sphiratrioth666's picture
Update README.md
7f5a5ac verified
|
raw
history blame
3.42 kB
metadata
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 documentation.

CONTENTS:

  • CONTEXT TEMPLATE (STORY STRING)
  • INSTRUCT TEMPLATE
  • SETTINGS (SAMPLERS)

  • SAMPLERS (USED):

  • Temperature
  • Min-P
  • DRY (prevents repetition)

  • All the other samplers neutralized. That's all you need in modern times (2024/2025).
    I am not a fan of XTC, it feels too "loose".

    PRESETS:

    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, 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, 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, around 2/3 narration against 1/3 dialogues >>>

    How to use:

    Advanced Users: Enjoy, modify, forget.
    Beginner Users: Read further.

    1. Find your LLM (model) 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 a fine-tune of Mistral Small" or "Nemo on steroids" 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 better. 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, Tolkien's Lord of the Templates.>>>/
    3. Download my presets.
    4. Copy the [CONTEXT TEMPLATE] files to (...)\SillyTavern\data\default-user\context
    5. Copy the [INSTRUCT TEMPLATE] files to (...)\SillyTavern\data\default-user\context
    6. Copy the [SETTINGS] files to SillyTavern\data\default-user\TextGen Settings

    Context Template = Story String People often get confused with names.