CoolFace
Modelpublic

leon2k2k2k/qwen2.5-3b-countdown-grpo

sourceHugging Faceotherupdated 3mo agoView on Hugging Face
0likes19downloads
8 commits on main
44b292b3mo ago

Add live writeup link

leon2k2k2k
0cad9933mo ago

Soften overclaim (base near-zero, not 'below baseline')

leon2k2k2k
e41dbdf3mo ago

Add GRPO iter-300 weights

leon2k2k2k
089329d3mo ago

Remove Limitations section

leon2k2k2k
3e7c11f3mo ago

Set Qwen Research License + attribution

leon2k2k2k
52c35093mo ago

Fix card frontmatter (yaml at top)

leon2k2k2k
7a046283mo ago

Add card

leon2k2k2k
95995a33mo ago

initial commit

leon2k2k2k