both repositories for pre-training and post-training are actually empty... someone might have jumped the gun on the release.
K2 Horizon: A connected fleet of six open models
11–20 of 141 posts
Re: K2 Horizon: A connected fleet of six open models
#12Earlier quoted context omitted.
But it's missing the all-important charts that the blog had before it started asking for authentication.
You can find some of the charts on huggingface https://huggingface.co/collections/IFM/k2-horizon
Thanks! Qwen-3.8 27B seems to benchmark better but I'd like to try this some time.
Re: K2 Horizon: A connected fleet of six open models
#13A bit off topic, but I think I'm starting to get model fatigue. These come out 10x faster than new Javascript frameworks were coming out 10 years ago (at least new models are far easier to adopt).
Just wait until RSI gains enough traction. We'll be compute-limited rather than labor-limited.
Re: K2 Horizon: A connected fleet of six open models
#14A bit off topic, but I think I'm starting to get model fatigue. These come out 10x faster than new Javascript frameworks were coming out 10 years ago (at least new models are far easier to adopt).
At least this one can claim being fully open to differentiate it
Re: K2 Horizon: A connected fleet of six open models
#15Fully open models really need to be a big part of the AI future. That includes all source code, open training data, how it's organized, fed to the model, processed, etc. Until that becomes a thing you're always going to be left wondering what exactly lies underneath the closed model you are using, leaving open the possibility for societal manipulation.
Why? Sure, I’d prefer it, too, but this is just another GNU/Linux vs. macOS situation: most of us would prefer the first, but actually get shit done on the latter.
Re: K2 Horizon: A connected fleet of six open models
#16Not to be confused with Kimi K2. Out of all the names they could've used, they picked one that would be confusing.
Re: K2 Horizon: A connected fleet of six open models
#17Fully open models really need to be a big part of the AI future. That includes all source code, open training data, how it's organized, fed to the model, processed, etc. Until that becomes a thing you're always going to be left wondering what exactly lies underneath the closed model you are using, leaving open the possibility for societal manipulation.
Why? Sure, I’d prefer it, too, but this is just another GNU/Linux vs. macOS situation: most of us would prefer the first, but actually get shit done on the latter.
which is why everyone runs docker on mac, to get shit done.
Re: K2 Horizon: A connected fleet of six open models
#18Fully open models really need to be a big part of the AI future. That includes all source code, open training data, how it's organized, fed to the model, processed, etc. Until that becomes a thing you're always going to be left wondering what exactly lies underneath the closed model you are using, leaving open the possibility for societal manipulation.
The training data would need to have a permissive license for this to be possible.
Re: K2 Horizon: A connected fleet of six open models
#19The comparisons with other models here are odd.. the other models change depending on the task. It would be far more useful to at least compare against the more recent open models (DS4Flash/GLM53Flash/Qwen38).
Re: K2 Horizon: A connected fleet of six open models
#20Fully open models really need to be a big part of the AI future. That includes all source code, open training data, how it's organized, fed to the model, processed, etc. Until that becomes a thing you're always going to be left wondering what exactly lies underneath the closed model you are using, leaving open the possibility for societal manipulation.
The training data would need to have a permissive license for this to be possible.
You could sidestep it by running non-permissibly licensed training data that you purchased through an LLM. Legal attitude so far seems to be that this is transformative as long as it's not 1:1. The question on whether or not the end result is copyrightable of course remains controversial and inconsistent, but that question is also fairly irrelevent. You don't get more libre than public domain.
That's a fair amount of computational and labor overhead mind you, as you'll need to verify and prune the quality of your mountain of synthetic data, but certainly possible.
Though this assumes the legal system is a rational actor playing by the set of rules it claims to. In fact, I highly suspect you could get very unlucky and get an unfavorable ruling against you, because you stepped on a big pile of money's toes in the process of doing this.