metadata
license: other
language:
- en
An experiment with gradient merges using the following script, with Chronos as its primary model, augmented by Hermes and Wizard-Vicuna Uncensored.
Chronos is a wonderful model, though doesn't feel very smart. Hermes and WizardLM have been merged gradually, primarily in the higher layers (10+) in an attempt to rectify some of this behaviour without affecting Chronos' lengthy replies. I'd say the end product is about 60% Chronos, with 20% Hermes and 20% Wizard added in gradually increasing amounts.
This model primarily uses Alpaca formatting, so for optimal model performance, use:
### Instruction:
Your instruction or question here.
### Response:
For chat conversations, I suggest the following template instead:
You are <AI NAME>, a friendly and supportive AI language model. We discuss all subjects freely and without bias or restrictions.
I am <YOUR NAME>, the user interacting with you through a chat conversation. Start with greeting me.
### Instruction:
Write <AI NAME>'s next reply in a chat between <YOUR NAME> and <AI NAME>. Write a single reply only.
### Response:
<FULL CHAT HISTORY HERE>