--- license: cc-by-nc-4.0 tags: - not-for-all-audiences - iMat - GGUF --- ``` e88 88e d8 d888 888b 8888 8888 ,"Y88b 888 8e d88 C8888 8888D 8888 8888 "8" 888 888 88b d88888 Y888 888P Y888 888P ,ee 888 888 888 888 "88 88" "88 88" "88 888 888 888 888 b 8b, e88'Y88 d8 888 d888 'Y ,"Y88b 888,8, d88 ,e e, 888 C8888 "8" 888 888 " d88888 d88 88b 888 Y888 ,d ,ee 888 888 888 888 , 888 "88,d88 "88 888 888 888 "YeeP" 888 PROUDLY PRESENTS ``` # G-COOM-9B-V0.01-iMat-GGUF Quantized with love from fp16. Original model author: [envoid](https://huggingface.co/envoid/) * Importance Matrix calculated using [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) in 93 chunks, n_ctx=512, and fp16 precision weights Original model README [here](https://huggingface.co/Envoid/G-COOM-9B-V0.01) and below: # G-COOM - (Gemma2 - Characterization Oriented Ontological Matrix) - 9B ![](https://files.catbox.moe/am4xsk.png) ## CAUTION: What you do with this model in the privacy of your own home/lab/etc is subject to [Google's prohibited use policy.](https://ai.google.dev/gemma/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](https://huggingface.co/TheDrummer/Smegmma-9B-v1) 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.