brainrot_vs_rl_qwen0.5
Collection
Collection of fine-tuned model of Qwen2.5-0.5B-Instruct on the MATH dataset using PPO, GRPO, and RLOO under varying proportions of junk data, • 20 items • Updated
No model card
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support