Kaiwen Wang's picture

1

Kaiwen Wang

kaiwenw

·

https://kaiwenw.github.io/

AI & ML interests

Reinforcement Learning

Recent Activity

updated a dataset about 12 hours ago

kaiwenw/distill-r1-qwen-1.5b-hmmt-feb-25-4096-with-bt-model-with-sigmoid

updated a dataset about 12 hours ago

kaiwenw/distill-r1-qwen-1.5b-hmmt-feb-24-4096-with-bt-model-with-sigmoid

published a dataset about 12 hours ago

kaiwenw/distill-r1-qwen-1.5b-hmmt-feb-25-4096-with-bt-model-with-sigmoid

View all activity

Organizations

None yet

Papers 3

arxiv:2407.15762

arxiv:2403.05385

arxiv:2302.03201

models 9

kaiwenw/test_bt-step-20

Updated 1 day ago

kaiwenw/test_bt-step-10

Updated 1 day ago

kaiwenw/nov11_oasst_aft_llama_lr_3e-5_rerun

Text Generation • Updated Dec 9, 2024

kaiwenw/nov22_lr_3e-6_lora_32_dropout_0.1_all_reject_first_ep_4

Text Generation • Updated Dec 7, 2024 • 1

kaiwenw/nov22_lr_3e-6_lora_32_dropout_0.1_all_reject_first_ep_3

Text Generation • Updated Dec 7, 2024

kaiwenw/nov22_lr_3e-6_lora_32_dropout_0.1_all_reject_first_ep_2

Text Generation • Updated Dec 7, 2024

kaiwenw/nov22_lr_3e-6_lora_32_dropout_0.1_all_reject_first_ep_1

Text Generation • Updated Dec 7, 2024

kaiwenw/nov2_oasst_aft_llama_lr_3e-5

Text Generation • Updated Nov 8, 2024 • 2

kaiwenw/oct31_oasst_llama70b_jft

Text Generation • Updated Nov 6, 2024 • 2

datasets 220

kaiwenw/distill-r1-qwen-1.5b-hmmt-feb-25-4096-with-bt-model-with-sigmoid

Viewer • Updated about 12 hours ago • 123k

kaiwenw/distill-r1-qwen-1.5b-hmmt-feb-24-4096-with-bt-model-with-sigmoid

Viewer • Updated about 12 hours ago • 123k

kaiwenw/distill-r1-qwen-1.5b-aime-25-4096-with-bt-model-with-sigmoid

Viewer • Updated about 13 hours ago • 123k

kaiwenw/distill-r1-qwen-1.5b-aime-24-4096-with-bt-model-with-sigmoid

Viewer • Updated about 13 hours ago • 123k

kaiwenw/distill-r1-qwen-1.5b-hmmt-feb-25-4096-with-bt-model-wout-sigmoid

Viewer • Updated about 13 hours ago • 123k

kaiwenw/distill-r1-qwen-1.5b-hmmt-feb-24-4096-with-bt-model-wout-sigmoid

Viewer • Updated about 14 hours ago • 123k

kaiwenw/distill-r1-qwen-1.5b-aime-25-4096-with-bt-model-wout-sigmoid

Viewer • Updated about 15 hours ago • 123k

kaiwenw/distill-r1-qwen-1.5b-aime-24-4096-with-bt-model-wout-sigmoid

Viewer • Updated about 16 hours ago • 123k

kaiwenw/distill-r1-qwen-1.5b-hmmt-feb-25-4096-with-old-prm-indices_61440_69120

Viewer • Updated 1 day ago • 7.68k • 4

kaiwenw/distill-r1-qwen-1.5b-hmmt-feb-25-4096-with-old-prm-indices_76800_84480

Viewer • Updated 1 day ago • 7.68k • 5