Normally when you fine-tune an LLM you end up making Jeff Bezos just a little bit richer due to the enormous compute power required even for the simplest of fine-tuning. I tried every free avenue I could think of to demonstrate fine-tuning using Mistral-7B-Instruct, but it failed on Google Colab fre...

Modern AI tooling is mainly based on building models trained by lots of data rather than developing clever algorithms. This means that once you move beyond the basics of calling models others have developed and want to start training your own models, you'll need some data to do that training with.

Imagine that you went to high school in a place where everyone was rich except for you. Your parents had very mediocre jobs, enough to put food on the table and pay for school fees but nothing else.

Further imagine that you didn't want anyone else to know this. How would you cover it up?

First, yo...

Let's play a game of prompt engineering frisbee.

Rules: Each person takes a turn creating a prompt template and tries to get the LLM to respond in a believable way based on the template. The first person whose prompt fails to produce a convincing result loses the round.

Setup

Let's start with the...

To be able to interact with the Hugging Face community, you need to create an API token. Let's take a look at the steps.

1. Sign up for Hugging Face
   If you haven't gotten an account yet, sign up here: https://huggingface.co/join

2. Hover over the account icon in the upper right corner and choose

   ...