this post was submitted on 09 Jul 2025
22 points (95.8% liked)

Hacker News

1975 readers
407 users here now

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

founded 10 months ago
MODERATORS
patrick@lemmy.bestiver.se
rssbot@lemmy.bestiver.se
22
OLMo – a fully open LLM outperforming GPT 4o mini (allenai.org)
submitted 1 day ago by rssbot@lemmy.bestiver.se to c/hackernews@lemmy.bestiver.se
2 comments fedilink hide all child comments
 

Comments

top 2 comments
sorted by: hot top controversial new old
[–] pennomi@lemmy.world 6 points 1 day ago

Fully open is extremely good, it uses entirely open datasets and has all training and inference code. We need more things like that.

[–] BaroqueInMind@piefed.social 4 points 1 day ago

Just checked this out on HF and this shit isn't even on the top 100 in any leaderboard. What gives?