Now we need someone to de-neuter this and make it less bias. I wonder how both the 7B and 13B compares with Mistral. So far it’s hype until I see other people’s results-tests.

Sorry I was playing around with it for the last day… So far I prefer it over 34B Dolphin Yi (GGUF Q4_K_m)… As for context size I only used 8k and it was pretty good with going far back. It might be able to do 12K, idk… Haven’t tried it.

He probably got repositioned somewhere else within Microsoft… probably.