Comment by phoyd
7 hours ago
Torrents should really be the preferred method for distributing AI model weights. Why rely on a single point of failure like Hugging Face? BitTorrent was made for exactly this.
7 hours ago
Torrents should really be the preferred method for distributing AI model weights. Why rely on a single point of failure like Hugging Face? BitTorrent was made for exactly this.
In my experience public torrents often die as they grow older. It doesn't help that BitTorrent V1 makes long term seeding annoying, and BitTorrent V2 is almost never used.
I never understood this, is there anything that makes it difficult for the original uploader, the one that supposedly offers the file directly, to offer a torrent instead for the same amount of time?
As far as perennity is concerned it seems strictly better.
Every change to the source is effectively a new torrent. This creates a ton of fragmentation as data is reorganized, remixed, reencoded, and so on.
You can see this with many Linux distros: there is no single Debian torrent that people seed for years because there's always a refreshed version.
Distros are a bad use case for P2P anyway since you depend on upstream as soon as you start upgrading and installing packages.
11 replies →
If they're no longer using that model they may not be willing to continue using their storage for it.
7 replies →
You can add an existing HTTP download as a "web seed" to a torrent, so they don't actually need to do anything for people to share it as a torrent.
The biggest problem with BTv1 was the lack of per-file checksumming, and swarm merging (i.e. individual files have shared seeding pools across torrents). BTv2 specs the latter, but I think only BiglyBT actually implements it. Having both of those features from the get-go would've gone a LONG way to fixing the dead torrent problem.
You only need one person/organization to commit to seeding. The majority of people do not want to seed at all without some sort of incentive.
If this site represents a coordinated datahoarding effort then there will be at least a few people who will seed indefinitely.
The last guy (kimdotcom) who was working on this (incentive for seeding) seems to be heading to the US: https://www.rnz.co.nz/news/science-and-technology/651123/cou...
It’s interesting he’s no longer getting any media attention any more.
Yeah but that's what provider like huggingface could just do, keep seeding the models so they are still accessible
A torrent with a webseed is strictly more resilient than a direct download link alone.
I always wondered why v2 is never used... you can even search for files by their individual hash with it.
Because history is path-dependent, as engineers keep learning over and over again. It doesn't matter whether Plan9 is theoretically superior to Linux - we're all on Linux and nobody's porting all the apps over.
HF is meant to be a single point of control. AI models and Linux distros aren't usually for normies, so distribution via torrents would make sense, especially to save the provider some bandwidth. Ubuntu has been offering torrent downloads for ages. No mention of torrents on HF. I believe most downloads will soon be account/EULA-walled.
Yeah, I thought they were used for this already. Surprised this is news, but also relieved.
IIRC Mistral used to do it, not sure if that's still the case
EDIT/ Yes they did, that no longer seems to be the case though
https://x.com/MistralAI/status/1833758285167722836
ages ago I tried using IPFS to more or less accomplish this, I imagined it to act more like a weights/training data network fs that everyone would be able to participate in.