Tencent Cloud Large Model Training and Inference Platform TI-ONE is a one-stop large model training and inference platform built for AI engineers, providing users with end-to-end development support from data access, model training, and model management to model service. The TI-ONE platform supports multiple training methods and algorithm frameworks to meet the needs of different AI application scenarios.
The TI-ONE platform API interfaces described in this chapter are all API 3.0 interfaces.
You can call APIs to perform operations on the TI-ONE platform, such as creating model training tasks and model services.
For all API information supported by the TI-ONE platform, please see API overview.
See the table below for common terminology of TI-ONE platform API interfaces:
Terminology |
Description |
|---|---|
| Training task | An async process in which input data executes model training on computing resources to generate model files. |
| Model | A result produced by training tasks based on data and algorithm code. It can predict new data. |
| Model service | Deploy the model as an online API service (such as a RESTful API) to support real-time inference requests. |
For API parameter limits, see the parameter description in each API document.
You can use the API Explorer tool to call APIs online.
This document uses creating a model training task as an example. The steps to make an API call through the API Explorer Tool are as follows:
Was this page helpful?
You can also Contact sales or Submit a Ticket for help.
Help us improve! Rate your documentation experience in 5 mins.
Feedback