TogetherAI_API_KEY

Gain insights into Llama 3 by learning prompting techniques, mastering control parameters, exploring real-world applications, and addressing ethical challenges to enhance efficiency in various creative tasks.

llama.tar.gz

together_api

hugging_face

together_api_streamlit

Generative AI and large language models have brought opportunities for improving work efficiency by automating several tasks that would otherwise take much of our time. They have also changed how people—who would otherwise need to rely on others—can now do creative work using various generative AI tools. Demand for people knowledgeable in these tools continues to grow.

This course starts by introducing learners to Llama 3. You’ll begin by learning different prompting techniques and best practices to get the desired results. Then, you’ll look at various parameters that can be used to control the model’s output. From there, you’ll get hands-on exposure to some real-world applications. You’ll end the course by discussing certain ethical challenges and limitations of Llama 3.

By the time you finish this course, you will be able to utilize Llama 3 in scenarios ranging from text summarization, sentiment analysis, and image generation on one hand, to code generation and frontend development on the other.

Introduction to Prompt Engineering with Llama 3

Providing the model with relevant research papers.

Providing some examples to guide the model on the required response style.  

Adding constraints to specify what not to include in the response.

Rephrasing the prompt after analyzing the first output.

**Scenario:** We are collecting data on the long-term effects of COVID-19 on recovered patients.

Which technique will *not* improve the factual accuracy of the response?

Scenario: We are collecting data on the long-term effects of COVID-19 on recovered patients.
Which technique will not improve the factual accuracy of the response?

**Prompt:** Write a scary story about a haunted house.

`temperature=0.9`

**Prompt:** Write a story about the mystery of a haunted house with a surprising twist at the end.

`temperature=0.5`

**Prompt:** Write a suspenseful story about a group of friends who investigate the mystery of a haunted house for children aged 8–10.

`temperature=0.7`

**Prompt:** Write a story filled with scary sounds and terrifying descriptions as a group of friends explore a haunted house.

`temperature=0.2`

Which prompt will generate the most relevant results for writing a unique and creative story about the mystery of a haunted house?

Which prompt will generate the most relevant results for writing a unique and creative story about the mystery of a haunted house?

Summarize the security guard's log entry for the night of the robbery.

Search for keywords related to suspicious activity in the witness interviews.

Analyze the bank transaction log to find suspicious transactions.

Summarize the descriptions of suspicious individuals in the witness interviews.

**Scenario:** We are investigating a robbery at a bank. We have access to the following details:

* Security camera footage transcript with timestamps.

* Witness interview notes.

* Bank transaction log from the day of the robbery.

* A security guard's log from the night of the robbery.


Which prompt will help us extract descriptions of suspicious individuals?

Scenario: We are investigating a robbery at a bank. We have access to the following details:
<ul>
<li>
Security camera footage transcript with timestamps.
</li>
<li>
Witness interview notes.
</li>
<li>
Bank transaction log from the day of the robbery.
</li>
<li>
A security guard’s log from the night of the robbery.
</li>
</ul>
Which prompt will help us extract descriptions of suspicious individuals?

How many system messages can a prompt template have?


How many system messages can a prompt template have?

```
<|begin_of_text|>

Book a flight from New York to Los Angeles

<|eot_id|>
```

```
<|begin_of_text|>

<|start_header_id|>system<|end_header_id|>
{{ You are a helpful AI assistant who responds to user messages accurately and unbiasedly}} <|eot_id|>

<|start_header_id|>user<|end_header_id|>
{{ Book a flight from New York to Los Angeles}} <|eot_id|>
```

```
<|begin_of_text|>

<|start_header_id|>system<|end_header_id|>
{{ You are a helpful AI assistant who responds to user messages accurately and unbiasedly}} <|eot_id|>

<|start_header_id|>user<|end_header_id|>
{{ Book a flight from New York to Los Angeles}} <|eot_id|>

<|start_header_id|>assistant<|end_header_id|>
```

**Scenario:** You want to create a prompt template for a conversation about booking a flight.

Which prompt format is most suitable?

Scenario: You want to create a prompt template for a conversation about booking a flight.
Which prompt format is most suitable?

Take a short quiz to test your understanding of prompt engineering.

Getting Started

Getting Started with Llama 3

Prompt Engineering

Prompt Engineering for Specific Tasks

Wrap Up

Quiz: Prompt Engineering