You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This is a WIP model, it probably sucks and is bad, access at your own risk.

Log in or Sign Up to review the conditions and access this model content.

This is a 22b Mistral finetune created with a dataset I created, Retrowave, which is a small creative writing set, and a cut down version of Creative Writing Multiturn. Theoretically It'll be the start of a cool roleplay model. This is currently WIP, please leave comments where ever with your thoughts.

image/png

Downloads last month
4
GGUF
Model size
22.2B params
Architecture
llama

16-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for defen/retroturn

Quantized
(35)
this model

Dataset used to train defen/retroturn