Qwen2.5

Big Data Technology Architecture

Feb 9, 2025 · Artificial Intelligence

Reproducing Deepseek RI Reasoning Ability with GRPO on Qwen2.5‑7B in Colab

This article explains how to replicate Deepseek RI's slow‑thinking inference using the GRPO reinforcement‑learning algorithm on the Qwen2.5‑7B model in a free Colab notebook, covering the underlying COT concept, reward‑function design, data preparation, training configuration, and observed results.