I just find it hilarious how approximately 100% of models beat all other models on benchmarks.
What do you mean?
Mixtral 8x22B
11–20 of 252 posts
Re: Mixtral 8x22B
#12Isn't equating active parameters with cost a little unfair since you still need full memory for all the inactive parameters?
Re: Mixtral 8x22B
#13Is this the best permissively licensed model out there?
Today. Might change tomorrow at the pace this sector is at.
Re: Mixtral 8x22B
#14"64K tokens context window" I do wish they had managed to extend it to at least 128K to match the capabilities of GPT-4 Turbo
Maybe this limit will become a joke when looking back? Can you imagine reaching a trillion tokens context window in the future, as Sam speculated on Lex's podcast?
Re: Mixtral 8x22B
#15Is this the best permissively licensed model out there?
So far it is Command R+. Let's see how this will fare on Chatbot Arena after a few weeks of use.
Re: Mixtral 8x22B
#16I just find it hilarious how approximately 100% of models beat all other models on benchmarks.
What do you mean?
Virtually every announcement of a new model release has some sort of table or graph matching it up against a bunch of other models on various benchmarks, and they're always selected in such a way that the newly-released model dominates along several axes.
It turns interpreting the results into an exercise in detecting which models and benchmarks were omitted.
Re: Mixtral 8x22B
#17Great to see such free to use and self-hostable models, but it's said that open now means only that. One cannot replicate this model without access to the training data.
...And a massive pile of cash/compute hardware.
not that massive, we're talking six figures. There was a blogpost about this a while back on the startpage of HN.
Re: Mixtral 8x22B
#18How much vram is need to run this?
Re: Mixtral 8x22B
#19I just find it hilarious how approximately 100% of models beat all other models on benchmarks.
gotta cherry pick your benchmarks as much as possible
Re: Mixtral 8x22B
#20I'm really excited about this model. Just need someone to quantize it to ~3 bits so it'll run on a 64GB MacBook Pro. I've gotten a lot of use from the 8x7b model. Paired with llamafile and it's just so good.