1. Tutorial Introduction

Llama-3.3-70B-Instruct is a large language model launched by Meta in 2024. It is the only open source model in the Llama 3.3 series, and has specially optimized the instruction fine-tuning version. The model supports 8 languages including English, German, French, Italian, Portuguese, Hindi, Spanish and Thai, but currently does not support Chinese. In the performance evaluation, the parameter scale of Llama-3.3-70B-Instruct is about 70B, but the various evaluation indicators are approximately equal to the Llama3.1-405B model with a parameter scale of 405B, which means that text can be generated faster with fewer resources, and the performance is similar to that of a large model with nearly 6 times the parameter scale. This makes Llama-3.3-70B-Instruct a powerful and cost-effective alternative, providing excellent performance in key benchmarks while remaining open source and accessible.

本教程使用 Llama-3.3-70B-Instruct（采取 int4 量化）作为演示，算力资源采用 A6000 。

2. Operation steps

1. After starting the container, click the API address to enter the web interface (If "Bad Gateway" is displayed, it means that the model is initializing. Since the model is large, please wait about 5 minutes and try again.)

2. Once you enter the webpage, you can start a conversation with the model!

Model dialogue flow

Exchange and discussion

🖌️ If you see a high-quality project, please leave a message in the background to recommend it! In addition, we have also established a tutorial exchange group. Welcome friends to scan the QR code and remark [SD Tutorial] to join the group to discuss various technical issues and share application effects↓