Remix.run Logo
ipaddr 11 hours ago

Simplest way pack all text into a prompt.

You could use a vector database.

You could train a model from scratch.

Probably easiest to use OpenAI tools. Upload documents. Make custom model.

How do you make it answer your phone? You could use twillio api + script + llm + voice model. Want natural use a service.

echelon 10 hours ago | parent [-]

I think you're absolutely right about the easiest approach. I hope you don't mind me asking for a bit more difficulty.

Wouldn't fine tuning produce better results so long as you don't catastrophically forget? You'd preserve more context window space, too, right? Especially if you wanted it to memorize years of facts?

Are LoRAs a thing with LLMs?

Could you train certain layers of the model?

dannyw 10 hours ago | parent [-]

A good place to start with your journey is this guide from Unsloth:

https://docs.unsloth.ai/get-started/fine-tuning-llms-guide