Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Neutrino-1 8B

fermionresearch.com

Post reply on HN
Print view View original

11–20 of 51 posts

Re: Neutrino-1 8B

#11

Post by NetOpWibby »

There’s a new announcement every other day wrt models. How do y’all keep track of them all same know what’s decent? Good grief!

And if it’s decent today, it’s shit in eight months! I tool hop as much as the next dev but this is a bit much.

Re: Neutrino-1 8B

#13

Post by weikju »

NetOpWibby wrote: post #11

There’s a new announcement every other day wrt models. How do y’all keep track of them all same know what’s decent? Good grief! And if it’s decent today, it’s shit in eight months! I tool hop as much as the next dev but this is a bit much.

I just tune out. It’s not worth knowing, following every development in the field. If something works now it will probably work in 8 months even if it’s no longer the new hype thing. Who cares.

Not using any of it is also a valid option though it doesn’t satisfy your FOMO. But nothing ever will.

Re: Neutrino-1 8B

#14

Post by dofm »

Twirrim wrote: post #5
kamranjon wrote: post #4

There's a really interesting trend of labs using "proprietary" methods to convert existing models to a compressed ternary format. PrismML actually targeted the same Qwen 8b model and got it down to 1.75gb here: https://prismml.com/news/ternary-bonsai I wonder how proprietary it all is though, since the BitNet b1.58 paper has been out for a couple years now: https://arxiv.org/abs/2402.17764 From the wikipedia on 1.58…

Independent testing of prismml suggest quite a capability drop off outside of their cherry picked benchmarks. I'll be curious to see what this model achieves though.

I really had high hopes for the larger Ternary Bonsai and it feels like there is scope to improve, but I get the sense (albeit a naïve, probably not fully informed sense) that improvement can perhaps only come by training directly into ternary.

Re: Neutrino-1 8B

#15

Post by Havoc »

Can’t say I’m a fan of containers for this. A big chunk of local LLM gains come (imo) from the open modular nature of llama.cpp and friends. Easy to modify. Easy to experiment.

Containers are the proprietary binary blob in hardware world equivalent

Re: Neutrino-1 8B

#17

Post by secult »

There is not a single person mentioned on the website, github created 3 days ago, no real contact, everything hidden. Completely anonymous. Domain owner hidden.

Re: Neutrino-1 8B

#19

Post by LtdJorge »

kamranjon wrote: post #6
Twirrim wrote: post #5

Earlier quoted context omitted.

Independent testing of prismml suggest quite a capability drop off outside of their cherry picked benchmarks. I'll be curious to see what this model achieves though.

Unfortunately Fermion Research appears to entirely AI generate all of their content here, even for the research section: https://www.fermionresearch.com/research/neutrino-8b/ "Neutrino-1 8B was trained natively in its shipping format. There is no full-precision product model that was rounded afterward: the ternary representation is the medium the weights learned in, and the training methods that hold this quality at…

I guess it's saying how many of the weights are -1, 0 or +1.

Re: Neutrino-1 8B

#20

Post by naruhodo »

moinism wrote: post #7

The content on that page is too AI-generated to make sense to me; I don't understand what the model is for.

I have the same question.

I get that it’s designed to run on a CPU, big GPU or MacBook (although the way that was phrased confused me at first).

I’m struggling with what a “decoder-only” model is good for.

Post reply on HN