leon2k2k2k/qwen2.5-3b-countdown-sft-grpo
011
Add live writeup link
Add SFT-then-GRPO weights
Remove Limitations section
Set Qwen Research License + attribution
Fix card frontmatter (yaml at top)
Add card
initial commit
Add live writeup link
Add SFT-then-GRPO weights
Remove Limitations section
Set Qwen Research License + attribution
Fix card frontmatter (yaml at top)
Add card
initial commit