Commit
·
e13f23a
1
Parent(s):
31c36da
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,8 @@ This is an experimental instruct-tuned [mistralai/Mixtral-8x7B-v0.1](https://hug
|
|
| 21 |
|
| 22 |
It primarily uses the Capybara and No Robots datasets (thus the name). The goal was to create an uncensored general instruction following model, as well as test various loss implementations while we figure out how the heck to train Mixtral properly.
|
| 23 |
|
|
|
|
|
|
|
| 24 |
## Usage:
|
| 25 |
The intended prompt format is a modified multi-turn Alpaca instruction format:
|
| 26 |
```
|
|
|
|
| 21 |
|
| 22 |
It primarily uses the Capybara and No Robots datasets (thus the name). The goal was to create an uncensored general instruction following model, as well as test various loss implementations while we figure out how the heck to train Mixtral properly.
|
| 23 |
|
| 24 |
+
[Exl2 Quants](https://huggingface.co/royallab/Norobara-ZLoss-8x7B-exl2)
|
| 25 |
+
|
| 26 |
## Usage:
|
| 27 |
The intended prompt format is a modified multi-turn Alpaca instruction format:
|
| 28 |
```
|