Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms
firelex · 569 points · 222 comments · wczoraj · Open original
Comments
5 preview comments · loading full thread
Log in to use comments
Log in to h4cker, then connect Hacker News to publish comments.
HAhadlockwczoraj
If you're looking for a more impressive doom example, I put together laya-duum which uses open source micropython implementation of doom (duum) and freeware freedoom1.wad. It uses the standard jev api and will play through the first two levels to completion: https://github.com/Hadlock/laya-duum
VEvektormemorywczoraj
Can someone remove the extra LLM and just have an embedder do the classifier work?
It's turning into pimp my llm...
TRtrebligdivadwczoraj
What proportion of commercial LLM use is classification? I'm just wondering what happens to business AI spending/data centre usage when they realise they don't need full LLMs.
AGAgentMasterRacewczoraj
I compared it to Jev in my current use cases and it's very inaccurate. 70% vs 94% . for classification, it's unacceptable.
OLolwmcwczoraj
Sorry, do we have actual clear implementation details for Jev? I keep seeing these "recreations" or "Do Jev at home" but do we have access to their architecture? I haven't even used the product, I just find it strange.
Comments
5 preview comments · loading full threadLog in to h4cker, then connect Hacker News to publish comments.
If you're looking for a more impressive doom example, I put together laya-duum which uses open source micropython implementation of doom (duum) and freeware freedoom1.wad. It uses the standard jev api and will play through the first two levels to completion: https://github.com/Hadlock/laya-duum
Can someone remove the extra LLM and just have an embedder do the classifier work? It's turning into pimp my llm...
What proportion of commercial LLM use is classification? I'm just wondering what happens to business AI spending/data centre usage when they realise they don't need full LLMs.
I compared it to Jev in my current use cases and it's very inaccurate. 70% vs 94% . for classification, it's unacceptable.
Sorry, do we have actual clear implementation details for Jev? I keep seeing these "recreations" or "Do Jev at home" but do we have access to their architecture? I haven't even used the product, I just find it strange.