---
license: other
language:
- en
---
An experiment with gradient merges using [the following script](https://github.com/TehVenomm/LM_Transformers_BlockMerge), with [Chronos](https://huggingface.co/elinas/chronos-13b) as its primary model, augmented by [Hermes](https://huggingface.co/NousResearch/Nous-Hermes-13b) and [Wizard-Vicuna Uncensored](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-HF).

Quantizations are available from TheBloke (You're the best!):

[GGML](https://huggingface.co/TheBloke/MythoLogic-13B-GGML)
[GPTQ](https://huggingface.co/TheBloke/MythoLogic-13B-GPTQ)

Chronos is a wonderfully verbose model, though it definitely seems to lack in the logic department. Hermes and WizardLM have been merged gradually, primarily in the higher layers (10+) in an attempt to rectify some of this behaviour.

The main objective was to create an all-round model with improved story generation and roleplaying capabilities.

Below is an illustration to showcase a rough approximation of the gradients I used to create MythoLogic:

![](approximation.png)

This model primarily uses 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
---