license: other
language:
- en
The Llama 2 sequel to my original experiment with gradient merges using the following script. Its three models (Hermes, Chronos and Airoboros) are almost evenly divided over the layer structure this time. Airoboros was the "wildcard model" due to its superior ability to understand complex instructions.
Model details
As always, the main objective was to create an all-round model with improved roleplaying capabilities. MythoLogic-L2 differs from its predecessor in that it focuses primarily on the understanding of instructions and personalities of complex character cards.
Illustrated below are the gradients used for this specific L2 recipe;
Prompt Format
This model primarily uses (and wast tested with) Alpaca formatting, so for optimal model performance, use:
### Instruction:
Your instruction or question here.
### Response:
For chat/roleplay conversations, I suggest the following structure 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.
### Chat History:
<AI NAME>: Good day, <YOUR NAME>! How can I assist you today?
(Etc, etc)
### Response:
<AI NAME>: