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.
view the rest of the comments
Nice. I'm not an expert on NLP, are there any resources or frameworks out there to help handing a language model and guiding it to handle the specific set of commands/entities and areas? Or do you design everything from scratch?
When I first started tinkering with oobabooga's webui and the roleplay abilities, I also tried to create a character for my smart home. That certainly was fun and I like the idea of having a house with some kind of soul. But I never figured out how to make that useful. It just tried switching on or off random stuff and couldn't figure out what i wanted nor understand how my apartment looked. And of course kept hallucinating devices.
With HomeAssistant having 'The Year of the Voice'. This might get useful soon. They now(?) have official integrations for Whisper STT and a STT. And they're probably designing the language processing stuff and whatever is needed to handle commands regarding areas or specific domains. I think i will try that, once it's ready to use. But i want some scifi house with a soul, or the computer from the 'Enterprise'. And i think i also need more LLM power for that.
Yeah I'm using it with home assistant :)
Basically I'm using oobabooga for inference and providing an API endpoint as if it were OpenAI, and then plugging that into Microsoft's guidance, which I then give a tool. The tool takes as input the device and the state, and then calls my home assistant rest endpoint to execute the command!
Thank you for pointing that out. I was completely unaware of microsoft guidance. Once they merge/implement llama.cpp support, i'm definitely going to try it, too.
That will certainly be amazing, but for now it's actually not bad to use either oobabooga web UI or koboldcpp to run the inferencing and provide a rest endpoint, cause you can trick basically any program into treating it as if it's OpenAI and use it the same way