Update README.md
Browse files
README.md
CHANGED
|
@@ -39,7 +39,7 @@ Not using the format will make the model perform significantly worse than intend
|
|
| 39 |
Sampling and settings can make a significant difference for this model, so play around with them. I was also informed by a user that if you are using **KoboldCPP** that using the flag
|
| 40 |
`--unbantokens` may improve model performance **significantly**. This has not been tested by myself, but that is something to keep in mind.
|
| 41 |
|
| 42 |
-
##
|
| 43 |
|
| 44 |
[LlamaCPP Versions provided by @TheBloke]()
|
| 45 |
|
|
|
|
| 39 |
Sampling and settings can make a significant difference for this model, so play around with them. I was also informed by a user that if you are using **KoboldCPP** that using the flag
|
| 40 |
`--unbantokens` may improve model performance **significantly**. This has not been tested by myself, but that is something to keep in mind.
|
| 41 |
|
| 42 |
+
## Quantized Versions for Consumer GPU Usage
|
| 43 |
|
| 44 |
[LlamaCPP Versions provided by @TheBloke]()
|
| 45 |
|