81–90 of 261 posts
> Every weight tensor in Rio is, to thousands of standard deviations, the same 0.6/0.4 blend of Nex and Qwen — across all 60 layers and every component of the network. Other finetunes cannot be explained as interpolations. I find it amazing how robust the current deep learning models are. A simple linear combination of every weight did not degrade the performance of the model, but enhanced it.
Not surprised
why not?
The majority of their politicians have ties to organized crime. There is a virtual revolving door between police and crime, where people migrate from one to the other.
It is like Chicago in the 20s, Naples and Medelin in the 80s or Moscow and Culiacan (Sinaloa, Mexico) today.
Earlier quoted context omitted.
How do they just splice two models together?
Out of curiosity, how was it discovered? You would have to look for it to find this linear combination.
Scroll past the first issue to find it. It’s further down.
The model's webpage at https://huggingface.co/prefeitura-rio/Rio-3.5-Open-397B says it's a merge now. It previously didn't contain this paragraph: >The model is built via a merge of https://huggingface.co/nex-agi/Nex-N2-Pro and https://huggingface.co/Qwen/Qwen3.5-397B-A17B , proceeded by On-Policy Distillation from a stronger model. We detected an incorrect upload in the previous version, where the base merged versio…
Edit: I didnt even notice until someone pointed out this was on the Nex-n2 repo not the rio one, now I understand the OP’s confusion! It wasnt framed as an issue which is the norm breakage I think you’re reacting to, as in they didnt ask that the readme be updated etc, but it is common now for folks to use a project’s issue tracker to name and shame them in a place they cant easily ignore. Whether that’s right, proso…
i.e. this is the maintainer posting on their own GitHub Issues.
I'm honestly surprised that they even had the inclination to attempt creating a model. I guess it's bullish that a municipal IT department had the guts to try this?
Wasn’t it already obvious given the awfully familiar parameter numbers?
Earlier quoted context omitted.
Great, now we're defending embezzlement and fraud with public funds on HN, because we really really hate big business. A child caught doing something bad will cry "but my friends also did it!", is that the level of reasoning hackers want to be at?
There are no hackers around here anymore. HN is mainly about business nowadays
The municipality of Rio de Janeiro (via its IT company IplanRIO) released Rio-3.5-Open-397B, presented as a homegrown Qwen3.5 fine-tune that beats comparable open models on benchmarks. The linked issue argues it's actually a weighted merge of ~60% Nex-N2 Pro + ~40% Qwen3.5-397B-A17B - Nex-N2 having been released about a week earlier.
I didn't know model merging like that was possible. (Obviously possible from a pure software standpoint but I'm surprised it's effective)