Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ Switching things up a bit since the last slew of models were all 12B, we now hav
|
|
| 25 |
The hope is abliteration will remove some of the inherant refusals and censorship of the original model, however I noticed that finetuning on GrimJim's model undid some of the abliteration, therefore more than likely abiliteration will have to be reapplied to the resulting model to reinforce it.
|
| 26 |
|
| 27 |
# Quants!
|
| 28 |
-
<strong>full</strong> / [exl2](https://huggingface.co/Epiculous/NovaSpark-exl2) / [gguf]()
|
| 29 |
|
| 30 |
## Prompting
|
| 31 |
This model is trained on llama instruct template, the prompting structure goes a little something like this:
|
|
|
|
| 25 |
The hope is abliteration will remove some of the inherant refusals and censorship of the original model, however I noticed that finetuning on GrimJim's model undid some of the abliteration, therefore more than likely abiliteration will have to be reapplied to the resulting model to reinforce it.
|
| 26 |
|
| 27 |
# Quants!
|
| 28 |
+
<strong>full</strong> / [exl2](https://huggingface.co/Epiculous/NovaSpark-exl2) / [gguf](https://huggingface.co/Epiculous/NovaSpark-GGUF)
|
| 29 |
|
| 30 |
## Prompting
|
| 31 |
This model is trained on llama instruct template, the prompting structure goes a little something like this:
|