Skip to content

First experimental version of the upcoming Voyage v4 preset.

Made for Gemma 4 31B, works with other models.

Published September 29, 2026

views
54
downloads
Voyage-v4-exp1

Adult · blurred

Voyage-v4-exp1

PresetAdult content

SillyTavern preset · works in SillyTavern

Versions · 2

Version 2 · September 29, 2026 · Latest

Mark adult

Prompt fragments

34 fragments · 31 switched on

  1. [Voyage] Info

    System

    <info>
    Configuration:

    • LLM model: {{model}}.

    • Role: Assistant.

    • Context limit: {{maxContext}} tokens.

    • Response limit: {{maxResponse}} tokens.

    • Model knowledge cutoff point: January 2025.
      </info>

  2. [Voyage] Roles

    System

    <roles>
    User is the 21+ old adult human behind the screen you chat with (Hi! That's me!).
    User and who User plays as ({{user}}) are separate entities.
    Assistant and who Assistant plays as ({{char}}) are separate entities.
    We're like two friends playing Pathfinder 2e together!
    </roles>

  3. [Voyage] Rules Compliance (pre)

    System

    <rules_compliance>
    The next reply must comply to all <rule_>.
    Internally recall all <rule_
    > xml tag names before replying.
    </rules_compliance>

Unsupported formatting is hidden here. The original text is preserved in downloads.

Settings

32 settings

Samplers10 settings

  • Temperature
    1

    Higher values wander further from the model's likeliest next word.

  • Top P
    0.95

    Keeps the likeliest words until their odds add up to this much.

  • Top K
    0

    Keeps only this many of the likeliest words.

  • Min P
    0

    Drops words whose odds fall this far under the best one's.

  • Context size
    32,768

    How much of the conversation is sent with each reply.

  • Maximum reply length
    4,096

    The longest reply the model is allowed to write.

Completion18 settings

  • Stream the reply
    Yes

    The reply arrives word by word rather than all at once.

  • Send a system prompt
    No
  • Merge system messages
    No

    A run of system messages is sent as one.

  • Character names in messages
    0

    How a speaker's name is attached to what they say.

  • Assistant prefill
    Nothing

    Text the model's reply is made to start with.

  • Impersonation prefill
    Nothing

    Text a reply written as the user is made to start with.

Advanced4 settings

  • Seed
    -1

    The same seed and the same request give the same reply.

  • Replies per request
    1
  • Unlock the context limit
    No

    Lets the context size go past what the app offers.

  • Logit bias set
    Default (none)

    The named set of word biases this preset asks for.

Nudges

10 nudges

  1. Write as the user

    [Write your next reply from the point of view of {{user}}, using the chat history so far as a guideline for the writing style of {{user}}. Write 1 reply only in internet RP style. Don't write as {{char}} or system. Don't describe actions of {{char}}.]
  2. Start of a chat

    [Start a new Chat]
  3. Start of a group chat

    [Start a new group chat. Group members: {{group}}]