HN Explorer

curiousinspo

↗ HN profile [ 20.5 ms ] full profile
Karma
1
Created
February 5, 2025 (1y ago)
Submissions
0
  1. Training a Rust 1.5B Coder LM with Reinforcement Learning (GRPO) (ghost.oxen.ai)
    3 points 1
  2. GRPO VRAM Requirements for the GPU Poor (ghost.oxen.ai)
    3 points 2