license: other
language:
- en
Model details
MythoLogic-Mini-7b can be considered the little brother in my Mytho series of models: MythoLogic-13b and MythoBoros-13b).
Its Llama-2 core is powered by Nous Hermes-2, which is further augmented by Stable Beluga and a carefully distilled Kimiko LoRa.
Since 7B models tend to be less capable all-rounders, more emphasis was put on improving the roleplaying aspects for this gradient merge, of which various gradients were benchmarked before settling on the configuration shown below.
In technical terms, the Hermes-2 core starts at 90% strength before fading away completely at the 12th layer level, where Stable Beluga (and Kimiko) handle the more intricate linguistic aspects.
Prompt Format
Due to its Hermes-2 core this model works best 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>: