Update README.md
Browse files
README.md
CHANGED
@@ -31,7 +31,7 @@ ArliAI-RPMax-12B-v1.2 is a variant based on Mistral Nemo 12B Instruct 2407.
|
|
31 |
|
32 |
This is arguably the most successful RPMax model due to how Mistral is already very uncensored in the first place.
|
33 |
|
34 |
-
v1.2 update
|
35 |
|
36 |
### Training Details
|
37 |
|
|
|
31 |
|
32 |
This is arguably the most successful RPMax model due to how Mistral is already very uncensored in the first place.
|
33 |
|
34 |
+
v1.2 update completely removes non-creative/RP examples in the dataset and is also an incremental improvement of the RPMax dataset which dedups the dataset even more and better filtering to cutout irrelevant description text that came from card sharing sites.
|
35 |
|
36 |
### Training Details
|
37 |
|