inflatebot/MN-12B-Mag-Mell-R1
Text Generation
•
Updated
•
1.75k
•
78
hence my idea of the SILLY versions... ;)
I am pretty sure that the actual models "AS THEY ARE" could perform 10 times better using chain of thought and some algorithms like these. Without needing a different training. And I think that's probably what CLAUDE does,