Qwen2.5-3B-Instruct-Reasoning-Enhanced-with-Unsloth-and-GRPO-on-GSM8K

This project enhances the Qwen2.5-3B-Instruct model by integrating advanced reasoning capabilities using Unsloth. Additionally, it leverages GRPO, a reinforcement learning policy, for optimized performance. Trained and fine-tuned on the GSM8K dataset to improve problem-solving and inference.