Skip to content
X · @rasbt · X / Twitter

Crazy model! It actually uses the old Qwen2.5-Coder-3B stack and got really great performance with their post-training stack. Need to use it in the ne…

Crazy model! It actually uses the old Qwen2.5-Coder-3B stack and got really great performance with their post-training stack. Need to use it in the next days to see if vibes of VibeCoder actually check out in practice. But impressive first impression!Based on the tech report, some of the important pieces of their post-