swappy's picture

In a Training Loop 🔄

swappy PRO

rycerzes

·

https://rycerz.es

AI & ML interests

Deep learning, LLMs/VLMs, RL

Recent Activity

upvoted an article 3 days ago

The Open Source Community is backing OpenEnv for Agentic RL

updated a Space 12 days ago

rycerzes/swe-async-grpo-train

upvoted a changelog 13 days ago

Filter Models page by Base Models only

View all activity

Organizations

rycerzes 's datasets 4

rycerzes/ml-intern-sessions

Preview • Updated 29 days ago • 28

rycerzes/fswe-pg-01-traj-q36-27b

Updated Apr 26 • 102

rycerzes/fswe-hcapo-pg-01-trajectories

Viewer • Updated Apr 25 • 14 • 16

rycerzes/frontier-swe-pg-task-001-dpo-trajectories

Viewer • Updated Apr 25 • 135 • 24