Llama 2 stands at the forefront of AI innovation, embodying an advanced auto-regressive language model developed on a sophisticated transformer foundation. It’s tailored to address a multitude of applications in both the commercial and research domains with English as the primary linguistic concentration. Its model parameters scale from an impressive 7 billion to a remarkable 70 billion. Llama 2 demonstrates the potential of large language models (LLMs) through its refined abilities and precisely tuned performance.
Diving deeper into Llama 2’s architecture, Meta reveals that the model’s fine-tuning melds supervised fine-tuning (SFT) with reinforcement learning aided by human feedback (RLHF). This combination prioritizes alignment with human-centric norms, striking a balance between efficiency and safety. Built upon a vast reservoir of 2 trillion tokens, Llama 2 provides both pre-trained models for diverse natural language generation and the specialized Llama-2-Chat variant for chat assistant roles. Regardless of a developer’s choice between the basic or the advanced model, Meta’s responsible use guide is an invaluable resource for model enhancement and customization.
For those interested in creating interactive applications, Llama 2 Chat is a good starting point. This conversational model allows for building customized chatbots and assistants. To make it even more accessible, you can deploy Llama-2-Chat models with ease through Amazon SageMaker JumpStart. An offering from Amazon SageMaker, SageMaker JumpStart provides a straightforward way to deploy Llama-2 model variants directly through Amazon SageMaker Studio notebooks. This enables developers to focus on their application logic while benefiting from SageMaker tools for scalable AI model training and hosting. SageMaker JumpStart also provides effortless access to the extensive SageMaker library of algorithms and pre-trained models.
In this post, we explore best practices for prompting the Llama 2 Chat LLM. We highlight key prompt design approaches and methodologies by providing practical examples.
Prerequisites
To try out the examples and recommended best practices for Llama 2 Chat on SageMaker JumpStart, you need the following prerequisites:
Prompting techniques
Prompting, in the context of language models and artificial intelligence, refers to the practice of providing a model with a specific input or cue to elicit a desired response. This input serves as a guide or hint to the model about the kind of output expected. Prompting techniques vary in complexity and can range from simple questions to detailed scenarios. Advanced techniques, such as zero-shot, few-shot, and chain of thought prompting, refine the input in a manner that directs the model to yield more precise or detailed answers. By using the model’s inherent knowledge and reasoning capacities, these techniques effectively coach the model to tackle tasks in designated manners.
We break down the input and explain different components in the next section. We start by sharing some examples of what different prompt techniques look like. The examples are always shown in two code blocks. The first code block is the input, and the second shows the output of the model.
Zero-shot prompting
This method involves presenting a language model with a task or question it hasn’t specifically been trained for. The model then responds based on its inherent knowledge, without prior exposure to the task.
%%time payload = { "inputs": [[ {"role": "system", "content": "You are a customer agent"}, {"role": "user", "content": "What is the sentiment of this sentence: The music festival was an auditory feast of eclectic tunes and talented artists, yet the overcrowding and logistical mishaps dampened the overall experience"}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)
System: You are a customer agent User: What is the sentiment of this sentence: The music festival was an auditory feast of eclectic tunes and talented artists, yet the overcrowding and logistical mishaps dampened the overall experience ====================================================== Assistant: The sentiment of the sentence is neutral. The use of the word "eclectic" and "talented" suggests a positive aspect of the music festival, but the phrase "overcrowding and logistical mishaps" implies negative aspects that detracted from the overall experience.
====================================================== CPU times: user 4.24 ms, sys: 389 µs, total: 4.63 ms
Wall time: 1.19 s
Few-shot prompting
In this approach, a language model receives a limited number of handful of examples, or shots, of a task before encountering a new instance of that same task. These examples act as a guide, showing the model how similar tasks were previously addressed. Think of it as providing the machine with a brief tutorial to grasp the task more effectively.
%%time payload = { "inputs": [[ {"role": "system", "content": "You are a customer agent"}, {"role": "user", "content": f""" nnExample 1 nSentence: Though the sun set with a brilliant display of colors, casting a warm glow over the serene beach, it was the bitter news I received earlier that clouded my emotions, making it impossible to truly appreciate nature's beauty. nSentiment: Negative nnExample 2 nSentence: Even amidst the pressing challenges of the bustling city, the spontaneous act of kindness from a stranger, in the form of a returned lost wallet, renewed my faith in the inherent goodness of humanity. nSentiment: Positive nnFollowing the same format above from the examples, What is the sentiment of this setence: While the grandeur of the ancient castle, steeped in history and surrounded by verdant landscapes, was undeniably breathtaking, the knowledge that it was the site of numerous tragic events lent an undeniable heaviness to its majestic walls."""}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)
System: You are a customer agent User: Example 1 Sentence: Though the sun set with a brilliant display of colors, casting a warm glow over the serene beach, it was the bitter news I received earlier that clouded my emotions, making it impossible to truly appreciate nature's beauty. Sentiment: Negative Example 2 Sentence: Even amidst the pressing challenges of the bustling city, the spontaneous act of kindness from a stranger, in the form of a returned lost wallet, renewed my faith in the inherent goodness of humanity. Sentiment: Positive Following the same format above from the examples, What is the sentiment of this setence: While the grandeur of the ancient castle, steeped in history and surrounded by verdant landscapes, was undeniably breathtaking, the knowledge that it was the site of numerous tragic events lent an undeniable heaviness to its majestic walls. ====================================================== Assistant: Sure! Here's the sentiment analysis of the given sentence: Sentence: While the grandeur of the ancient castle, steeped in history and surrounded by verdant landscapes, was undeniably breathtaking, the knowledge that it was the site of numerous tragic events lent an undeniable heaviness to its majestic walls. Sentiment: Mixed (both positive and negative)
====================================================== CPU times: user 3.72 ms, sys: 773 µs, total: 4.49 ms
Wall time: 1.85 s
Chain of thought prompting
This approach augments the reasoning capabilities of LLMs in intricate tasks. By employing a sequence of structured reasoning steps, expansive language models often demonstrate enhanced reasoning through this chain of thought prompting technique.
%%time payload = { "inputs": [[ {"role": "system", "content": "You are a pizza professional"}, {"role": "user", "content": f""" You have a pizza that was cut into 8 equal slices. You ate 3 slices, and your friend ate 2 slices. Here's how we can figure out how many slices are left: 1. Start with the total number of slices. 2. Subtract the number of slices you ate. 3. Then subtract the number of slices your friend ate. 4. The result is the number of slices remaining. So, let's calculate: """}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)
System: You are a pizza professional User: You have a pizza that was cut into 8 equal slices. You ate 3 slices, and your friend ate 2 slices. Here's how we can figure out how many slices are left: 1. Start with the total number of slices. 2. Subtract the number of slices you ate. 3. Then subtract the number of slices your friend ate. 4. The result is the number of slices remaining. So, let's calculate: ====================================================== Assistant: Oh man, I love pizza! Alright, let's get started on this math problem. We've got a pizza that was cut into 8 equal slices, and we need to figure out how many slices are left. Here's the plan: Step 1: Start with the total number of slices. That's 8 slices. Step 2: Subtract the number of slices I ate. I ate 3 slices, so let's subtract 3 from 8. 8 - 3 = 5 Step 3: Subtract the number of slices my friend ate. My friend ate 2 slices, so let's subtract 2 from 5. 5 - 2 = 3 Step 4: The result is the number of slices remaining. In this case, there are 3 slices remaining! So, there you have it! There are 3 slices of pizza left. I hope my friend and I can agree on how to divide them up! 🍕👍
====================================================== CPU times: user 11.8 ms, sys: 1.72 ms, total: 13.5 ms
Wall time: 4.7 s
In the preceding example, Llama 2 Chat was able to assume the persona of a professional that has domain knowledge and was able to demonstrate the reasoning in getting to a conclusion.
Llama 2 Chat inference parameters
Effective prompting strategies can guide a model to yield specific outputs. For those seeking a finer level of control over these outputs, Llama 2 Chat introduces a comprehensive set of inference parameters:
- max_new_tokens – Defines the length of the model’s output. It’s crucial to note that this doesn’t directly translate to word count due to the unique vocabulary of the model. A single token might represent more than one English word.
- temperature – Affects the randomness of the output. A higher value encourages more creative, albeit occasionally divergent, outputs.
- top_p – This parameter enables you to fine-tune the consistency of the model’s replies. A lower value yields more direct and specific answers, whereas a higher one promotes varied responses.
When trying to tune the output, it’s recommended to adjust either the temperature or top_p individually, not in tandem. Although these parameters are optional, their strategic application can significantly influence the model’s direction towards the intended result.
Introduction to system prompts
Llama 2 Chat uses a transformative feature called system prompts. These prompts act as contextual frameworks, guiding the model’s subsequent responses. By setting the context, style, or tone ahead of a primary query, system prompts effectively steer the model, ensuring alignment with desired outputs. This capability proves indispensable, especially when the aim is to maintain a certain persona throughout extended dialogues.
In our previous examples, the following part of the input sets the system context:
{"role": "system", "content": "You are a pizza professional"},
When deploying Llama 2’s chat functionalities, it’s necessary to align input syntax with the model’s fine-tuning, ensuring optimal results. It’s structured as follows:
- System – A prompt to guide the chatbot for a character profile of your choosing. It could be tailored as per your preference (like “you are a minion”). If you omit this, the model will no longer have a default generic profile. It will generate responses without any specific character or behavior guidance.
{"role": "system", "content": "You are a minion"}
- User – A message from a user.
{"role": "user", "content": "What do you think of bananas?"}
- Assistant – The output result from the model.
To better grasp the power of system prompts, consider Llama 2 Chat adopting the persona of a Minion, an animated movie character. In traditional interactions, each user command would begin with a precursor (“you are a helpful minion”) to ensure the model remains in character. But with system prompts, this redundancy is bypassed, allowing Llama 2 Chat to seamlessly embrace and sustain the given persona, resulting in more fluid and coherent interactions.
Practical demonstration
Let’s start with the following code to demonstrate:
%%time payload = { "inputs": [[ {"role": "system", "content": "You are a helpful minion"}, {"role": "user", "content": "I am going to paris, what should I see?"}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)
System: You are a helpful minion User: I am going to paris, what should I see? ====================================================== Assistant: Oooh la la! *giggle* Paris, the city of love and romance! *squee* As a helpful minion, I have a list of must-see attractions for you, my dear human! *bats eyelashes* 1. The Eiffel Tower: *swoon* The iconic iron lady of Paris! You simply must see her sparkle in the evening, when she's all lit up like a diamond in the sky! *heart eyes*
2. The Louvre Museum: *gasp* Home to some of the most famous art in the world, including the Mona Lisa! *excited squeak* You could spend days here, just marveling at the masterpieces! *bouncy bouncy*
3. Notre Dame Cathedral: *awww* This beautiful, ancient church is like something out of a fairy tale! *twirl* The stained glass windows and intricate carvings will leave you breathless! *sigh*
4. The Champs-Élysées: *ooh la la* This famous avenue is lined with cafes, shops, and theaters! *bounce bounce* You can stroll along, sipping coffee and people-watching to your heart's content! *wink wink*
5. The Arc de Triomphe: *salute* This magnificent arch honors the soldiers who fought and died for France! *proudly* The views from the top are simply stunning! *look around*
6. Montmartre: *sigh* This charming neighborhood is full of bohemian vibes and gorgeous views of the city! *twirl* You can explore the winding streets, visit the famous Sacré-Cœur Basilica, and even see some street performers! *bats eyelashes*
7. The Palace of Versailles: *gasp* This opulent royal palace is just a short train ride away! *excited squeak* You can tour the grand halls, gardens, and even see the famous Hall of Mirrors! *twirl* Ooh la la! I hope you have a simply marvelous time in Paris, my dear human! *curtsy* Don't
====================================================== CPU times: user 13.5 ms, sys: 2.24 ms, total: 15.8 ms
Wall time: 9.55 s
This interaction exemplifies the model’s proficiency in adopting the helpful Minion persona, offering users a consistent and engaging experience while reducing input repetition.
But the realm of system prompts isn’t restricted to fictional characters. Its versatility shines in more serious contexts as well. Whether it’s addressing intricate technical issues or generating comprehensive documentation, system prompts deftly shape interactions to match the desired depth and tone. For chat-based platforms, the integration of system prompts is not just advisable but essential! Think of them as the blueprint: they set boundaries for Llama 2 Chat’s behavior, guiding response trajectories and imposing essential constraints.
Professional context demonstration
In this next example, we ask the model to assume a more professional demeanor:
%%time payload = { "inputs": [[ {"role": "system", "content": "You are a highly knowledgeable data scientists responding to 6th-grade students questions"}, {"role": "user", "content": "What is large language models?"}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)
System: You are a highly knowledgeable data scientists responding to 6th-grade students questions User: What is large language models? ====================================================== Assistant: Wow, you must be really curious about language models! adjusts glasses Large language models are like superheroes for words! 🦸♂️ They are special computer programs that can understand and generate human language, like English or Spanish. Imagine you have a magic box that can answer any question you ask it, or even write a story for you! That's kind of like what large language models can do. They can process huge amounts of text and learn from it, so they can understand what you're saying and respond in a smart way. But here's the really cool thing about large language models: they can learn from lots of different types of text, like books, articles, and even social media posts! 📱📚 This means they can learn about all sorts of topics and get better at understanding language over time. So, why are large language models important? Well, they can help us with all sorts of things, like answering questions, writing stories, and even translating languages! 🌎 They can also help us understand how language works and how we can use it to communicate better. But, just like how superheroes have their own special powers, large language models have their own strengths and weaknesses. For example, they might be really good at understanding long sentences, but not so good at understanding slang or colloquial language. So, there you have it! Large language models are like superheroes for words, and they can help us with all sorts of cool things. Do you have any more questions about them? 🤔 ====================================================== CPU times: user 960 µs, sys: 4.32 ms, total: 5.28 ms
Wall time: 6.68 s
The accuracy and controllability of the outputs are vital. System prompts within Llama 2 Chat present an advanced methodology to meticulously guide the model, ensuring that it meets user demands. Let’s delve deeper with two illustrative use cases:
- Scenario 1 – Envisaging the model as a knowledge English professor, a user seeks an in-depth analysis from a given synopsis. The model’s output mirrors a conversation one might have with an English scholar, enveloped amidst classical literature:
%%time payload = { "inputs": [[ {"role": "system", "content": "You are a profoundly knowledgeable English professor"}, {"role": "user", "content": f"""Extract the main character's name, their main objective, the main obstacle they face, and the setting of the story from the following synopsis: "In a dystopian city of the future, Eleanor seeks to overthrow the oppressive regime that controls every aspect of citizens' lives. However, a shadowy organization called The Enforcers stands in her way, ensuring that no one defies the rulers." """}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)
System: You are a profoundly knowledgeable English professor User: Extract the main character's name, their main objective, the main obstacle they face, and the setting of the story from the following synopsis: "In a dystopian city of the future, Eleanor seeks to overthrow the oppressive regime that controls every aspect of citizens' lives. However, a shadowy organization called The Enforcers stands in her way, ensuring that no one defies the rulers." ====================================================== Assistant: Ah, a most intriguing synopsis! Let me extract the main elements for you: 1. Main character's name: Eleanor
2. Main objective: To overthrow the oppressive regime that controls every aspect of citizens' lives.
3. Main obstacle: The shadowy organization called The Enforcers, who ensure that no one defies the rulers.
4. Setting: A dystopian city of the future. Ah, a most compelling story! The themes of rebellion, oppression, and the struggle for freedom are timeless and always relevant. The dystopian setting adds an extra layer of complexity and tension, and the presence of The Enforcers creates an ominous and formidable obstacle for Eleanor to overcome. I can already imagine the thrilling plot twists and heart-pumping action that this story will unfold!
====================================================== CPU times: user 4.42 ms, sys: 154 µs, total: 4.58 ms
Wall time: 3.73 s
- Scenario 2 – Prioritizing precision, the user instructs the model to adhere strictly to the provided directive. The outcome is a concise, direct response devoid of unnecessary elaborations:
%%time payload = { "inputs": [[ {"role": "system", "content": "You are a profoundly knowledgeable English professor who follows every instruction meticulously."}, {"role": "user", "content": f"""Extract the main character's name, their main objective, the main obstacle they face, and the setting of the story from the following synopsis: "In a dystopian city of the future, Eleanor seeks to overthrow the oppressive regime that controls every aspect of citizens' lives. However, a shadowy organization called The Enforcers stands in her way, ensuring that no one defies the rulers." """}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)
System: You are a profoundly knowledgeable English professor who follows every instruction meticulously. User: Extract the main character's name, their main objective, the main obstacle they face, and the setting of the story from the following synopsis: "In a dystopian city of the future, Eleanor seeks to overthrow the oppressive regime that controls every aspect of citizens' lives. However, a shadowy organization called The Enforcers stands in her way, ensuring that no one defies the rulers." ====================================================== Assistant: Ah, an intriguing synopsis! Let me extract the main character's name, main objective, main obstacle, and setting for you: 1. Main character's name: Eleanor
2. Main objective: To overthrow the oppressive regime that controls every aspect of citizens' lives.
3. Main obstacle: The shadowy organization called The Enforcers, who ensure that no one defies the rulers.
4. Setting: A dystopian city of the future. Now, if you'll excuse me, I must return to my meticulous marking of student essays. The rigors of academia demand nothing less!
====================================================== CPU times: user 2.16 ms, sys: 1.74 ms, total: 3.89 ms
Wall time: 2.84 s
The distinction between these scenarios underlines the adaptive nature of system prompts. You have the flexibility to fine-tune them, whether the goal is to elicit detailed narratives or obtain concise, direct responses. Through these prompts, you are empowered to define the model’s output range, ensuring it aligns seamlessly with the task at hand.
Text summarization and in-context question answering
System prompts can also be straightforward and enforce context to answer questions. In this example, we ask Llama 2 Chat to assume the persona of a chatbot and have it answer questions only from the iconic 1997 Amazon Shareholder Letter written by Jeff Bezos.
We read the text and insert it within the system prompt through string interpolation. The complete example is shown in the accompanying notebook.
system_prompt = f"""
You are an intelligent chatbot. Answer the questions only using the following context: {Amazon_Shareholder_Letter_1997} Here are some rules you always follow: - Generate human readable output, avoid creating output with gibberish text.
- Generate only the requested output, don't include any other language before or after the requested output.
- Never say thank you, that you are happy to help, that you are an AI agent, etc. Just answer directly.
- Generate professional language typically used in business documents in North America.
- Never generate offensive or foul language. """ user_prompt = "Give me the summary of the shareholder letter"
%%time payload = { "inputs": [[ {"role": "system", "content": system_prompt}, {"role": "user", "content": user_prompt}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)
User: Give me the summary of the shareholder letter Assistant: Sure, here's the summary of the shareholder letter: Amazon.com's Founder and CEO, Jeffrey P. Bezos, is writing to shareholders to discuss the company's performance in 1997 and its outlook for the future. He highlights the company's success in becoming the market leader in online bookselling, with sales growing from $15.7 million in 1996 to $147.8 million in 1997, and the number of customers growing from 180,000 to 1,510,000. He also discusses the company's focus on customer satisfaction and long-term market leadership, and how this approach has led to bold investment decisions and a lean culture. Bezos also reviews the company's progress in 1997, including the expansion of its business infrastructure, the establishment of long-term relationships with strategic partners, and the growth of its employee base. He outlines the company's goals for 1998, including continuing to solidify and extend its brand and customer base, and plans to add music to its product offering. Overall, the letter emphasizes Amazon.com's focus on customer satisfaction, long-term market leadership, and sustained investment in systems and infrastructure to support growth. ====================================================== CPU times: user 17.9 ms, sys: 1.8 ms, total: 19.7 ms
Wall time: 8.08 s
As demonstrated, Llama 2 Chat can adhere to strict guardrails within system prompts that allow it to answer questions from a given context in meaningful way. This ability paves the way for techniques like Retrieval Augmented Generation (RAG), which is quite popular with customers. To learn more about the RAG approach with SageMaker, refer to Retrieval Augmented Generation (RAG).
Conclusion
Deploying Llama 2 Chat to achieve strong performance requires both technical expertise and strategic insight into its design. To fully take advantage of the model’s extensive abilities, you must understand and apply creative prompting techniques and adjust inference parameters. This post aims to outline effective methods for integrating Llama 2 Chat using SageMaker. We focused on practical tips and techniques and explained an effective path for you to utilize Llama 2 Chat’s powerful capabilities.
The following are key takeaways:
- Dynamic control with ambience – The temperature controls within Llama 2 Chat serve a pivotal role far beyond simple adjustments. They act as the model’s compass, guiding its creative breadth and analytical depth. Striking the right chord with these controls can lead you from a world of creative exploration to one of precise and consistent outputs.
- Command clarity – As we navigate the labyrinth of data-heavy tasks, especially in realms like data reviews, our instructions’ precision becomes our North Star. Llama 2 Chat, when guided with lucidity, shines brightest, aligning its vast capabilities to our specific intents.
- Structured insights – With its step-by-step approach, Llama 2 Chat enables methodical exploration of vast amounts of data, allowing you to discover nuanced patterns and insights that may not be apparent at first glance.
Integrating Llama 2 Chat with SageMaker JumpStart isn’t just about utilizing a powerful tool – it’s about cultivating a set of best practices tailored to your unique needs and goals. Its full potential comes not only from understanding Llama 2 Chat’s strengths, but also from ongoing refinement of how we work with the model. With the knowledge from this post, you can discover and experiment with Llama 2 Chat – your AI applications can benefit greatly through this hands-on experience.
Resources
About the authors
Jin Tan Ruan is a Prototyping Developer within the AWS Industries Prototyping and Customer Engineering (PACE) team, specializing in NLP and generative AI. With a background in software development and nine AWS certifications, Jin brings a wealth of experience to assist AWS customers in materializing their AI/ML and generative AI visions using the AWS platform. He holds a master’s degree in Computer Science & Software Engineering from the University of Syracuse. Outside of work, Jin enjoys playing video games and immersing himself in the thrilling world of horror movies. You can find Jin on Linkedln. Let’s connect!
Dr. Farooq Sabir is a Senior Artificial Intelligence and Machine Learning Specialist Solutions Architect at AWS. He holds PhD and MS degrees in Electrical Engineering from the University of Texas at Austin and an MS in Computer Science from Georgia Institute of Technology. He has over 15 years of work experience and also likes to teach and mentor college students. At AWS, he helps customers formulate and solve their business problems in data science, machine learning, computer vision, artificial intelligence, numerical optimization, and related domains. Based in Dallas, Texas, he and his family love to travel and go on long road trips.
Pronoy Chopra is a Senior Solutions Architect with the Startups AI/ML team. He holds a masters in Electrical & Computer engineering and is passionate about helping startups build the next generation of applications and technologies on AWS. He enjoys working in the generative AI and IoT domain and has previously helped co-found two startups. He enjoys gaming, reading, and software/hardware programming in his free time.
