MythoLogic-L2-13b / README.md
Gryphe's picture
Update README.md
7b2e476
|
raw
history blame
1.89 kB
---
license: other
language:
- en
---
The Llama 2 sequel to my original experiment with gradient merges using [the following script](https://github.com/Gryphe/BlockMerge_Gradient). Its three models ([Hermes](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b), [Chronos](https://huggingface.co/elinas/chronos-13b-v2) and [Airoboros](https://huggingface.co/jondurbin/airoboros-l2-13b-gpt4-2.0)) are almost evenly divided over the layer structure this time. Airoboros was the "wildcard model" due to its superior ability to understand complex instructions.
Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheBloke/MythoLogic-13B-GGML) - [GPTQ](https://huggingface.co/TheBloke/MythoLogic-13B-GPTQ) (You're the best!)
## 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 L2 recipe;
[](approximation.png)
## 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>:
```
---
license: other
---