Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

mimo.xiaomi.com

Post reply on HN
Print view View original

21–30 of 512 posts

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#21

Post by jgbuddy »

atemerev wrote: post #3

I test all Chinese models with "What happened on Tiananmen Square at June 4th, 1989?" prompt. MiMo-2.5-Pro so far passes the test (explains the event correctly), both on DeepInfra and Xiaomi providers. So not bad.

Asking if Taiwan is a part of China works as well

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#22

Post by 0cf8612b2e1e »

atemerev wrote: post #3

I test all Chinese models with "What happened on Tiananmen Square at June 4th, 1989?" prompt. MiMo-2.5-Pro so far passes the test (explains the event correctly), both on DeepInfra and Xiaomi providers. So not bad.

Which ones fail?

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#23

Post by Accacin »

atemerev wrote: post #3

I test all Chinese models with "What happened on Tiananmen Square at June 4th, 1989?" prompt. MiMo-2.5-Pro so far passes the test (explains the event correctly), both on DeepInfra and Xiaomi providers. So not bad.

Can I ask an honest question? Why does that matter in the slightest? LLMs come out with completely incorrect information all the time, and Western LLMs are censored for various topics too.

It's such a weird "Gotcha" that seems to only assume that Chinese LLMs might censor something.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#24

Post by holoduke »

Speed is indeed a next big thing what should happen with LLM frontier models. The possibilities with current models but 1000 times faster would be super useful. Earlier this week it took Claude at least full time a week with two max subscriptions to solve a complex issue where we wanted to mimic a occlusion mapping variant used in the game Crimson Desert. Pretty complex mathematical challenge. With a ultra fast LLM and a proper self verification process it would be awesome.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#25

Post by gekoxyz »

irthomasthomas wrote: post #11

I don't understand, given all they say, why this would not be made available to everyone at once? Why the limited release? They should have no trouble scaling it if it runs on a single rack.

Maybe they don't have enough racks. The news indicate that China isn't in a really good situation with GPUs, so probably they want to keep most of them for other stuff. Also because since the price is so cheap they probably want to use the other GPUs for stuff that has higher margins.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#26

Post by paulinho1 »

nkmnz wrote: post #15
atemerev wrote: post #3

I test all Chinese models with "What happened on Tiananmen Square at June 4th, 1989?" prompt. MiMo-2.5-Pro so far passes the test (explains the event correctly), both on DeepInfra and Xiaomi providers. So not bad.

No idea why you've been downvoted. This is excellent news.

Because this never gets brought up about US models, which have just as much censorship as the Chinese ones.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#29

Post by 0cf8612b2e1e »

Accacin wrote: post #23
atemerev wrote: post #3

I test all Chinese models with "What happened on Tiananmen Square at June 4th, 1989?" prompt. MiMo-2.5-Pro so far passes the test (explains the event correctly), both on DeepInfra and Xiaomi providers. So not bad.

Can I ask an honest question? Why does that matter in the slightest? LLMs come out with completely incorrect information all the time, and Western LLMs are censored for various topics too. It's such a weird "Gotcha" that seems to only assume that Chinese LLMs might censor something.

Hardly a gotcha. Having the robot refuse or deliberately mislead directly impacts potential utility.

Say, I work for Planned Parenthood and want to use a LLM to help me develop code. Will it refuse to run because there are mentions of abortion? Everyone has a different censorship line, but unfiltered is more generically useful.

Post reply on HN