Tianlin Liu's picture

Tianlin Liu

tianlinliu0121

·

https://tianlinliu.com/

liutianlin0121

AI & ML interests

None yet

Organizations

Articles 1

Article

59

The N Implementation Details of RLHF with PPO

Papers 2

arxiv:2402.04792

arxiv:2402.02992

models 4

tianlinliu0121/zephyr-7b-dpo-full-debug-regression

Text Generation • 7B • Updated Dec 7, 2023 • 12

tianlinliu0121/zephyr-7b-dpo-full-beta-0.2

Text Generation • 7B • Updated Nov 23, 2023 • 15

tianlinliu0121/zephyr-7b-dpo-full-beta-0.083

Text Generation • 7B • Updated Nov 19, 2023 • 17

tianlinliu0121/zephyr-7b-dpo-full

Text Generation • 7B • Updated Nov 18, 2023 • 18

datasets 0

None public yet