Moescape AI
  • 👋Welcome to Moescape.AI
  • Getting Started
    • âš™ī¸How to create an account on Moescape AI?
    • 🍡What is Mochi & How to get it?
  • Image Generation Guide
    • 📍Where to generate art?
    • 📜Prompt
      • How to emphasize certain keywords using (), []?
    • đŸĒ„Improved Prompt Feature
    • 🎨Models & Spells Selection
    • âš™ī¸Image Gen Settings
    • â˜ī¸Model Hub Beta
    • đŸĒ„LoRA Training
    • đŸ—ƒī¸Image Generation History
    • đŸ–ŧī¸Regional Prompter + ADetailer
    • 🔎Upscaler Tool
    • HiRes.Fix Tool
    • Image To Image Feature
    • đŸ•šī¸ControlNet Tool
    • 🔧Additional Image Tools
    • 💡PonyXL Model Guide
    • 🔮Introducing Flux models on Moescape AI
  • Tavern - Chatbot Guide
    • 🤖What is Tavern?
    • 📚Knowledge Base
    • âš™ī¸Tavern Models
    • đŸŽ›ī¸Tavern Parameters
    • System Prompt
    • 🧠Knowledge base & Scan Depth Support
    • User Persona
    • Memory Box
    • đŸ–ŧī¸Image Generation In-Chat
    • đŸ‘ĨTavern Character Presets Feature
    • 💡How To Create High-quality Chatbot Manually
    • đŸĒ„How To Create High-quality Chatbot With Moepilot
    • 💡Tips On How To Enhance Character
    • 🚀Advanced Character Creator Guide
  • ❓FAQs
Powered by GitBook
On this page
  • What are parameters
  • Customize these parameters further using the sliders available in Chat Settings.
  • Max New Tokens
  • Temperature
  • Top P
  • Top K
  • Repetition Penalty
  1. Tavern - Chatbot Guide

Tavern Parameters

PreviousTavern ModelsNextSystem Prompt

Last updated 23 days ago

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.

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.

Customize these parameters further using the sliders available in Chat Settings.

đŸŽ›ī¸