arxiv:2407.15762
Kaiwen Wang
kaiwenw
AI & ML interests
Reinforcement Learning
Recent Activity
updated
a dataset
3 days ago
kaiwenw/verified_open_r1
updated
a dataset
3 days ago
kaiwenw/test_open_r1
published
a dataset
3 days ago
kaiwenw/test_open_r1
Organizations
None yet
Papers
3
models
7
kaiwenw/nov11_oasst_aft_llama_lr_3e-5_rerun
Text Generation
•
Updated
•
13
kaiwenw/nov22_lr_3e-6_lora_32_dropout_0.1_all_reject_first_ep_4
Text Generation
•
Updated
•
6
kaiwenw/nov22_lr_3e-6_lora_32_dropout_0.1_all_reject_first_ep_3
Text Generation
•
Updated
•
9
kaiwenw/nov22_lr_3e-6_lora_32_dropout_0.1_all_reject_first_ep_2
Text Generation
•
Updated
•
5
kaiwenw/nov22_lr_3e-6_lora_32_dropout_0.1_all_reject_first_ep_1
Text Generation
•
Updated
•
5
kaiwenw/nov2_oasst_aft_llama_lr_3e-5
Text Generation
•
Updated
•
8
kaiwenw/oct31_oasst_llama70b_jft
Text Generation
•
Updated
•
7
datasets
84
kaiwenw/verified_open_r1
Viewer
•
Updated
•
58.1k
•
105
kaiwenw/test_open_r1
Viewer
•
Updated
•
1k
•
48
kaiwenw/aft_after_jaft_test
Viewer
•
Updated
•
1.41k
•
59
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_75_chosen_25_reject
Viewer
•
Updated
•
14.1k
•
66
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_25_chosen_75_reject
Viewer
•
Updated
•
18.6k
•
53
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_50_chosen_50_reject
Viewer
•
Updated
•
37.9k
•
55
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_all_reject_first
Viewer
•
Updated
•
26.7k
•
46
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_all_chosen_first
Viewer
•
Updated
•
20.1k
•
38
kaiwenw/dec9_sp1_repeat_5_pref_jdpo
Viewer
•
Updated
•
44.5k
•
50
kaiwenw/dec9_sp1_repeat_5_pref_jdpo_n_7_temp_0.9
Viewer
•
Updated
•
36.4k
•
73