CoolFace
Modelpublic

karthik/verl-qwen2.5-0.5b-gsm8k-ppo-step360

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes16downloads
4 commits on main
33338c11y ago

Update README.md

karthik
1898d0f1y ago

Add converted model weights (safetensors format)

karthik
59ea2361y ago

Add VERL fine-tuned Qwen2.5-0.5B tokenizer and config (360 steps)

karthik
176cb491y ago

initial commit

karthik