Update README.md

README.md

@@ -24,7 +24,10 @@ tags:
 # Previous Rendition:
 [v0.3](https://huggingface.co/Blackroot/Mirai-70B-0.3)
 
-This is the 43rd evolution, some changes from the prior model:
+This is the 43rd evolution. I like this model so much I'm calling it a 1.0 release. This is by far the most liked version of any of the evolutions I tested. The prose is excellent, instruction and especially the huge amount of variety and intrigue is really something.
+
+# Some random advice:
+Try entirely disabling repetition filtering/penalties. I found overall the model improves substantially in others areas and the repetition seems quite low (for what I'm testing.) This model can withstand very high temperature, though of course it has the typical downsides, but I'd play with between 0.3-2.5. It's stable-ish even into the 2.X range, though I'd only recommend that for really wild experiences more akin to an Ai-dungeon run. Finally, I use a min-p of 0.05, too low and there's obvious linguistic issues in other languages like korean popping up. I would not go much higher than 0.05. 
 
 # Remove DISLab/SummLlama3-70B
 This model is certainly responsible for short responses, and I removed it because they were too short on average for my tastes. The writing style seemed to converge a bit as well, in a way that I found to get boring.