You must log in or register to comment.
Interesting but that’s not what I’m getting at all from gemma and phi on ollama.
Then again on a second attempt I get wildly different resutls, for both of them. Might be a matter of advanced settings, like temperature, but single examples don’t seem to be indicative of one being better than the other at this type of Qs.
Gemma seems very heavily censored to avoid anything remotely controversial. I gave up on it after trying it a few times. Phi-2 has other issues, but overall seems much better.
I find gemma to be too censored, I’m not using it until someone releases a cleaned up version.
Phi on the other hand outputs crazy stuff too often for my liking. maybe I need to tune some inference parameters.
