Total beginner on how to use a model exactly

  1. TL;DR: I need LLMs to categorize text/articles into a list of pre-determined categories based on the title of the article. I think I’ve found a fine-tuned model on hugging face pre trained on those IAB categories [1] but all it outputs is sentiment analysis, not the 700+ categories I think it has been trained on. The readme is basically empty. Yet it has some 50+ downloads so someone must be using it? HELP

CONTEXT: I’ve read a bit about the differences about fine-tuning and in-context learning. … I’ve been experimenting with a rudimentary approach using chatGPT to read the categories from a PDF via a plugin.

The process is quite straightforward - I input the title and the first two lines of an article, and chatGPT does a fairly decent job of predicting the most fitting category. The downside? I’m concerned about its scalability and economic viability. The current method might not work so well when we’re talking about classifying a significant number of articles.

My question to you, my fellow AI enthusiasts: How would you approach designing a system, via an API, capable of doing this quickly and on a larg-ish scale?

1 Like