README.md

---
license: cc-by-nc-3.0
language:
- en
---
Simple, effective, universal presets for Silly Tavern role-playing purposes. Organized file names, organized preset names, detailed instruction and explanations.<br><br>There are other great presets from Virt-AI or Marinara available on the site but they come with messy preset names, less clear file structures or forced instructions such as including the character example messages through instruct/context template, which becomes the unnecessary bother. Importing those presets into Silly Tavern requires a bit of work and deeper understanding - you need to manually change the presets names in JSON files to something recognizable/useful, do the same with file names to understand what's what on the long Silly Tavern lists when loading the presets up etc.<br><br>Both Marinara and Virt-AI are great creators so when you learn and understand how presets actually work - be sure to give their presets collections a try! :-) 

<h1><ins>CONTENTS:</ins></h1>
<li>CONTEXT TEMPLATES (STORY STRING)</li>
<li>INSTRUCT TEMPLATES</li>
<li>SYSTEM PROMPTS</li>
<li>SETTINGS (SAMPLERS)</li>
<br>
<h1><ins>SAMPLERS (USED):</ins></h1>
<li>Temperature</li>
<li>Min-P</li>
<li>DRY (prevents repetition)</li>
<br>
> All the other samplers neutralized. That's all you need in modern times (2024/2025).<br>> I am not a fan of XTC, it feels too "loose".
<br>
<br>
<h1><ins>VARIANTS:</ins></h1>
<li>Sphiratrioth [T=0.7] (Temperature = 0.7) - less creative, more precise, tames down the "fidgeting" models</li>
<li>Sphiratrioth [T=1.0] (Temperature = 1.0) - standard, works well with most models</li>
<li>Sphiratrioth [T=0.7] (Temperature = 1.3) - creative boost - without going off the rails</li>
<br>
<h1><ins>MESSAGES FORMATS:</ins></h1>
<li>1st Person / 3rd Person Narration (switch through System Prompt Presets!)</li>
<li>DIALOGUES - plain text, no markdowns, it's a bother</li>
<li>NARRATION - italics</li>
<li>Trim Incomplete Sentences: ON (it prevents messeges from being cut in half with short maximum tokens setting in "conversation" mode preset)</li>
<br>
<h1><ins>PRESETS:</ins></h1>

**A) Sphiratrioth (Conversation)** - minimal narration - when you want to simulate a natural, human-like conversation with a bot. For those who do not like the "verbose" role-play.
***<<< conversation-like, ~ 150 tokens responses, around 2/3 dialogue against 1/3 narration >>>***

**B) Sphiratrioth (Roleplay)** - balanced RP - when you want to experience a balanced role-play with responses around 1-2 paragraphs.
***<<< 1 short paragraph, ~ 250 tokens responses, around 50/50 balance in dialogues against narration >>>***

**C) Sphiratrioth (Story)** - AI becomes your Game Master (GM) - when you want those long, verbose paragraphs with rich narration & story-telling.
***<<< 1-3 paragraphs, ~ 350 tokens responses, around 2/3 narration against 1/3 dialogues >>>***
<br>
<h1><ins>How to use:</ins></h1>

**Advanced Users:** Enjoy, modify, forget.\
**Beginners:** Read further.

1. Find your model's native INSTRUCT TEMPLATE. Every fine-tune stands on a base model, which is usually specified by its creator in a manner of "We're presenting the first fine-tune of Mistral Small" or "Nemo on steroids" or "LLAMA 3 with our special sauce" etc. It may be confusing, it may be clear. Not my fault :-P However, you need to identify the base model of a fine-tune by reading its description page. Different templates may be used by creators (tuners) for training - and then - templates suggested on a fine-tune's page work best. However, creators often just choose the basic template of a model they're tuning - so make sure to check the model's description page or assume it's using the base model's template (template of the main model that a given tuner is tuning).
***<<< Most typical templates: Mistral, ChatML, Alpaca, Metharme/Pygmalion >>>***
2. Golden Rule: Match CONTEXT TEMPLATE (Story String) and INSTRUCT TEMPLATE with your model. For instance, when Mistral-Nemo fine-tune is using the Mistral Instruct Template (as specified by creator of a fine-tune) - pick up the "Sphiratrioth - Mistral [CONTEXT TEMPLATE]" file and "Sphiratrioth - Mistral [INSTRUCT TEMPLATE]" file. It's very easy. I keep my naming clear - both the file names and preset names inside of the Silly Tavern UI list when you load them up. They're always clear and distinguishable.
***<<< This rule may be broken when you become the advanced user. Then, you'll know what you're doing so you'll mix different context/instruct templates. For now - one ring... khem - one template to rule them all. Don't be the Amazon Saur-off. Be a true Lord of the Templates.>>>***/
3. Download my presets.
4. Copy the [Sphiratrioth-(...)-CONTEXT TEMPLATE] files to (...)\SillyTavern\data\default-user\context.
5. Copy the [Sphiratrioth-(...)-INSTRUCT TEMPLATE] files to (...)\SillyTavern\data\default-user\context.
6. Copy the [Sphiratrioth-(...)-SETTINGS] files to SillyTavern\data\default-user\TextGen Settings.
7. Copy the [Sphiratrioth-(...)-PROMPT] files to (...)\SillyTavern\data\default-user\sysprompt.
8. Open up Silly Tavern UI.
9. Click on the "Capital A" tab in Silly Tavern UI (AI Response Formatting).
10. Load up my Context Template (Story String) Preset from the Context Templates list.
11. Click on the "Enable Instruct Mode" button (ON/OFF next to the name "Instruct Template").
12. Load up my Instruct Template Preset from the Instruct Templates list.
13. Load up my System Prompt from the System Prompts list.
14. Click on the "Sliders" tab in Silly Tavern UI (AI Response Configuration).
15. Load up my Settings Preset from the Text Completion Presets list.
16. Switch between the 1st Person/3rd Person narration by switching the System Prompt Presets. Theoretically, it should re-evaluate the prompt but it may not work unless you start a new chat!
17. Switch between Conversation/Roleplay/Story Modes by switching the Settings (Text Completion Presets/Samplers).
18. Enjoy.
<br>
<br>
<h1><ins>BEWARE:</ins></h1>

**IF YOU WANT THE PRESETS TO WORK PROPERLY, REMEMBER TO START A NEW CHAT FOR TESTING PURPOSES/ACTUAL ROLE-PLAY. WHEN YOU SWITCH THE PRESETS "HOT", YOU MAY EASILY FALL INTO A TRAP OF CONTINUING THE PREVIOUS PROMPT. IN RESULT, THE SHORT/BALANCED/LONG RESPONSES AND NARRATION IN 1st/3rd PERSON WILL NOT SWITCH. ALWAYS START A NEW CHAT. THEORETICALLY, SWITCHING A SYSTEM PROMPT FORCES THE PROMPT EVALUATION BUT IN REALITY - IT OFTEN BREAKS, IT DOES NOT WORK PROPERLY. IT WORKS WHEN YOU START A NEW CHAT THOUGH - OR WHEN YOU RELOAD THE WHOLE SILLY TAVERN UI.**

<h1><ins>CUSTOMIZATION:</ins></h1>
<li>Dialogues in Markdowns - modify the SYSTEM PROMPT ("Capital A" tab of Silly Tavern UI). It's simple - find the following line and replace with: Respect this markdown format: "direct speech", *actions*</li>
<li>Narration in Plain Text - modify the SYSTEM PROMPT ("Capital A" tab of Silly Tavern UI). Find the following line and replace with: Respect this markdown format: "direct speech", actions</li>
<li>Shorter/Longer Replies (additional ways of setting it up): a) character example messages - this helps a lot; b) shorter/longer starting message; c) OOC - check what's that, some models support it well - such as Celeste</li>
<br>
<h1><ins>PLANS FOR THE FUTURE:</ins></h1>
<li>Maybe switching narration type and messages formatting from System Prompt to Context Template</li>
<br>
<h1><ins>ANNOTATIONS:</ins></h1>
<li>Context = Context Template = Story String (IN TERMS OF PRESETS)</li>
I'm simplifying here but people often get confused with names. Story String is a part of the Context Template - to be precise - but creators of models and presets use those terms as equivalents...
<li>Context = Context Length of a model (IN TERMS OF PROPER USE OF A WORD). People simplify and use mental leaps. Not my fault, again :-P</li>