Quick Deployment of Ziya Model

Introduction

The Ziya model is a leading natural language processing model developed by IDEA. Based on the large-scale pre-training model of LLaMa with 13 billion parameters, it has the capabilities of translation, programming, text classification, information extraction, abstract, copywriting generation, common sense Q&A and mathematical calculation. Currently, the “Ziya” model has completed the three-stage training process of large-scale pre-training, multi-task supervised fine-tuning and human feedback learning.

Quick Deployment

Log in to the UCloud Global console (https://console.ucloud-global.com/uhost/uhost/create), select “GPU Type” for the machine type, and “V100S”. Detailed configurations such as the number of CPUs and GPUs can be selected as needed.
The minimum recommended configuration: 10-core CPU, 64G memory, 1 V100S.
Choose “Image Market” for the image, search for “Ziya” in the image name, and select this image to create a GPU cloud host.
After the successful creation of the GPU cloud host, log in to the GPU cloud host.