Vincent Tu's picture

26 121

Vincent Tu

alckasoc

·

alckasoc

AI & ML interests

None yet

Recent Activity

upvoted a collection 18 days ago

upvoted an article about 2 months ago

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

upvoted a paper 2 months ago

The Unreasonable Effectiveness of Scaling Agents for Computer Use

View all activity

Organizations

alckasoc 's datasets 26

alckasoc/triviaqa_200_train

Viewer • Updated Jul 15 • 200 • 25

alckasoc/fever_200_train

Viewer • Updated Jul 15 • 200 • 19

alckasoc/ambignq_200_train

Viewer • Updated Jul 15 • 200 • 22

alckasoc/tabmwp_200_train

Viewer • Updated Jul 14 • 200 • 12

alckasoc/mbpp_120_train

Viewer • Updated Jul 14 • 120 • 17

alckasoc/gsm8k_200_train

Viewer • Updated Jul 14 • 200 • 20

alckasoc/hotpotqa_200_train

Viewer • Updated Jul 9 • 200 • 14

alckasoc/gsm8k_200

Viewer • Updated Jul 4 • 200 • 17

alckasoc/mbpp_200

Viewer • Updated Jul 4 • 200 • 10

alckasoc/svamp_200

Viewer • Updated Jul 4 • 200 • 12

alckasoc/tabmwp_200

Viewer • Updated Jul 4 • 200 • 12

alckasoc/triviaqa_200

Viewer • Updated Jul 4 • 200 • 19

alckasoc/triviaqa_expel_train_100

Viewer • Updated Oct 15, 2024 • 100 • 14

alckasoc/tabmwp_expel_train_100

Viewer • Updated Oct 15, 2024 • 100 • 14

alckasoc/mbpp_expel_train_100

Viewer • Updated Oct 15, 2024 • 100 • 14 • 1

alckasoc/gsm8k_expel_train_100

Viewer • Updated Oct 14, 2024 • 100 • 13 • 1

alckasoc/fever_expel_train_100

Updated Oct 14, 2024 • 12

alckasoc/ambignq_expel_train_100

Viewer • Updated Oct 14, 2024 • 100 • 10

alckasoc/hotpotqa_expel_train_100

Viewer • Updated Oct 13, 2024 • 100 • 19

alckasoc/ambignq_500

Viewer • Updated Sep 19, 2024 • 500 • 18

alckasoc/fever_500

Updated Sep 19, 2024 • 12 • 1

alckasoc/hotpotqa_500

Viewer • Updated Sep 18, 2024 • 500 • 13 • 1

alckasoc/smollm_dpo_examples_19k_3

Viewer • Updated Sep 15, 2024 • 19.8k • 20

alckasoc/smollm_dpo_examples_19k_2

Viewer • Updated Sep 15, 2024 • 19.8k • 28 • 1

alckasoc/smollm_dpo_examples_19k_1

Viewer • Updated Sep 15, 2024 • 19.8k • 15 • 1

alckasoc/smollm_dpo_examples_19k

Viewer • Updated Sep 14, 2024 • 19.8k • 27 • 1