So Matt Pocock says models typically are smartest in the first 140k tokens. Hes using the big boy cloud models tho. Does that hold true for 27b-35b range? Or is it smaller and how much?

What would the ‘smart range’ be for tiny models that fit in 2gb? Would be it be like a sentence or two? I have an old 1050 was thinking of throwing in rig but im not sure what id even be able to do with such a small model

you are viewing a single comment's thread
view the rest of the comments
[–] [S] 6 points 2 weeks ago

Wow amazing stuff! Goes to show the gulf of knowledge between a noob just getting into local llama and you. Ty! I dont even know what to search for lol

  • source
  • parent