Ask HN: How to train a LLM against a knowledge base I understand that this might be a bit late to ask this question, and I don’t know a lot about AI/ML in general. I have to train/tune a pre-trained model for specific context. By context, I mean a knowledge base, a product’s documentation, or user manual, or in my case, an inventory of electronic items in our warehouse. I tried dumping the inventory information and basic BOM content as a system message for ChatGPT4-o model using their platform playground, and asking questions like “we are making 1000 power banks this month, so which components should I pre-order so that we don’t run out of them?”. This works as expected, but it took me a while to realize that each query used more than 30K tokens! That’s a quick way to lose money. I am looking for a solution from someone who trained/tuned a decent LLM on custom data, and I’m pretty sure a lot of other small business owners are looking for something like this. Thank you! |