From the course: LLaMa for Developers
Unlock this course with a free trial
Join today to access over 25,300 courses taught by industry experts.
Few shot learning with LLaMA - Llama Tutorial
From the course: LLaMa for Developers
Few shot learning with LLaMA
- [Instructor] In this video, we're going to learn how to prompt Llama better. We're going to use a technique called few-shot learning. Few-shot learning is providing Llama with some examples. Let's dive in. Now, I'm here in 05_02 under our exercise files. Now, I've already downloaded Llama, just so we can get started and let's scroll down to the exercise. So here, I've created a prompt to classify some reviews into different categories. My goal with this prompt is to have Llama fill in these colons to give me a response after each of these lines. So let's go ahead and run this notebook cell. All right, here we go. So our output starts here and we really didn't get the results that we were looking for. Let's try again. Now, because Llama is a smaller model, sometimes you'll get more chaotic responses. All right, here we go. We got something slightly better. We got classifications from our input, but it's not in…
Contents
-
-
-
-
-
-
-
(Locked)
Difference between LLaMA with commercial LLMs4m 8s
-
(Locked)
Few shot learning with LLaMA5m 7s
-
(Locked)
Chain of thought with LLaMA3m 16s
-
(Locked)
Using schemas with LLaMA3m 1s
-
(Locked)
Optimizing LLaMA prompts with DSPy4m 39s
-
(Locked)
Challenge: Generating product tags25s
-
(Locked)
Solution: Generating product tags1m
-
(Locked)
-