But why they didn't compare it to SOTA finetuned...(like vicuna playtus..)?
... smells a bit strange..
42 karma · joined April 25, 2023
This is like Cold-war between companies, that we as users are the cannon fodder...
Any ideas how we, the users of the internet, should act to prevent those steps? or building a much better connected and not controlled by mega-corporates INTERNET social platform?
Suggestion: please add the ability to use credential for social, to be able to perform social tasks.
You have two options:
1- Find some port for it to run locally on GitHub (it will be quantized and not that useful right now, till 2024-till Qualcomm will ship their phones). - see https://github.com/Bip-Rep/sherpa
*The better one* 2- Host the version on a server on the cloud (or locally on your computer with tunneling) using ooga-booga (with --api flag), and communicate with that self-hosted llama, directly. This way you won't be limited to 7/13B versions but can run the 70B...
Sharing data with OpenAI it's *irresponsible step* at this time of development.
There is not much point to give crawlers a lot of content generation; but rather only the succinct "prompt".
In that way, it will be easy to signal to crawlers what to crawl, and user can be read the content after the function of LLM...