PaulCalhoun

joined 10 months ago

[D] Massive amount of RAM needed to run a model. in c/machinelearning@academy.garden

[–] PaulCalhoun@alien.top 1 points 9 months ago

Could put a swap file on LTFS. Or just load more RAM via your local MicroCenter's IPoAC.

New Microsoft codediffusion paper suggests GPT-3.5 Turbo is only 20B, good news for open source models? in c/localllama@poweruser.forum

[–] PaulCalhoun@alien.top 1 points 10 months ago

People used to confuse the different GPT-__s all the time. The author probably read something about NeoX-20b and thought it was 3.5.