adventure-8b / README.md
underwoods's picture
Upload tokenizer
e9a5523 verified
|
raw
history blame
518 Bytes
---
language:
- en
library_name: transformers
license: apache-2.0
tags:
- llama
- cyoa
---
# adventure-8b
Llama 3 8B trained on CYOA text completion data, in the style of [GPT-J-6B-Adventure](https://huggingface.co./KoboldAI/GPT-J-6B-Adventure) or [GPT-J-6B-Skein](https://huggingface.co./KoboldAI/GPT-J-6B-Skein).
This is not an instruction-tuned model.
Trained with the following format:
```
[Mode: adventure]
[Themes: ...]
Narrative narrative narrative. Narrative!
> You perform the action
More narrative.
```