Model Introduction

Compared with Qwen1.5, the upgraded Qwen2 has the following features:

• Pre-trained and finger-tuned models of 5 sizes: Qwen2-0.5B, Qwen2-1.5B, Qwen2-7B, Qwen2-57B-A14B, Qwen2-72B;
• In addition to English and Chinese, it has been trained on data in 27 other languages;
• State-of-the-art performance in a wide range of benchmarks;
• Coding and math scores improved significantly;
• Extended context length supports up to 128K tokens with Qwen2-7B-Instruct and Qwen2-72B-Instruct.

Run steps

1. After cloning the tutorial and starting it, directly copy the API address and paste it into any URL (real-name authentication must have been completed, and there is no need to open the workspace for this step)

2. Enter the chat interface and start chatting