Kaiwen Wang's picture

7 2

Kaiwen Wang

kaiwenw

·

https://kaiwenw.github.io/

AI & ML interests

Reinforcement Learning

Organizations

kaiwenw 's datasets 220

kaiwenw/open_r1_apr9_round1_combined_balanced

Viewer • Updated Apr 14 • 49.4k • 6

kaiwenw/open_r1_apr9_round1_combined_random

Viewer • Updated Apr 14 • 49.4k • 12

kaiwenw/open_r1_apr9_DeepSeek_R1_Distill_Qwen_32B_tokenized

Viewer • Updated Apr 13 • 49.4k • 13

kaiwenw/open_r1_apr9_DeepSeek_R1_Distill_Qwen_14B_tokenized

Viewer • Updated Apr 11 • 49.4k • 10

kaiwenw/open_r1_apr9_DeepSeek_R1_Distill_Qwen_7B_tokenized

Viewer • Updated Apr 11 • 49.4k • 12

kaiwenw/open_r1_apr9_DeepSeek_R1_Distill_Qwen_1.5B_tokenized

Viewer • Updated Apr 11 • 49.4k • 12

kaiwenw/open_r1_apr9

Viewer • Updated Apr 9 • 49.4k • 8

kaiwenw/combine_1.5B_7B_and_32B

Viewer • Updated Apr 4 • 49.5k • 34

kaiwenw/combine_1.5B_and_blockwise

Viewer • Updated Apr 4 • 49.5k • 20

kaiwenw/open_r1_mar2_DeepSeek_R1_Distill_Qwen_1.5B_tokenized

Viewer • Updated Apr 4 • 49.5k • 28

kaiwenw/open_r1_mar2_DeepSeek_R1_Distill_Qwen_32B_tokenized

Viewer • Updated Apr 3 • 49.5k • 17

kaiwenw/open_r1_mar2_mar20_1.5b_n_4_nl_8_tokenized

Viewer • Updated Apr 3 • 49.5k • 12

kaiwenw/open_r1_mar2_DeepSeek_R1_Distill_Qwen_7B_tokenized

Viewer • Updated Mar 30 • 49.5k • 21

kaiwenw/open_r1_mar2_round_1_tokenized

Viewer • Updated Mar 4 • 49.5k • 22

kaiwenw/open_r1_mar2_round_1

Viewer • Updated Mar 3 • 45.3k • 24

kaiwenw/open_r1_mar2

Viewer • Updated Mar 2 • 49.5k • 4

kaiwenw/verified_open_r1

Viewer • Updated Feb 20 • 58.1k • 4

kaiwenw/test_open_r1

Viewer • Updated Feb 20 • 1k • 1

kaiwenw/aft_after_jaft_test

Viewer • Updated Jan 13 • 1.41k • 4

kaiwenw/dec9_sp1_repeat_5_pref_jdpo_75_chosen_25_reject

Viewer • Updated Dec 10, 2024 • 14.1k • 3

kaiwenw/dec9_sp1_repeat_5_pref_jdpo_25_chosen_75_reject

Viewer • Updated Dec 10, 2024 • 18.6k • 3

kaiwenw/dec9_sp1_repeat_5_pref_jdpo_50_chosen_50_reject

Viewer • Updated Dec 10, 2024 • 37.9k • 5

kaiwenw/dec9_sp1_repeat_5_pref_jdpo_all_reject_first

Viewer • Updated Dec 10, 2024 • 26.7k • 1

kaiwenw/dec9_sp1_repeat_5_pref_jdpo_all_chosen_first

Viewer • Updated Dec 10, 2024 • 20.1k • 3

kaiwenw/dec9_sp1_repeat_5_pref_jdpo

Viewer • Updated Dec 10, 2024 • 44.5k • 1

kaiwenw/dec9_sp1_repeat_5_pref_jdpo_n_7_temp_0.9

Viewer • Updated Dec 10, 2024 • 36.4k • 1

kaiwenw/dec9_sp1_repeat_5

Viewer • Updated Dec 9, 2024 • 18.2k • 5

kaiwenw/dec9_sp1_pref_jdpo_75_chosen_25_reject

Viewer • Updated Dec 9, 2024 • 2.39k • 2

kaiwenw/dec9_sp1_pref_jdpo_25_chosen_75_reject

Viewer • Updated Dec 9, 2024 • 3.39k • 2

kaiwenw/dec9_sp1_pref_jdpo_50_chosen_50_reject

Viewer • Updated Dec 9, 2024 • 6.4k • 1