Apple AI Released a 7B Open-Source Language Model Trained on 2.5T Tokens on Open Datasets.

21 comments

They managed a substantial incremental improvement over previous models by first creating a better set of data as their starting point.
https://huggingface.co/apple/DCLM-7B
Is this the one the 'research only' one that was trained on YouTube transcripts including mkbhd?
- As someone who knows nothing about this stuff, yes.
  
  Happy cake day, Wang suck dude
  
  As someone who know f-all about AI I support your endorsement, if only by being impressed the training took 2.5 trillion tokes so you know that AI smokes like a banger!
Hopefully they'll be able to put something together that can run locally, so they can finally stop using this "Open"AI bullshit

You've viewed 21 comments.