News for hackers. Stuff that matters.
Re:Mistral AI Launches New 8x22B MOE Model by swalsh on Tuesday April 09, 2024 @09:33PM (#39986109)
Is this Mistral large?
Re:Mistral AI Launches New 8x22B MOE Model by varunvummadi on Tuesday April 09, 2024 @09:33PM (#39986116)
Not sure trying to download the torrent and checking it out
Re:Mistral AI Launches New 8x22B MOE Model by fbdab103 on Tuesday April 09, 2024 @10:54PM (#39986525)
For those of us without twitter, how many GB is the model?
Re:Mistral AI Launches New 8x22B MOE Model by KTibow on Tuesday April 09, 2024 @11:01PM (#39986548)
(hope this isn't against rules but) If you don't have Twitter, the magnet link is

  magnet:?xt=urn:btih:9238b09245d0d8cd915be09927769d5f7584c1c9&dn=mixtral-8x22b&tr=udp%3A%2F%http://2Fopen.demonii.com%3A1337%2Fannounce&tr=http%3A%2F%http://2Ftracker.opentrackr.org%3A1337%2Fannounce
Re:Mistral AI Launches New 8x22B MOE Model by confused_boner on Tuesday April 09, 2024 @11:06PM (#39986580)
262 gb
Re:Mistral AI Launches New 8x22B MOE Model by fbdab103 on Tuesday April 09, 2024 @11:20PM (#39986648)
Ooof. I really need to pick up another HD, these model sizes are killer.

Lacking a godly GPU, I will probably hold off for a quanitized version which has the potential to run okish on CPU or my modest GPU, but really appreciate the info.

Re:Mistral AI Launches New 8x22B MOE Model by Jackson__ on Wednesday April 10, 2024 @02:04AM (#39987431)
Unlikely, this model has a max sequence length of 65k, while mistral large is 32k.