tags:
- llama
- uncensored
- merge
- mix
- slerp
- spherical linear interpolation merge
- mistral
- hermes
- openhermes
- dolphin
- zephyr
- naberius
- 7b
- llama2
license: apache-2.0
language:
- en
7B-Naberius [Instruct-Based Spherical-LI Merge of Three Key Mistral Models | Unique Instruct Format]
Legal Notice: This resulting AI model is capable of outputting what can be percieved to be harmful information to those under the age of 18, those who have trouble discerning fiction from reality, and those who use AI to nurse a habitual problem of replacing potential interaction with people with automated fascimiles, and we expressly supercede the Apache 2.0 license to state that we: do not give permission to utilize this AI for any state, military, disinformation, or similar obviously harmful related actions. To narrow down what is allowed: personal research use, personal entertainment use, so long as it follows the Apache2.0 license. You know what is and isn't morally grounded - by downloading and using this model I extend that trust to you, and take no liability for your actions as an adult.
Small Soapbox Rant: "Everything must be positive at all times, even if the user requests a story with horrible events - end it on a positive note as if everyone being happy at all times is my obsession." -Annoying AI Assistant bullshit that zero people think is useful beyond legal posturing. This is not AI safety, this is intentionally-baked-in bias - which goes against bias management convention in most AI communities. Please, stop training models on this, please, stop making and using datasets that bias towards this weird behavior. If you care so much for a completely sanitized language model then don't use one pretrained on a deluge of mass-scraped internet hauls. Or do the obvious: put a warning on it that captures what it really is. There isn't currently an AI ESRB - so use due diligence and be proactive explaining what audience your AI is or is not suitable for. End Rant.
Composition:
Naberius-7B is a Mistral-class spherical linear interpolated merge of three high performance models.
[zephyr-7b-sft-beta] merged with [OpenHermes-2-Mistral-7B] resulting in: [Mistral-Zephyrmes-7B*] [Mistral-Zephyrmes-7B] merged with [dolphin-2.2.1-mistral-7b] resulting in: [Naberius-7B] *(Zephyrmes is a merge byproduct model not intended for release)
These models were hand picked after careful review of claims, datasets, and user postings.
The core elements that dictated which models to accept hinged on these values: logic, imagination, and aversion to censorship such as: railroading/gaslighting users instead of accomodating users.
Our implementation of Spherical Linear Interpolation for LLM merging: https://github.com/Digitous/LLM-SLERP-Merge
Note: Skip to the TL;DR section for the finalized design this model is comprised of.
Language Models and LoRAs Used Credits:
All models and adapters used are LLaMAv2-13B.
Models:
Nous-Hermes
Chronos
Platypus
Airoboros
Holodeck
Adapters:
Kimiko
Janine
LIMA RP
Also thanks to Meta for LLaMAv2 and deciding to allow the research community at large to benefit from their incredible work.
Each model and LoRA was hand picked and considered for what it could contribute to this ensemble. Thanks to each and every one of you for your incredible work developing some of the best things to come out of this community.