What does an MCP server do?

The point in time after the first qbit based supercomputers transitioned from theoretical abstraction to physical proven reality. Thus opening up the can-of-worms of feasabily cracking classical cryptographic encryptions like an egg within human acceptable time frames instead of longer-than-the-universes-lifespan timeframes… Thanks, superposition probability based parallel computations.

Thank you for deciding to engage with our community here! You’re in good company.

Kobold just released a bunch of tools for quant making you may want to check out.

Kcpp_tools

I have not made my own quants. I usually just find whatever imatrix gguf bartowlski or the other top makers on HF release.

I too am in the process of upgrading my homelab and opening up my model engine as a semi public service. The biggest performance gains ive found are using CUDA and loading everything in vram. So far just been working with my old nvidia 1070ti 8gb card.

Havent tried vllm engine just kobold. I hear good things about vllm it will be something to look into sometime. I’m happy and comfortable with my model engine system as it got everything setup just the way I want is but I’m always open to performance optimization.

If you havent already try running vllm with its CPU nicencess set to highest priority. If vllm can use flash attention try that too.

I’m just enough of a computer nerd to get the gist of technical things and set everything up software/networking side. Bought a domain name, set up a web server and hardened it. Kobolds webui didnt come with https SSL/TLS cert handling so I needed to get a reverse proxy working to get the connection properly encrypted.

I am really passionate about this even though so much of the technical nitty gritty under the hood behind models goes over my head. I was inspired enough to buy a p100 Tesla 16gb and try shoving it into an old gaming desktop which is my current homelab project. I dont have a lot of money so this was months of saving for the used server class GPU and the PSU to run it + the 1070ti 8gb I have later.

The PC/server building hardware side scares me but I’m working on it. I’m not used to swapping parts out at all. when I tried to build my own PC a decade ago it didnt last long before something blew so there’s a bit of residual trauma there. I’m worried about things not fit right in the case, or destroying something or the the card not working and it all.

Those are unhealthy worries when I’m trying to apply myself to this cutting edge stuff. I’m really trying to work past that anxiety and just try my best to install the stupid GPU. I figure if I fail I fail thats life it will be a learning experience either way.

I want to document the upgrade process journey on my new self hosted site. I also want to open my kobold service to public use by fellow hobbyist. I’m not quite confident in sharing my domain on the public web though just yet I’m still cooking.

Coincidentally the same name as my geometry themed experimental grunge rock band

The first thought I had was this same scenario but all grown up. Imagine two fully grown 700 lb bovines crammed in your kitchen staring down your dishes lol theyre all cute until they become living flesh tanks then they’re still cute but hella bulky and slightly intimidating

nods and continues to use original doom wads with the red cross design for health pickups because the green one from BFG editions look like shit

Have you by chance checked out kobold.cpp lite webUI? It allows some of what your asking for like RAG for worldbuilding, adding images for the llm to describe to add into the story, easy editing of input and output, lots of customization in settings. I have a public instance of kobold webui setup on my website and I’m cool with allowing fellow hobbyist using my compute to experiment with things. If your interested in trying it out to see if its more what youre looking for, feel free to send me a pm and I’ll send you the address and a api key/password.

In an ideal work what exactly would you want an AI integrated text editor to do? Depending on what you need to have happen in your workflow you can automate copy pasting and automatic output logging with python scripts and your engines api.

Editing and audiing stories isnt that much different from auditing codebases. It all boils down to the understanding and correct use of language to convey abstraction. I bet tweaking some agebic personalities and goals in vscode+roo could get you somewhere

deleted by creator

Good to hear you figured it out with router settings. I’m also new to this but got all that figured out this week. As other commenters say I went with a reverse proxy and configured it. I choose caddy over nginx for easy of install and config. I documented just about every step of the process. I’m a little scared to share my website on public fourms just yet but PM me ill send you a link if you want to see my infrastructure page where I share the steps and config files.

Nice post Hendrik thanks for sharing your knowledge and helping people out :)

I once got kobold.CPP working with their collection of TTS model+ wav tokenizer system. Here’s the wiki page on it.

It may not be as natural as a commercial voice model but may be enough to wet your appetite in the event that other solutions feel overwhelmingly complicated

Wow this is some awese information Brucethemoose thanks for sharing!

I hope you dont mind if I ask some things. Tool calling is one of those things I’m really curious about. Sorry if this is too much please dont feel pressured you dont need to answer everything or anything at all. Thanks for being here.

I feel like a lot of people including myself only vaguely understand tool calling, how its supposed to work, and simple practice excersises to use it on via scripts and APIs. What’s a dead simple python script someone could cook to tool call within the openai-compatable API?

In your own words what exactly is tool calling and how does an absolute beginner tap into it? Could you clarify what you mean by ‘tool calling being built into their tokenizers’?

Would you mind sharing some sources where we can learn more? I’m sure huggingface has courses but maybe you know some harder to find sources?

Is tabbyAPI an engine similar to ollama, llama.cpp, ect?

What is elx2,3, ect?

Pangolin.

Yes it would have been awesome of them to release a bigger one for sure :( At the end of the day they are still a business that needs a product to sell. I don’t want to be ungrateful complaining that they dont give us everything. I expect some day all these companies will eventually clam up and stop releasing models to the public all together once the dust settles and monopolies are integrated. I’m happy to be here in an era where we can look forward to open licence model released every few months.

At the end of the day you need to decide what kind of person you are. Are you pragmatic or idealistic? Are you able to separate art from artist and creation from creator? Should you support a good open source service created for the betterment of everyone if you dont like the politics of its developers?

I’m a pragmatist by nature. I believe that a useful tool remains a useful tool even when its crafted by tankie assholes. If I found out the maker of a computer command like sudo was a leninist or whatever I wouldnt go out of my way to install an alternative just because I dont agree with the batshit politics of the creator. Just like I wouldn’t stop enjoying a song after finding out the ones who made it were greedy egotistical dickheads in personal life.

Young and politically charged idealist love that online social justice warrior signalling and political identity posturing. Everythings gotta be us vs them culture war, with us needing to always be on the morally/politically high ground else your a filthy inhuman nazi them who must be refunded/canceled. You get older and realize most people no matter the lean have some level of dogshit half baked politics or some other degree of mental emotional whackiness from past trauma or poor life circumstances causing them to be imperfect animals with dumb fucking biases. That’s humanity and the heart of darkness for ya. You can choose to associate the imperfections of the creator with the creation, or you can try to decouple them and see them as separate entities linked by causality.

The free API is the gateway drug to selling the product to customers (devs). The average consoomers attention and data is the product to be sold to customers (advertisers and big brother)

In the comics Thanos was straight up the right man hand/side hoe of the concept of death made manifest the whole point of offing half of all life was just to make mistress death happy (I think she actually ordered it). A lot of the original plot points of the infinity war and its buildup was lost in translation. Movie thanos motivations werent even half baked, he could have doubled resources and made a paradise for life with his motivations

Ding Ding, check this comment chain for your answer. Today you, tomorrow me.

Question one: yes and no. Most of the vomiting emojis shared here in comments are fake made using googles emoji kitchen thing. But there are many real modifiers for emojis like skin color or adding accents like tildes to regular english alphabet characters.

Question two: Modern keyboards typically have most emojis built in for you to select through. I dont think typing in the unicode values will automatically convert on phone operating systems but this might help if using windows or programming into a website.

the XKCD explained article on this actually gave some really great info.