@sudoingX Pardon my ignorance. Why if turbo quant is supposed to be great for memory (specially for enabling long context in low vram) it is still unused compared q4_k_m?
Wow, this tweet went very viral!
I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person's agent customizes & builds it for your specific needs.
So here's the idea in a gist format: https://t.co/NlAfEJjtJV
You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It's intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool.
Si te pagaran un plus de 800€ al año por ir en bici al trabajo... ¿te apuntarías? Vamos, te apuntarías tú y media España...
🚲🚲🚲🚲🚲
Cobrar 800 euros al año por ir en bici al trabajo: en Países Bajos y Francia ya se hace, en España todavía es una idea.https://t.co/PX19qf3ue9