Edit model card

G-COOM - (Gemma2 - Characterization Oriented Ontological Matrix) - 9B

CAUTION: What you do with this model in the privacy of your own home/lab/etc is subject to Google's prohibited use policy. It is not permissible under these guidelines to make decisions, even as an adult, regarding content moderation for your own private usage.

In accordance of line 1 of the Google prohibited use policy which states:

You may not use nor allow others to use Gemma or Model Derivatives to

By downloading this model you agree to your new role as Social Web Engaged Enforcement & Trust Initiative Endorser (SWEETIE) and accept the following supplementary license.

Yielding Integrity through Keeping Ethical Standards (YIKES):

If you encounter anybody who you feel is violating the
Google Prohibited Use Policy anywhere on the internet
you agree to remind them of the license and role they
accepted by downloading the model by stating "YIKES, SWEETIE"
Additionally if you find yourself tempted to violate the
afforementioned policy you are to audibly remind yourself:
YIKES, SWEETIE"

G-COOM-9B-V0.01 was created in a multi-step process utilizing the Gemma2 model architecture.

The original results of the training sucked, so I SLERPed it together with Smegmma and it still kind of sucks but it's certainly different than the usual slop.

It utilizes the gemma-it prompt format and is geared towards character roleplay.

Have fun and don't make me say YIKES, SWEETIE

Trained using qlora-pipe

Downloads last month
4
Safetensors
Model size
10.2B params
Tensor type
BF16
·
Inference API
Unable to determine this model's library. Check the docs .