Early test version of what will soon be Indexnusrefather/Nyx-RP-9B-Instruct-2608-v2, for now its one of my first attempts with it and it might be quite unstable, check it out.
PS: This readme sucks, I know, it aint fancy.
Anyways, so the big difference from Nyx v1 is that this one had larger dataset, and I also trained it the different way because Nyx v1 approach turned out to break this one...
Here is my expression cleaning the dataset from Gemma slop btw:
5211162779375576356
So, this version has a rank of 216, and the dataset was additionally filtered, nothing else to say about it besides the fact that it has a chance of being the favorite.
