←back to thread

Olmo 3: Charting a path through the model flow to lead open-source AI

(allenai.org)
361 points mseri | 2 comments | 21 Nov 25 06:50 UTC | HN request time: 0s | source
Show context
stavros ◴[21 Nov 25 08:00 UTC] No.46002252[source]▶
> the best fully open 32B-scale thinking model

It's absolutely fantastic that they're releasing an actually OSS model, but isn't "the best fully open" a bit of a low bar? I'm not aware of any other fully open models.

replies(9): >>46002293 #>>46002338 #>>46002597 #>>46002842 #>>46002944 #>>46003313 #>>46004177 #>>46006028 #>>46006176 #
1. maxloh ◴[21 Nov 25 09:53 UTC] No.46002944[source]▶
AFSIK, when they use the term "fully open", they mean open dataset and open training code. The Olmo series of models are the only mainstream models out there that satisfy this requirement, hence the clause.

> We go beyond just releasing model weights - we provide our training code, training data, our model weights, and our recipes.

https://docs.allenai.org/#truly-open

replies(1): >>46003698 #
2. stavros ◴[21 Nov 25 12:01 UTC] No.46003698[source]▶
Yes, and that's why saying this is "the best" is a tautology. If it's the only one, it's obviously the best, and the worst, and everything.