|
--- |
|
license: cc-by-nc-4.0 |
|
--- |
|
|
|
This model is the first in a series of experiments to make my models a bit smarter. Its nowhere near done, but my initial testing was good so I'm uploading so people can check it out. |
|
|
|
Datasets Used: |
|
|
|
* Dolphin |
|
* Ultrachat |
|
* Capybara |
|
* Augmental |
|
* ToxicQA |
|
* Magiccoder-Evol-Instruct-110k |
|
* Yahoo Answers |
|
* OpenOrca |
|
* Airoboros 3.1 |
|
* grimulkan/physical-reasoning and theory-of-mind |
|
|
|
|
|
## Prompt Format: Chat ( The default Ooba template and Silly Tavern Template ) |
|
``` |
|
{System Prompt} |
|
|
|
Username: {Input} |
|
BotName: {Response} |
|
Username: {Input} |
|
BotName: {Response} |
|
|
|
``` |
|
|
|
## Recommended Silly Tavern Preset -> (Temp: 1.25, MinP: 0.1, RepPen: 1.03) |
|
## Recommended Kobold Horde Preset -> MinP |