adventure-8b

Llama 3 8B trained on CYOA text completion data, in the style of GPT-J-6B-Adventure or GPT-J-6B-Skein.

This is not an instruction-tuned model.

Uses the following format:

[Mode: adventure]
[Themes: ...]

Narrative narrative narrative. Narrative!

> You perform the action

More narrative.

Trained on the Skein dataset created by VE FORBRYDERNE of KoboldAI.