1.Added the ability to select the model's temperature (Creativity) and the maximum response length (Max Output Tokens)

2.All mod settings are configurable through the menu (/cubeintellect settings)

3.Added a new model

4.If the model's response is longer than 200 characters, the response will be split into multiple parts

5.Added support for English and Russian

6.Minor fixes

Outdated! Please use version >= 1.0.2

Release