News for hackers. Stuff that matters.
Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by Animats on Monday April 10, 2023 @12:59AM (#35509320)
Most of this is about the base model. How's open-source "fine tuning" coming along? I'd like to add a few hundred questions and answers on a specialist topic. Recommendations?
Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by amrb on Monday April 10, 2023 @01:02AM (#35509331)
Seems the fine tuned models I.e. gpt4all and alpaca are trained as LoRa's. Best advice is jump in and try the demos on hugging space!