🔄 In a Training Loop

ar0cket1

ar0cket1

3 5

·

ar0cket1

AI & ML interests

None yet

Recent Activity

commentedon an article 11 days ago

Score Function Centering: Your Stale Rollout Does Not Have to Be Importance Sampled and Stabilize Your Async RL Training with Trainer-Generator KL

updated a dataset 2 months ago

ar0cket1/qwen3-4b-base-self-distillation-hints

published a dataset 2 months ago

ar0cket1/qwen3-4b-base-self-distillation-hints

View all activity

Organizations

ar0cket1 's models 1

ar0cket1/qwen3-30b-a3b-base-reasoning-sft-nemotron-math-v4-500m

Text Generation • 31B • Updated Aug 3 • 13