# Tavern Parameters
## What are parameters
Parameters are advanced settings that allow you to precisely adjust or wholly transform your character's response. Parameter presets govern response length, randomness, and repetitiveness, you can choose from the ready-made presets craft your own to ensure your character’s reactions perfectly reflect your ideal vision.
Customize these parameters further using the sliders available in Chat Settings.\
\
\
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
## **Max New Tokens**
#### Maximum number of tokens to generate.
The lower the max new tokens number, the shorted the length of the response and vice versa. Use this to adjust the length of the responses you wish to receive from the characters.
***
## Temperature
#### Controls the randomness of the generated text.
* Lower value - the answers are more logical but less creative.
* Higher value - the answers are more creative but less logical.
***
## Top P
Limits the token pool to however many tokens it takes for their probabilities to add up to P.
* A lower number is more consistent but less creative.
***
## Top K
#### Set The Range of possible random results
* A lower number is more consistent but less creative.
***
## Repetition Penalty
Higher values make the output less repetitive.
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.moescape.ai/tavern-chatbot-guide/tavern-parameters.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
