News for hackers. Stuff that matters.

A comment on Rio de Janeiro's "homegrown" LLM appears to be a merge of an existing model. Parent comment

Re:Rio de Janeiro's "homegrown" LLM appears to be a merge of... by jwitthuhn on Monday June 15, 2026 @02:37AM (#48537417)
They did upload the wrong model but as of the time of writing they have not fixed it. Right now, 12 hours after they took the old one down, there is simply no model present in their huggingface repo.
[ Parent | on HN ]
Re:Rio de Janeiro's "homegrown" LLM appears to be a merge of... by xiphias2 on Monday June 15, 2026 @04:15AM (#48538132)
I guess they will upload it later, it seems like an honest mistake to me.

Anyways SwiTransformer paper looks interesting and doing a post training to optimize for it looks interesting as well.

[ Parent | on HN ]
Re:Rio de Janeiro's "homegrown" LLM appears to be a merge of... by 00index on Tuesday June 16, 2026 @12:31AM (#48550608)
Looks like they couldn't find the correct weights. https://x.com/IplanRio_rj/status/2066693494769348946
[ Parent | on HN ]