Aochong Oliver Li's picture

Aochong Oliver Li

aochongoliverli

·

https://aochong-li.github.io/

AI & ML interests

Large Language Models, Natural Language Processing, Machine Learning

Recent Activity

updated a model 23 days ago

aochongoliverli/Qwen2.5-3B-limo-qwq-16k-3epochs-5e-5lr-step150

published a model 23 days ago

aochongoliverli/Qwen2.5-3B-limo-qwq-16k-3epochs-5e-5lr-step150

liked a dataset 2 months ago

zai-org/terminal-bench-2-verified

View all activity

Organizations

None yet

aochongoliverli 's datasets 72

aochongoliverli/countdown_level_4

Viewer • Updated Jun 27, 2025 • 55k • 2

aochongoliverli/countdown_level_3

Viewer • Updated Jun 27, 2025 • 55k • 2

aochongoliverli/R1-Distill-Qwen-1.5B-deepmath-level5-6-max-length-16384-rollout-8-temperature-0.5-rollouts

Viewer • Updated Jun 22, 2025 • 19.2k • 2

aochongoliverli/R1-Distill-Qwen-1.5B-deepmath-level5-6-beta-max-length-4096-rollout-4-rollouts

Viewer • Updated Jun 20, 2025 • 9.89k • 2

aochongoliverli/Qwen2.5-3B-countdown-level4-1epochs-4rollouts-1024max-length-reasoning-traces-rollout-sft

Viewer • Updated Jun 2, 2025 • 1.54M • 6

aochongoliverli/Qwen2.5-3B-countdown-level4-1epochs-4rollouts-1024max-length-reasoning-traces

Viewer • Updated Jun 2, 2025 • 164k • 4

aochongoliverli/Qwen2.5-3B-countdown-level4-1epochs-8rollouts-3840max-length-reasoning-traces

Viewer • Updated Jun 2, 2025 • 164k • 3

aochongoliverli/Qwen2.5-3B-countdown-level4-1epochs-4rollouts-3840max-length-reasoning-traces

Viewer • Updated Jun 2, 2025 • 102k • 4

aochongoliverli/Qwen2.5-Math-1.5B-deepmath-hard-1800-steps-4096-self-distill-sft

Viewer • Updated May 30, 2025 • 356k • 3

aochongoliverli/deepmath-4096-hard-sft

Viewer • Updated May 24, 2025 • 104k • 3

aochongoliverli/deepmath-4096-hard-rl

Viewer • Updated May 24, 2025 • 46.6k • 4

aochongoliverli/KUP

Viewer • Updated Apr 1, 2025 • 5k • 109 • 2