Kai Ye's picture

Open to Collab

3

Kai Ye

Kyleyee

·

https://noncollapse.github.io/

AI & ML interests

None yet

Recent Activity

updated a dataset about 17 hours ago

Kyleyee/READER_dataset

published a dataset about 17 hours ago

Kyleyee/READER_dataset

updated a dataset 3 days ago

Kyleyee/test_final

View all activity

Organizations

Kyleyee 's datasets 202

Kyleyee/train_data_imdb_for_drdpo_wrong_preference

Viewer • Updated Mar 21, 2025 • 26k • 4

Kyleyee/eval_data_imdb_with_estimate_preference

Viewer • Updated Mar 21, 2025 • 5k • 6

Kyleyee/eval_data_imdb_muti_temp_with_estimate_preference

Viewer • Updated Mar 21, 2025 • 5k • 7

Kyleyee/train_data_imdb_for_drdpo_with_dpo_preference

Viewer • Updated Mar 21, 2025 • 26k • 2

Kyleyee/eval_data_imdb

Viewer • Updated Mar 20, 2025 • 5k • 1

Kyleyee/train_data_imdb_for_drdpo_preference

Viewer • Updated Mar 20, 2025 • 26k • 6

Kyleyee/train_data_imdb_for_drdpo

Viewer • Updated Mar 20, 2025 • 100 • 6

Kyleyee/evaluate-dataset-HH

Viewer • Updated Mar 19, 2025 • 11.8k • 6

Kyleyee/eval_data_hh_dpo_hinge_multi_temp_reformed

Viewer • Updated Mar 19, 2025 • 11.8k • 5

Kyleyee/eval_data_hh_dpo_hinge_multi_temp

Viewer • Updated Mar 19, 2025 • 11.8k • 7

Kyleyee/eval_dataset_hh_beta0.1_multi_temp_reformed

Viewer • Updated Mar 19, 2025 • 11.8k • 1

Kyleyee/eval_dataset_hh_beta0.1_multi_temp

Viewer • Updated Mar 18, 2025 • 11.8k • 6

Kyleyee/eval_data_hh_sft_dpo_drdpo_beta0.1_multi_temp

Viewer • Updated Mar 18, 2025 • 11.8k • 6

Kyleyee/train_data_Helpful_drdpo

Viewer • Updated Mar 16, 2025 • 46.2k • 2

Kyleyee/train_data_hh_stf

Viewer • Updated Mar 16, 2025 • 46.2k • 4

Kyleyee/eval_data_tldr_sft_dpo_drdpo_beta0.1_multi_temp

Viewer • Updated Mar 15, 2025 • 43k • 2

Kyleyee/train_data_SFT_Helpful

Viewer • Updated Mar 15, 2025 • 46.2k • 2

Kyleyee/train_data_Helpful_explicit_prompt

Viewer • Updated Mar 15, 2025 • 46.2k • 3

Kyleyee/train_data_Helpful_implicit_prompt

Viewer • Updated Mar 15, 2025 • 46.2k • 2

Kyleyee/train_data_SFT_HH

Viewer • Updated Mar 15, 2025 • 169k • 3

Kyleyee/eval_data_tldr_sft_dpo_drdpo_beta0.5_multi_temp

Viewer • Updated Mar 15, 2025 • 43k • 2

Kyleyee/train_data_HH_sft_2

Viewer • Updated Mar 14, 2025 • 169k • 5

Kyleyee/train_data_HH_sft

Viewer • Updated Mar 14, 2025 • 169k • 2

Kyleyee/tldr_test_tiny_data_drpo

Viewer • Updated Mar 14, 2025 • 50 • 1

Kyleyee/train_data_HH_implicit_prompt

Viewer • Updated Mar 14, 2025 • 169k • 2

Kyleyee/train_data_HH_explicit_prompt

Viewer • Updated Mar 14, 2025 • 169k • 5

Kyleyee/train_data_tldr_SFT_dpo_drdpo_multi_temp

Viewer • Updated Mar 13, 2025 • 43k • 2

Kyleyee/train_data_tldr_drdpo_hinge_eval_multi_temp

Viewer • Updated Mar 12, 2025 • 43k • 1

Kyleyee/train_data_tldr_drdpo_hinge_eval_small_tem0

Viewer • Updated Mar 12, 2025 • 2.5k • 1

Kyleyee/train_data_tldr_eval_small_tem0

Viewer • Updated Mar 10, 2025 • 2.5k • 1