Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ widget:
|
|
| 27 |
This is...
|
| 28 |
## Llama Lo1 01
|
| 29 |
|
| 30 |
-
My first RP directed finetune and merge! Not as expresive like Llama Instruct might be. Writes simpler responses in chat. Somewhat broken as I did not figured how to deal properly with tokenizers.
|
| 31 |
|
| 32 |
Trained on few datasets from [jeiku](https://huggingface.co/jeiku) - Thank you!
|
| 33 |
|
|
@@ -35,6 +35,13 @@ Have fun!
|
|
| 35 |
|
| 36 |
<img src=https://huggingface.co/altomek/Lo101-3B-AnD/resolve/main/Lo101-chat1.png>
|
| 37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
## Quants
|
| 39 |
|
| 40 |
- [ExLlamav2 8bpw](https://huggingface.co/altomek/Lo101-3B-AnD-8bpw-EXL2)
|
|
|
|
| 27 |
This is...
|
| 28 |
## Llama Lo1 01
|
| 29 |
|
| 30 |
+
My first RP directed finetune and merge! Not as expresive like Llama Instruct might be. Writes simpler responses in chat. Somewhat broken as I did not figured how to deal properly with tokenizers.
|
| 31 |
|
| 32 |
Trained on few datasets from [jeiku](https://huggingface.co/jeiku) - Thank you!
|
| 33 |
|
|
|
|
| 35 |
|
| 36 |
<img src=https://huggingface.co/altomek/Lo101-3B-AnD/resolve/main/Lo101-chat1.png>
|
| 37 |
|
| 38 |
+
## Settings
|
| 39 |
+
|
| 40 |
+
- Kobold use Chat Mode
|
| 41 |
+
- SillyTawern use ChatML for Context Template and Llama 3 Instruct for Instruct Mode
|
| 42 |
+
- ChatterUI use Llama3
|
| 43 |
+
- Set Temperature below 1
|
| 44 |
+
|
| 45 |
## Quants
|
| 46 |
|
| 47 |
- [ExLlamav2 8bpw](https://huggingface.co/altomek/Lo101-3B-AnD-8bpw-EXL2)
|