AI & ML interests
Reinforcement Learning
Organizations
kaiwenw/open_r1_apr9_round1_combined_balanced
Viewer • Updated • 49.4k • 14
kaiwenw/open_r1_apr9_round1_combined_random
Viewer • Updated • 49.4k • 3
kaiwenw/open_r1_apr9_DeepSeek_R1_Distill_Qwen_32B_tokenized
Viewer • Updated • 49.4k • 31
kaiwenw/open_r1_apr9_DeepSeek_R1_Distill_Qwen_14B_tokenized
Viewer • Updated • 49.4k • 12
kaiwenw/open_r1_apr9_DeepSeek_R1_Distill_Qwen_7B_tokenized
Viewer • Updated • 49.4k • 242
kaiwenw/open_r1_apr9_DeepSeek_R1_Distill_Qwen_1.5B_tokenized
Viewer • Updated • 49.4k • 138
Viewer • Updated • 49.4k • 17
kaiwenw/combine_1.5B_7B_and_32B
Viewer • Updated • 49.5k • 12
kaiwenw/combine_1.5B_and_blockwise
Viewer • Updated • 49.5k • 15
kaiwenw/open_r1_mar2_DeepSeek_R1_Distill_Qwen_1.5B_tokenized
Viewer • Updated • 49.5k • 18
kaiwenw/open_r1_mar2_DeepSeek_R1_Distill_Qwen_32B_tokenized
Viewer • Updated • 49.5k • 26
kaiwenw/open_r1_mar2_mar20_1.5b_n_4_nl_8_tokenized
Viewer • Updated • 49.5k • 14
kaiwenw/open_r1_mar2_DeepSeek_R1_Distill_Qwen_7B_tokenized
Viewer • Updated • 49.5k • 35
kaiwenw/open_r1_mar2_round_1_tokenized
Viewer • Updated • 49.5k • 3
kaiwenw/open_r1_mar2_round_1
Viewer • Updated • 45.3k • 8
Viewer • Updated • 49.5k • 30
Viewer • Updated • 58.1k • 3
Viewer • Updated • 1k • 7
kaiwenw/aft_after_jaft_test
Viewer • Updated • 1.41k • 3
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_75_chosen_25_reject
Viewer • Updated • 14.1k • 14
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_25_chosen_75_reject
Viewer • Updated • 18.6k • 10
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_50_chosen_50_reject
Viewer • Updated • 37.9k • 5
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_all_reject_first
Viewer • Updated • 26.7k • 4
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_all_chosen_first
Viewer • Updated • 20.1k • 5
kaiwenw/dec9_sp1_repeat_5_pref_jdpo
Viewer • Updated • 44.5k • 11
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_n_7_temp_0.9
Viewer • Updated • 36.4k • 8
kaiwenw/dec9_sp1_repeat_5
Viewer • Updated • 18.2k • 5
kaiwenw/dec9_sp1_pref_jdpo_75_chosen_25_reject
Viewer • Updated • 2.39k • 5
kaiwenw/dec9_sp1_pref_jdpo_25_chosen_75_reject
Viewer • Updated • 3.39k • 7
kaiwenw/dec9_sp1_pref_jdpo_50_chosen_50_reject
Viewer • Updated • 6.4k • 6