Ironically thanks in no small part to Facebook releasing Llama and kind of salting the earth for similar companies trying to create proprietary equivalents.
Nowadays you either have gigantic LLMs with hundreds of billions of parameters like Claude and ChatGPT or you have open Models that are sub-200B.
I personally think the really large models are useless. What is very impressive is the small ones that somehow manage to be good. It blows my mind that so much information can fit in 8b.
Ironically thanks in no small part to Facebook releasing Llama and kind of salting the earth for similar companies trying to create proprietary equivalents.
Nowadays you either have gigantic LLMs with hundreds of billions of parameters like Claude and ChatGPT or you have open Models that are sub-200B.
I personally think the really large models are useless. What is very impressive is the small ones that somehow manage to be good. It blows my mind that so much information can fit in 8b.
True that, llms could be the future of lossy compression
Llama 3.1 405b has entered the chat
Waiting for a 8x1B MoE
Waiting till mixtral gonna optimise it enough to run on home computer, and then till dolphin uncensor it