From the course: AI Toolkit Essentials for Visual Studio Code

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Comparing models

Comparing models

- [Instructor] Another feature of AI Toolkit is the capability to compare models. These can be comparing the same model with different parameters or different models altogether with similar or different parameters. What it allows us to do is give both models the same input simultaneously, and then compare the results. This may be useful for things like comparing the difference in performance of different model deployments, comparing the results of different models to contrast their suitability to our business problem, or simply varying the parameters to see the impact. For example, we may want to compare what happens with different settings for the maximum tokens to see what settings give a response that is neither too short nor too long. Like the rest of the playgrounds that we have been examining so far, it is used interactively; that is to say we're going to manually type in requests and read out responses. So we're going to do a simple comparison. To start with, we want to open…

Contents