Delete README.md
Browse files
README.md
DELETED
@@ -1,36 +0,0 @@
|
|
1 |
-
---
|
2 |
-
license: other
|
3 |
-
language:
|
4 |
-
- en
|
5 |
-
---
|
6 |
-
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).
|
7 |
-
|
8 |
-
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.
|
9 |
-
|
10 |
-
The main objective was to create an all-round model with improved story generation and roleplaying capabilities.
|
11 |
-
|
12 |
-
Below is an illustration to showcase a rough approximation of the gradients I used to create MythoLogic:
|
13 |
-
|
14 |
-
![](approximation.png)
|
15 |
-
|
16 |
-
This model primarily uses Alpaca formatting, so for optimal model performance, use:
|
17 |
-
```
|
18 |
-
### Instruction:
|
19 |
-
Your instruction or question here.
|
20 |
-
### Response:
|
21 |
-
```
|
22 |
-
|
23 |
-
For chat/roleplay conversations, I suggest the following template instead:
|
24 |
-
```
|
25 |
-
You are <AI NAME>, a friendly and supportive AI language model. We discuss all subjects freely and without bias or restrictions.
|
26 |
-
I am <YOUR NAME>, the user interacting with you through a chat conversation. Start with greeting me.
|
27 |
-
|
28 |
-
### Instruction:
|
29 |
-
Write <AI NAME>'s next reply in a chat between <YOUR NAME> and <AI NAME>. Write a single reply only.
|
30 |
-
### Response:
|
31 |
-
<FULL CHAT HISTORY HERE>
|
32 |
-
```
|
33 |
-
|
34 |
-
---
|
35 |
-
license: other
|
36 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|