Retrieval-Augmented Generation (RAG) is probably the tech you’d want. It basically involves a knowledge library being built from the documents you upload, which is then indexed when you ask questions.
NotebookLM by Google is an off the shelf tool that is specialized in this, but you can upload documents to ChatGPT, Copilot, Claude, etc., and get the same benefit.
If you self hosted, Open WebUI with Ollama supports this, but far from the only one.
If you dislike decentralization, then that’s like being on an instance that’s banned every other instance.
Do you mean that you dislike defederation?
Wow, there isn’t a single solution in here with the obvious answer?
You’ll need a domain name. It doesn’t need to be paid - you can use DuckDNS. Note that whoever hosts your DNS needs to support dynamic DNS. I use Cloudflare for this for free (not their other services) even though I bought my domains from Namecheap.
Then, you can either set up Let’s Encrypt on device and have it generate certs in a location Jellyfin knows about (not sure what this entails exactly, as I don’t use this approach) or you can do what I do:
On your router, forward port 443 to the outbound secure port from your PI (which for simplicity’s sake should also be port 443). You likely also need to forward port 80 in order to verify Let’s Encrypt.
If you want to use Jellyfin while on your network and your router doesn’t support NAT loopback requests, then you can use the server’s IP address and expose Jellyfin’s HTTP ports (e.g., 8080) - just make sure to not forward those ports from the router. You’ll have local unencrypted transfers if you do this, though.
Make sure you have secure passwords in Jellyfin. Note that you are vulnerable to a Jellyfin or Traefik vulnerability if one is found, so make sure to keep your software updated.
If you use Docker, I can share some config info with you on how to set this all up with Traefik, Jellyfin, and a dynamic dns services all up with docker-compose services.
Look up “LLM quantization.” The idea is that each parameter is a number; by default they use 16 bits of precision, but if you scale them into smaller sizes, you use less space and have less precision, but you still have the same parameters. There’s not much quality loss going from 16 bits to 8, but it gets more noticeable as you get lower and lower. (That said, there’s are ternary bit models being trained from scratch that use 1.58 bits per parameter and are allegedly just as good as fp16 models of the same parameter count.)
If you’re using a 4-bit quantization, then you need about half that number in VRAM. Q4_K_M is better than Q4, but also a bit larger. Ollama generally defaults to Q4_K_M. If you can handle a higher quantization, Q6_K is generally best. If you can’t quite fit it, Q5_K_M is generally better than any other option, followed by Q5_K_S.
For example, Llama3.3 70B, which has 70.6 billion parameters, has the following sizes for some of its quantizations:
This is why I run a lot of Q4_K_M 70B models on two 3090s.
Generally speaking, there’s not a perceptible quality drop going to Q6_K from 8 bit quantization (though I have heard this is less true with MoE models). Below Q6, there’s a bit of a drop between it and 5 and then 4, but the model’s still decent. Below 4-bit quantizations you can generally get better results from a smaller parameter model at a higher quantization.
TheBloke on Huggingface has a lot of GGUF quantization repos, and most, if not all of them, have a blurb about the different quantization types and which are recommended. When Ollama.com doesn’t have a model I want, I’m generally able to find one there.
You said, and I quote “Find a better way.” I don’t agree with your premise - this is the better way - but I gave you a straightforward, reasonable way to achieve something important to you… and now you’re saying that “This is a discussion of principle.”
You’ve just proven that it doesn’t take a moderator to turn a conversation into a bad joke - you can do it on your own.
It’s a discussion of principle.
This is a foreign concept?
It appears to be a foreign concept for you.
I don’t believe that it’s a fundamentally bad thing to converse in moderated spaces; you do. You say “giving somebody the power to arbitrarily censor and modify our conversation is a fundamentally bad thing” like it’s a fact, indicating you believe this, but you’ve been given the tools to avoid giving others the power to moderate your conversation and you have chosen not to use them. This means that you are saying “I have chosen to do a thing that I believe is fundamentally bad.” Why would anyone trust such a person?
For that matter, is this even a discussion? People clearly don’t agree with you and you haven’t explained your reasoning. If a moderator’s actions are logged and visible to users, and users have the choice of engaging under the purview of a moderator or moving elsewhere, what’s the problem?
It is deeply bad that…
Why?
Yes, I know, trolls, etc…
In other words, “let me ignore valid arguments for why moderation is needed.”
But such action turns any conversation into a bad joke.
It doesn’t.
And anybody who trusts a moderator is a fool.
In places where moderator’s actions are unlogged and they’re not accountable to the community, sure - and that’s true on mainstream social media. Here, moderators are performing a service for the benefit of the community.
Have you never heard the phrase “Trust, but verify?”
Find a better way.
This is the better way.
Then why are you doing that, and why aren’t you at least hosting your own instance?
Yes, I know, trolls etc. But such action turns any conversation into a bad joke. And anybody who trusts a moderator is a fool.
Not just trolls - there’s much worse content out there, some of which can get you sent to jail in most (all?) jurisdictions.
And even ignoring that, many users like their communities to remain focused on a given topic. Moderation allows this to happen without requiring a vetting process prior to posting. Maybe you don’t want that, but most users do.
Find a better way.
Here’s an option: you can code a fork or client that automatically parses the modlog, finds comments and posts that have been removed, and makes them visible in your feed. You could even implement the ability to reply by hosting replies on a different instance or community.
For you and anyone who uses your fork, it’ll be as though they were never removed.
Do you have issues with the above approach?
As a user, you can:
If you host your own instance and communities within that instance, then at that point, you have full control, right? Other instances can de-federate from yours.
I recommend a used 3090, as that has 24 GB of VRAM and generally can be found for $800ish or less (at least when I last checked, in February). It’s much cheaper than a 4090 and while admittedly more expensive than the inexpensive 24GB Nvidia Tesla card (the P40?) it also has much better performance and CUDA support.
I have dual 3090s so my performance won’t translate directly to what a single GPU would get, but it’s pretty easy to find stats on 3090 performance.
From https://www.yalemedicine.org/news/covid-vaccines-reduce-long-covid-risk-new-study-shows
At the pandemic’s onset, approximately 10% of people who suffered COVID-19 infections went on to develop Long COVID. Now, the risk of getting Long COVID has dropped to about 3.5% among vaccinated people (primary series).
…
Then, the team conducted analyses to uncover the reasons for the observed decline in Long COVID cases from the pre-Delta to Omicron eras. About 70% of the decline was attributable to vaccination, they found.
The above post says it has support for Ollama, so I don’t think this is the case… but the instructions in the Readme do make it seem like it’s dependent on OpenAI.
stuck with the GPL forever
If you accept a patch and don’t have the ability to relicense it, you can remove it and re-license the new codebase. You can even re-implement changes made by the patch in many cases, whether those changes are bug fixes or new features.
If you re-implement the change, you do need to ensure this is done in a way that doesn’t cause it to become a derivative work, but it’s much easier if you have copyright to 99% of a work already and only need to re-implement 1% or so. If you’ve received substantial community contributions and the community is opposed to relicensing, it will be much harder to do so.
A clean room implementation - where the person rewriting the code doesn’t look at the original code, and is only given a description of the functionality - which can include a detailed description of the algorithm - is the most defensible way to perform such a rewrite and relicense, but it’s not the only option.
You should generally consult an attorney when relicensing and shouldn’t just do it casually. But a single patch certainly doesn’t mean you’re locked in forever.
16 GB of RAM, though? Is it even optimized for the Ryzen 9950X3D?
And a 4 TB SSD - not even necessarily NVME?
Doesn’t seem high powered to me.
Are you saying that NAT isn’t effectively a firewall or that a NAT firewall isn’t effectively a firewall?
Is there a way to use symlinks instead? I’d think it would be possible, even with Docker - it would just require the torrent directory to be mounted read-only in the same location in every Docker container that had symlinks to files on it.
It’s more likely that this is being done to either:
Depending on setup this can be true with Jellyfin, too. I have a domain registered, use dynamic DNS, and have Traefik direct a subdomain to my Jellyfin server. My mobile clients are configured using that. My local clients use the local static IP.
If my internet goes down, my mobile clients can’t connect, even on the LAN.
Apparently there’s a vulnerability with sending messages with images in them and “she” might be logging people’s IP addresses through that.
If the images are hosted on your instance, this wouldn’t be relevant. If they’re links to an image hosted somewhere, this is possible, but there’d be a lot of noise and not much value. To link accounts to IPs the URLs would themselves need to be different
I checked the urls to the images in my PMs and they’re all hosted on Lemmy.
The argument was not that it didn’t matter if a user didn’t download the entirety of a work from Meta, but that it didn’t matter whether a user downloaded anything from Meta, regardless of whether Meta was a peer or seed at the time.
Theoretically, Meta could have disabled uploading but not blocked their client from signaling that they could upload. This would, according to that argument, still counts as reproducing the works, under the logic that signaling that it was available is the same as “making it available.”
That’s irrelevant to the plaintiff’s argument. And beyond that, it would need to be proven on its own merits. This argument about torrenting wouldn’t be relevant if LLAMA were obviously a derivative creation that wasn’t subject to fair use protections.
It’s also irrelevant if Gemini can reproduce a work, as Meta did not create Gemini.
Does any Llama model reproduce the entirety of The Bedwetter by Sarah Silverman if you provide the first paragraph? Does it even get the first chapter? I highly doubt it.
There have been lawsuits against both ISPs and VPNs in recent years for being complicit in copyright infringement, but that’s a bit different. Generally speaking, there are laws, like the DMCA, that specifically limit the liability of network providers and network services, so long as they respect things like takedown notices.