Control the number of past messages in AI Chat to enhance context for responses. Include up to 10 me...
The Number of Tokens parameter in omniAI controls the maximum tokens in AI responses, balancing outp...
AI temperature settings control output randomness. Lower temperatures yield repetitive, deterministi...
Adjust Probability to control randomness in AI responses. Lower values narrow token selection to lik...
Stop Sequences are tokens that instruct AI to halt generation at specific points, like the end of a ...
Frequency Penalty, ranging from -2.0 to 2.0, influences how Omni AI penalizes tokens based on their ...