31–40 of 78 posts
I didn't see any info on how this is different than installing/running llamacpp or koboldcpp. New offerings are awesome of course, but what is it adding?
is it a free model or is the politically-correct-only response constraints in place?
Ok, since is running all private, how can I add my own private data? For example I have a 20+ years of an email archive that I'd like to be ingested.
I imagine this means you’d need to come up with own model, even if based on existing one.
I didn't see any info on how this is different than installing/running llamacpp or koboldcpp. New offerings are awesome of course, but what is it adding?
The main difference is setting everything up yourself manually, downloading the modal, optimizing the parameters for best performance, running an API server and a UI front-end - which is out of reach for most non-technical people. With LlamaGPT, it's just one command: `docker compose up -d` or one click install for umbrelOS home server users.
Anyone see if it contains utilities to import models from huggingface/github?
So many projects still using GPT in their name. Is the thinking here that OpenAI is not going to defend that trademark? Or just kicking the can down the road on rebranding until the C&D letter arrives?
Well, GPT is simply an initialism for "Generative Pre-trained Transformer". In Germany, a trademark can be lost if it becomes a "Gattungsbegriff" (generic term). This happens when a trademark becomes so well-known and widely used that it becomes the common term for a product or service, rather than being associated with a specific company or brand. For example, if a company invented a new type of vacuum cleaner and t…
(1) What are the best more creative/less lobotomized versions of Llama 2? (2) What's the best way to get one of those running in a similarly easy way?
Nice project! I could not find the information in the README.md, can I run this with a GPU? If so what do I need to change? Seems like it's hardcoded to 0 in the run script: https://github.com/getumbrel/llama-gpt/blob/master/api/run.s...
Ah yes, running on GPU isn't supported at the moment. But CUDA (for Nvidia GPUs) and Metal support is on the roadmap!
Oh I thought this was a quick guide to host it on any server (AWS / other clouds) of our choosing.
As an aside, UmbrelOS actually seems like a cool concept by itself btw, good to see these "self hosted cloud" projects coming together in a unified UI, I may investigate this more at some point.
Earlier quoted context omitted.
I imagine this means you’d need to come up with own model, even if based on existing one.
And is that hard? Sorry if this is a newbie question, I'm really out of the loop on this tech. What would be required? Computing power and tagging? Or can you like improve the model without much human intervention? Can it be done incrementally with usage and user feedback? Would a single user even be able to generate enough feedback for this?
Earlier quoted context omitted.
Yes! It can run on any home server or cloud server.
Interesting. I might try to get this to work on my NAS.