view the rest of the comments
LocalLLaMA
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
I don't have answers, because I've been looking for such an amazing deal to fall into my own lap ๐ I'd love to hear your plans though! Which models are you excited to try out and what sort of tasks? Are you going to try to run a big MoE with Colibri? https://github.com/JustVugg/colibri
Good luck, and have fun!
You know the more I lie about the cost, the more I believe it. Apply enough delusion and anything can become reality ๐
I'm a techy but to be honest my lack of knowledge of AI is shocking. I've heard of 'MoE' but I've no idea what is means. Never heard of Colibri. I've been messing around with a few models, so far Qwen is my favourite - its slower than others but its pretty dependable.
As for plans, who knows. Start with getting Hermes and opencode running and take it from there!