Are you running Domino IQ in Local mode or in Remote mode against your own llama.cpp based LLM runtime?
Then i recommend to watch this video: https://www.youtube.com/watch?v=8F_5pdcD3HY
In less than 15 minutes you will learn…
-
why it’s important to read (and understand) the model card of your selected LLM
-
why you should spend some time to learn about the different parameters you can use with llama.cpp