5b-2

Viewer • Updated Jul 7, 2025 • 5k • 1

august66/drpo_ultrafeedback_qwen2.5-1.5b-1

Viewer • Updated Jul 7, 2025 • 5k • 1

august66/drpo_ultrafeedback_qwen2.5-1.5b

Viewer • Updated Jul 7, 2025 • 30 • 1

august66/DRPO_data_from_ultrafeed_new_template

Viewer • Updated Jun 29, 2025 • 64k • 1

august66/DRPO_data_from_ultrafeed

Viewer • Updated Jun 24, 2025 • 64k • 1

august66/DRPO_first_iter_completion_label_test

Viewer • Updated Jun 16, 2025 • 200 • 1

august66/DRPO_first_iter

Viewer • Updated Jun 16, 2025 • 20k • 1

august66/dpo_train_data

Viewer • Updated Jun 3, 2025 • 25k • 1

august66/reward_data_for_dpo_train

Viewer • Updated Jun 2, 2025 • 25k • 1