Runze Liu's picture

5 20 4

Runze Liu

RyanLiu112

·

https://ryanliu112.github.io

AI & ML interests

LLM, RL

Recent Activity

upvoted an article 1 day ago

Deriving the PPO Loss from First Principles

upvoted a paper 5 days ago

Step-DeepResearch Technical Report

upvoted a collection 5 days ago

Physics of Language Models: Part 4.2

View all activity

Organizations

RyanLiu112 's models 8

RyanLiu112/1.5a_first2

2B • Updated 22 days ago • 20

RyanLiu112/1.5a_woabf_480

2B • Updated 22 days ago • 13

RyanLiu112/1.5a_wodiff_420

2B • Updated 22 days ago • 15

RyanLiu112/1.5a_atb_740

2B • Updated 22 days ago • 8

RyanLiu112/1.5t_700

2B • Updated 23 days ago • 8

RyanLiu112/1.5g_740

2B • Updated 23 days ago • 10

RyanLiu112/7t_400

8B • Updated Oct 23 • 2

RyanLiu112/7g_360

8B • Updated Oct 23 • 3