Hacker News Reader

This is one of the best, most detailed write-ups of how to fine-train a large language model on custom text that I've seen anywhere.

Thank you!! I felt it was getting so long and was worried it would be impenetrable, so I'm really pleased to hear it felt great.

Really great! With Alpaca-Lora 4-bit training getting usable any day now it should get a lot more affordable or you can even do it at home.

I agree. I've been looking to train/fine-tune an LLM model myself but the corpus I want to provide is not in question/answer mode.

Is there a way to train or fine-tune an LLM model using say only plain text files?

You can use an LLM to rewrite a document to a question answer form.

How would one go about this for a large number of documents?