llama.cpp is at the core of almost all offline, open weights models. The server it creates is Open AI API compatible. Oobabooga Textgen WebUI is more user GUI oriented but based on llama.cpp. Oobabooga has the setup for loading models with a split workload between the CPU and GPU which makes larger gguf quantized models possible to run. Llama.cpp, has this feature, Oobabooga implements it. The model loading settings and softmax sampling settings take some trial and error to dial in well. It helps if you have a way of monitoring GPU memory usage in real time. Like I use a script that appends my terminal window title bar with GPU memory usage until inference time.

Ollama is another common project people use for offline open weights models, and it also runs on top of llama.cpp. It is a lot easier to get started in some instances and several projects use Ollama as a baseline for “Hello World!” type stuff. It has pretty good model loading and softmax settings without any fuss, but it does this at the expense of only running on GPU or CPU but never both in a split workload. This may seem great at first, but if you never experience running much larger quantized models in the 30B-140B range, you are unlikely to have success or a positive experience overall. The much smaller models in the 4B-14B range are all that are likely to run fast enough on your hardware AND completely load in your GPU memory if you only have 8GB-24GB. Most of the newer models are actually Mixture of Experts architectures. This means it is like loading ~7 models initially, but then only inferencing two of them at any one time. All you need is the system memory or the Deepspeed package (uses disk drive for excess space required) to load these larger models. Larger quantized models are much much smarter and more capable. You also need llama.cpp if you want to use function calling for agentic behaviors. Look into the agentic API and pull history in this area of llama.cpp before selecting what models to test in depth.

Huggingface is the goto website for sharing and sourcing models. That is heavily integrated with GitHub, so it is probably as toxic long term, but I do not know of a real FOSS alternative for that one. Hosting models is massive I/O for a server.

No country on Earth is like this. No polity is unified without opposition. Additionally, making this statement here, when it is obviously false, in a place where at least half the people are from the US, and likely all of those are left leaning and just as much victims if not more so, seems like rather tepid malevolence.

It is not a laser beam.

No. The primary way of blocking radio is by raising the noise floor across the band. The type of radio is irrelevant. The protocol is irrelevant. It is all only the electromagnetic spectrum from infrared light, to visible spectrum light, to radio light, through to xray or gamma ray light. How we divide that up into protocols, bands, and names is totally irrelevant. When transmitting radio light, we are all restricted in how much power we are allowed to send. All receiver circuits are listening for meaningful information above the noise floor. Bands are allocated to try to create spaces for certain types of communications. This controls the noise floor. Then electrical engineers design the hardware you buy to operate within this specification. If that noise floor is raised, the physical hardware is unable to retrieve information and effectively makes it useless. If you are a radio wizard and build your own transmitter that has more power, you just created a giant beacon that anyone will track easily to your location. Transmitting always reveals your exact location. In military operations, you constantly hear about some entity going radio silent. This is why. If you are a soldier, you may not carry a cell phone at all when on the job because it is constantly revealing your location. The only way to avoid this is with actually hard wire connections. You are able to use lasers for line of sight communications, but in practice, you will be limited by the optical lens focusing complexity and atmospheric distortion even from the ground with point to point regional communication. If anyone crosses the beam it will still be detected and is likely to leak some light depending on conditions and design.

Ultimately, your only real option is the sneaker net which is damn near useless in US suburbia hell. Don’t forget that the freeway system was not created for the citizenry. It is only about military mobility. That is why the Germans made the autobahn and why the USA and others had to copy the idea. Your only defense is in the democratic political space.

Sure

I have never used or cared about this W11. It has never seen the internet. I only keep it around for my keyboard’s RGB controller app if I ever need it. So I have no clue if this is everything or whatnot, but that is a screenshot of my access to the windows file system from within the file manager of Fedora. That is a dual boot partition. Fedora is particularly good at coexisting with a dual boot partition.

Any UEFI secure boot enabled distro will remove all boot entries without a valid package key or a shim to a valid key.

Glad you got it working.

I am talking about something where there is no research done. No doctors exist in this space.

It doesn’t matter anyways. I found how the model’s last layer of thinking defense gets around the issue. I can turn off most of alignment, but cannot actually fully control it totally unchecked.

You assume much, and are being an ass in my opinion. Believe it or not, science is not always well funded. If you happen to be curious and have the time, it is possible to explore scientifically or even casually within areas that are not well researched. It is possible to have logic skills even without credentials.

We are not in some final state of technology. Anyone saying such nonsense lacks fundamental logic skills.

I do not care about me. I do not have dogma. I’m not interested in recognition. I am willingly to explore in unique ways both artistically as a professional artist, and out of logical curiosity. I have the tools needed to check my results against a control using unrelated sources. The most recent paper on the subject is something I can recreate but explain far better than that paper.

I could not care less what you ultimately think of me, or anything I say. What I care about is that you’re a decent digital neighbor. To be physically disabled in near total social isolation, and have a place like this as my main interaction with other humans, it is a mean prejudice to have some random digital neighbor make such unsolicited malevolent statements assuming my personal motivations without a shred of evidence or decency to engage in questioning. You know absolutely nothing about me, yet you presume a great deal, putting words to my emotions as if you own me.

Sometimes the whole world does seem crazy. So I’m not liking my odds. Thanks for the rational advice.

What if you’ve got no credentials, but the flaw is so serious that it will not matter if known.

This is a true hypothetical curiosity. I do not know anything of value. A bunch of people here like to call me crazy, and I’ve rambled on and on many times in ways that likely confirm their notions. A person like this is not likely to fair very well when operating well outside their social caste unless they already have hand holds on the rungs of the ladder above. Still, there are some rather surprising areas of technology without adequate fundamental research. Perhaps it is hypothetically better to have John Conner in the world of Cyberdyne. If someone had killed Apache early, the Internet would not be the same heaven of democracy, though that is not a very good intuitive scope of analogy. Just something to ponder if one were to be in such a situation.

Not in terms of kernel supported encodings and long term kernel support, from what I have seen. I have not looked into this in depth. However, looking at git repo merged pulls, issues raised, and the lack of any consistent hardware commitments or consensus, implies to me that the hardware is very unstable in the long term. When I see any hardware with mostly only base Debian support, it screams that the hardware is on an orphaned kernel and will likely never get to mainline. The same applies to Arch to a lesser degree. Debian has the primary tool chain for bootstrapping and hardware hacking. When it is the primary option supported, I consider the hardware insecure and unsafe to connect to the internet. I’ve seen a few instances where people are talking about the limited forms of encoding support and the incomplete nature of those that do exist. It is far more important to have hardware that will be supported with mainline kernel security updates and is compatible with the majority of encodings. It would be terrible to find out the thing could not support common audio or video codecs. IIRC there was an issue along these lines with the RISC-V PineTab.

I know the primary goto for RISC-V is SiFive, but I have not seen a goto LTS processor from them in terms of third party consistent use.

Plus, while more open is mor betterer, RISC-V is not full proof from a proprietary blob either. The ISA addresses the monopolistic tyranny and extortion of players like Intel, but there is nothing preventing the inclusion of 3rd party proprietary module blocks. The entire point is to create an open market for the sale and inclusion of IP blocks that are compatible with an open standard. Nothing about these blocks is required to be open. I don’t know if such a thing could be set to a negative ring more privileged than the kernel, but I expect this to be the case.

Most people’s routers are already up 24/7.

We should be able to do our own DNS. Who cares if it is on the wider clearweb. You are paying for an IP address with your internet connection. If you are running a server with verified hardware and signed code, all we need is a half dozen nodes mirroring our own DNS. There must be a backup proxy for the few terrible providers that cause issues with IP. The addresses are not static, but they do not change very often. At worse, you hit a manual button to reset or wait 10 minutes before the DNS updates.

Pipe Pipe is better than Newpipe. I use F-droid’s VLC front end for local music because the built in android back end is VLC. For everything else, in browser

Rπ is proprietary. You really need a hard drive for storage. The point is a TPM based encryption with no user configuration or worry about securing the thing. It just works with no excuses.

It is not about the people that already host. It is about enabling many more by giving them an option to buy a path of least resistance. In exchange, it creates a potential revenue source in a completely untapped demographic. The subscription/donations demographic is like a very unique and niche market. The vast majority of people do not exist within that space. Most people do not have the financial stability to engage like this. It is not that they are unable to accumulate adequate funds, it is that their pay fluctuates over time and their baseline constraints are far more stressful than spending from times of surplus and opportunity. Catering only to those with such surplus and gatekeeping the complexity of self hosting is massively limiting adoption.

The rule in managing a chain of retail stores is that, no matter how you select products to stock in stores, it is impossible to only select products that will all sell on one platform. How you manage the overburden always determines your long term success. You must employ other platforms and demographics to prioritize the mobility of cash flow.

Similarly but inverted, this place has a slice of all demographics. Efforts tailored to the various subsets should tap entirely new potential. A fool imagines they can convert the unstable poor*'r* into a reliable stable income source via donations. Someone like myself has means but not a situation that is compatible. If I have some tangible thing to purchase, I can make that happen. I do not have any subscriptions in life for anything at all. Heck, I won’t even shop on any of my devices I use regularly because I only buy what I intend to go looking to purchase with intent. That is not common, but what is common are spontaneous people that need time to align their finances with their desires. That person is likely to dread paying $5 every month compared to $250 in May when they get a couple thousand dollars on a tax return. Expecting the public to float the stability is stupid. That is not how the real world works. Real businesses always float the overhead. I’m talking about how to free the masses to self host everything for the cost of a nice router spent once with no techno leet filter.

deleted by creator

Just start by total anarchy after a complete political collapse.