This is a Mistral Nemo-based model consisting of a merge between:

This merge was performed with permission from the v1 creator (NGalrion). THe merge was performed in 2 steps.

The first is an intermediate starcannon v3 merge, but using magnum-v2.5-12b-kto:

The second is a merge between the intermediate starcannon v3 and Lyra, which reproduces LooseCannon.

This model will follow the ChatML instruct format:

<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

It can also follow the base Mistral Nemo instruct format, but ChatML is recommended.

The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It is not intended for supplying factual information or advice in any form.

This model is a merge. Please refer to the linked repositories of the merged models for details.

All my infrastructure and cloud expenses are paid out of pocket. If you'd like to donate, you can do so here: https://ko-fi.com/kingbri