News for hackers. Stuff that matters.
Re:Cheating Is All You Need by a5huynh on Thursday March 23, 2023 @01:53PM (#35278639)
You can calculate them yourself as well! huggingface has a great article on this: https://huggingface.co/blog/getting-started-with-embeddings

tl;dr, use: https://huggingface.co/sentence-transformers/all-MiniLM-L6-v...

Re:Cheating Is All You Need by saurik on Thursday March 23, 2023 @03:20PM (#35279966)
(I want to focus more attention on that "tl;dr", which I will arguing is carrying a lot of load in that response: the high-level answer to how one does this using the llama weights is "you don't, as that isn't the right kind of model; you need to use a different model, of which there are many".)
Re:Cheating Is All You Need by meghan_rain on Friday March 24, 2023 @08:53AM (#35288380)
Thanks, but I already worked with thus model and it was not good at all for my domain. Therefore, I wanted to finetrain llama for my domain and then use llama for embeddings. Should I finetune this model then?