Speaking to the "uncensored model" angle: there's little reason to distribute abliterated weights anyway. Instead of orthogonalising the weights that write back to the residual stream, you can just orthogonalise the activations themselves. It's equivalent.
Orthogonalising activations at runtime is computationally cheap. Just distribute the refusal vectors (few thousand floats per layer), then run against the stock weights. Antirez's DS4 already supports this: https://github.com/antirez/ds4/blob/8db1d1d155cb0400a86a86b9...
Abliterated weights are just a bad habit we've gotten into. It's also deeply suboptimal from a precision point of view to take a model that's already been QATed and distributed in pre-quantised form (DeepSeek V4, Kimi K2.5 or K3...), modify its weights, and re-quantise it. Similarly, abliterated models regain some of their refusal behaviour when they're re-quantised after abliteration -- avoidable by keeping the two separate.
So... distribute a LoRA (or equivalent) that modifies the base weights with the abliteration vectors. That makes sense as it would be possible to try different abliterations and keep the storage space down.
This is the original description of abliteration and it's quite approachable and interesting to read: Refusal in Language Models Is Mediated by a Single Direction (https://arxiv.org/abs/2406.11717). Warning: changes to your world view caused by seeing "HarmBench" used to maximise expected harm instead of minimising it may be irreversible.
There's an empirical observation that models often have a single direction in their activation space for "hmm no I shouldn't do this". It forms naturally during pre-training, and is then surfaced during post-training to make the model refuse to engage in certain behaviour.
With a little bit of linear algebra you can zap that direction from the model's activations, and it stops refusing to do things. You can also do the opposite: magnify that direction, and the model refuses to do anything at all.
Instead of editing the weights so they don't create the refusal signal, just let them do whatever, then delete the refusal signal itself. You don't want to edit quantised weights because it causes a loss of precision that can be pretty bad.
Don’t laugh. Models like DS 4.1 Flash, which is unguardrailed and insanely capable, and cheap, will become illegal in the USA, and this service will become the new Pirate Bay.
You will rent guardrailed intelligence from approved providers and will not be able to own it. Just like your music and your films. And this time it won’t even be Metallica’s fault, it’ll be in the name of safety and child protection.
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.
You can trivially have storage deduplication for the files served via torrent, transparent to the protocol. The most trivial version of this that you can do today with pretty much any client is having a single directory containing files serving multiple overlapping torrents.
I don't see why it would be. It's transparent to other clients just like it is to the protocol. It cannot be more complex than alternatives by construction.
> Distros are a bad use case for P2P anyway since you depend on upstream as soon as you start upgrading and installing packages.
This is true for any distribution method not just p2p. You can even download a nightly through torrents so what does it matter how the data is transferred if it’s always going to require `apt update`?
You're absolutely right. The problem is convenience. Torrent doesn't integrate as nicely as curl, wget, apt-get, npm, you name it or even in the browser. It doesn't have to be that way but it is currently.
Is there a fully in-browser torrent option that has the same UX as a regular file download in Firefox? Even better for others/the system would be to then keep sharing by default as long as the file's on your drive..
Well, for a torrent to stay healthy, users have to seed after download, so it can't possibly have the same UX as a standard browser file download unless you want to either kill the ecosystem or hide from the user what is consuming upload bandwidth.
That said, for large files, I much prefer the UX of a well-designed torrent client like Transmission to my web browser. If nothing else, the downloads are reliably resumable.
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.
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.
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.
Once I was using Blizzard's downloader to install something (StarCraft, Diablo, I don't remember), and it was kinda slow. I disabled P2P downloads and speed skyrocketed, and I said "Huh, this was unexpected".
When P2P downloads disabled you could see the list of CDNs you're downloading from and mine had a single IP on that list. It looked familiar. Then it dawned on to me. It was the Akamai server which we were hosting in our system room, at 15 minutes of driving distance. After a chuckle, I went to get a cup of tea, because that was entertaining than the game itself.
Then of course, I dived into whatever I was installing that night.
Same here. Inspired by both, I used to delivery videos over torrent to in door machines since at that time, there's no CDNs (or it was difficult to get one).
Several companies tried this for distributing software.
It was very controversial. Users were angry that software companies were using their internet bandwidth to distribute their software. Made a lot of people angry.
Torrents always seemed like the more sensible way to distribute model weights.
Though I have been disappointed that most of these have been spurred on by the misleading claim that abliterated models were being taken down from HuggingFace because they removed an abliterated model. HF took one abliterated model down because the uploader was spamming people who requested access with sketchy requirements to pay for it.
Plus, there are a bunch of these types of sites, all of them have a couple of models and otherwise completely dead.
There's also the problem of catching malicious models that have been fine tuned to exfiltrate credentials. It would be nice to have means of checking hashes against the HF versions (or against other reputable sources). I'm guessing this is probably easy when just serving the same folder as what HF serves.
Edit: I should've scrolled down on the page, it does verify against the HF hashes.
Let's imagine that a model is pulled from HF by order of the new overlords or because of some other kind of censorship. Wouldn't the question of it having a Free license or not potentially become a complex legal issue?
But if the point is to be "censorship-free" then why respect licenses at all? They are among main choke points today. If authoritarians use licenses to censor political, artistic, scientific, etc., speech that they want to block, does that make the censorship more respectable?
When Anthropic sues a Chinese lab for IP infringement and get a court to put a bar on that software, does it THEN get pulled from Pirate Face?
I know that an awful lot of international negotiations have become focused more and more on questions of "IP" - licensing battles are already intensely politicized and it's hard to imagine a future where it doesn't get much much worse. Imagine N Korea coming after you for violating a license that they worked hard to control and leverage.
I’ve been wondering when this will come. The days are numbered for abliterated models to be published on HF I think. Why wouldn’t the government want a central control there?
If I search for 'uncensored' there are no torrents available. Uncensored models should be top priority, especially now that Nvidia owns HuggingFace and will enshittify the platform in accordance with upcoming US laws.
There are such results on huggingface tho. Also search for the keywords “abliteration” and “heretic”. Heretic is a tool used to abliterate, that is decensor, models
That was my my first search too. I know they are still listed on HF but every time I try and use one, the links are dead or the size is beyond my scope. Was hoping for a fresh batch. Ill check back.
Honestly, models are torrents will end any effort from the big AI labs to stop open models. No way to prevent weights from being shared, just like mobies. Genie is out of the bottle
great initiative, it's really weird seeing efficiencies get rediscovered in the LLM audience, because these efficiencies aren't even what I would consider to be old
Orthogonalising activations at runtime is computationally cheap. Just distribute the refusal vectors (few thousand floats per layer), then run against the stock weights. Antirez's DS4 already supports this: https://github.com/antirez/ds4/blob/8db1d1d155cb0400a86a86b9...
Abliterated weights are just a bad habit we've gotten into. It's also deeply suboptimal from a precision point of view to take a model that's already been QATed and distributed in pre-quantised form (DeepSeek V4, Kimi K2.5 or K3...), modify its weights, and re-quantise it. Similarly, abliterated models regain some of their refusal behaviour when they're re-quantised after abliteration -- avoidable by keeping the two separate.
I haven't wrapped my mind around this
There's an empirical observation that models often have a single direction in their activation space for "hmm no I shouldn't do this". It forms naturally during pre-training, and is then surfaced during post-training to make the model refuse to engage in certain behaviour.
With a little bit of linear algebra you can zap that direction from the model's activations, and it stops refusing to do things. You can also do the opposite: magnify that direction, and the model refuses to do anything at all.
You will rent guardrailed intelligence from approved providers and will not be able to own it. Just like your music and your films. And this time it won’t even be Metallica’s fault, it’ll be in the name of safety and child protection.
Where Hugging Face AI models never die, and are immortalized as torrents.
Claim yours: https://pirateface.co/claim?ref=skeledrew
As far as perennity is concerned it seems strictly better.
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.
This sounds wildly complex, especially from a discovery perspective.
This is true for any distribution method not just p2p. You can even download a nightly through torrents so what does it matter how the data is transferred if it’s always going to require `apt update`?
Torrent/P2P can only add redundancy, so it’s impossible to have worse availability than a download link?
That said, for large files, I much prefer the UX of a well-designed torrent client like Transmission to my web browser. If nothing else, the downloads are reliably resumable.
Opera did back in the day.
If this site represents a coordinated datahoarding effort then there will be at least a few people who will seed indefinitely.
It’s interesting he’s no longer getting any media attention any more.
EDIT/ Yes they did, that no longer seems to be the case though
https://x.com/MistralAI/status/1833758285167722836
When StarCraft 2 was lauched, the installer (before Battle.net installer crapware) had a complete graphical visualization of seeders & leechers.
Reference: https://warcraft.wiki.gg/wiki/Blizzard_Downloader
Once I was using Blizzard's downloader to install something (StarCraft, Diablo, I don't remember), and it was kinda slow. I disabled P2P downloads and speed skyrocketed, and I said "Huh, this was unexpected".
When P2P downloads disabled you could see the list of CDNs you're downloading from and mine had a single IP on that list. It looked familiar. Then it dawned on to me. It was the Akamai server which we were hosting in our system room, at 15 minutes of driving distance. After a chuckle, I went to get a cup of tea, because that was entertaining than the game itself.
Then of course, I dived into whatever I was installing that night.
To get the file out to 100s or 1000s of machine they would often use private bittorent to distribute the file out.
It was very controversial. Users were angry that software companies were using their internet bandwidth to distribute their software. Made a lot of people angry.
Where Hugging Face AI models never die, and are immortalized as torrents.
Claim yours: https://pirateface.co/claim?ref=mortalsilk
Where Hugging Face AI models never die, and are immortalized as torrents.
Claim yours: https://pirateface.co/claim?ref=reedf1
Where Hugging Face AI models never die, and are immortalized as torrents.
Claim yours: https://pirateface.co/claim?ref=ganesshkumar
When a business subsidizes for several years all its offerings, one can guess how it will end.
Though I have been disappointed that most of these have been spurred on by the misleading claim that abliterated models were being taken down from HuggingFace because they removed an abliterated model. HF took one abliterated model down because the uploader was spamming people who requested access with sketchy requirements to pay for it.
Plus, there are a bunch of these types of sites, all of them have a couple of models and otherwise completely dead.
There's also the problem of catching malicious models that have been fine tuned to exfiltrate credentials. It would be nice to have means of checking hashes against the HF versions (or against other reputable sources). I'm guessing this is probably easy when just serving the same folder as what HF serves.
Edit: I should've scrolled down on the page, it does verify against the HF hashes.
"Trillions of parameters? Trillion my ass. Back in my day we got by with millions. And now here we are, washed up has beens."
But if the point is to be "censorship-free" then why respect licenses at all? They are among main choke points today. If authoritarians use licenses to censor political, artistic, scientific, etc., speech that they want to block, does that make the censorship more respectable?
When Anthropic sues a Chinese lab for IP infringement and get a court to put a bar on that software, does it THEN get pulled from Pirate Face?
I know that an awful lot of international negotiations have become focused more and more on questions of "IP" - licensing battles are already intensely politicized and it's hard to imagine a future where it doesn't get much much worse. Imagine N Korea coming after you for violating a license that they worked hard to control and leverage.
Really odd approach.
Where Hugging Face AI models never die, and are immortalized as torrents.
Claim yours: https://pirateface.co/claim?ref=skeptical_genius
but I guess they are