GRPO
2 items
2 posts
Blog
$500 RL Fine-Tune of a 9B Open Model Beat GPT-5.6 Sol and Claude Opus 4.8 on Catalog ReviewA $500 GRPO fine-tune of Qwen 3.5 9B beat GPT-5.6 Sol and Opus 4.8 on catalog review, hitting 97% accuracy at a fraction of the cost per listing.
Blog
DeepSeek R1, PPO, and GRPO Explained for DevsGRPO and PPO explained for developers with no RL background: how DeepSeek R1 was trained, why GRPO drops the value model, and a minimal GRPO run with TRL.
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever