I use it for development. All the things mentioned are nice, but there's no way I could afford to do development using a paid service. I pass/generate way too many tokens and my company hasn't really sponsored my work yet.
Having chatgpt write a pirate poem hardly costs a thing. Getting an llm to summarize a bunch of search results, or read an email inbox flagging certain scenarios, or parse through a codebase looking for specific features gets very, very expensive fast.
Of course someone beat me to it! I started doing something similar until I checked out SillyTavern and temporarily became obsessed with roleplay. I'll definitely spend more time checking this out when it isn't thanksgiving.
Funny. I can/will seed the hell out of some models when this happens.
This model is primarily recommended as a superior-to-Llama-2 baseline for additional finetuning,
According to the model, its not really supposed to compete with something like Vicuna. Sounds like they're trying to be an upgraded foundational model.
Anyone know a good tutorial for how merges are made?
10/10. Literally working of filing a patent at the moment and trying to make it as hyper specific as possible so a.) it doesn't overlap with anyone else's patent b.) pretty much only applies to what we're doing at the company.
I'm sure there's people in similar situations, but we're heavily incentivized to patent/publish something.
Do we have any reason to believe that it will be opensource?
Very good to know! I haven't fiddled with the new yi models too much yet since I was running into these exact issues. I'll definitely use this solution soon, thanks.