Add SmolLm2

Author: kaizengrowth

Intro Sessions/Session 1 - Product Engineering for AI/handson_AWS.md

@@ -1,8 +1,8 @@
-# Hands-on Guide: Setting Up Qwen 2.1 on AWS EC2 with Ollama
+# Hands-on Guide: Setting Up LLMs on AWS EC2 with Ollama
 
-This guide walks you through setting up and running Qwen 2.1, a small but efficient LLM, on a free tier AWS EC2 instance using Ollama.
+This guide walks you through setting up and running SmolLm2 or Qwen 2.1, small but efficient LLMs, on a free tier AWS EC2 instance using Ollama.
 
-## 1. Creating an EC2 Instance
+## 1. Create an EC2 Instance.
 
 1. **Log in to AWS Console**
    - Go to https://aws.amazon.com/console/
@@ -35,7 +35,7 @@ This guide walks you through setting up and running Qwen 2.1, a small but effici
  5.  - **Configure Storage**: 30GB gp3 (free tier maximum, 30GB+ recommended)
    - Click "Launch Instance"
 
-## 2. Connecting to Your Instance
+## 2. Connect to Your Instance
 
 1. **Find your instance public IP**
    - On EC2 dashboard, select your instance
@@ -49,7 +49,7 @@ This guide walks you through setting up and running Qwen 2.1, a small but effici
      ```
    - On Windows, use PuTTY or Windows Terminal
 
-## 3. Create swap space (8GB recommended)
+## 3. Create swap space (8GB recommended on free tier)
 
 ```bash
    sudo fallocate -l 8G /swapfile
@@ -58,7 +58,7 @@ This guide walks you through setting up and running Qwen 2.1, a small but effici
    sudo swapon /swapfile
 ```
 
-## 4. Installing Ollama
+## 4. Install Ollama
 
 **Install Ollama**
    ```bash
@@ -73,7 +73,7 @@ This guide walks you through setting up and running Qwen 2.1, a small but effici
 ![Install Ollama](https://raw.githubusercontent.com/kaizengrowth/oklahomai/main/assets/images/step4.png)
 
 
-## 5. Setting Up and Running a Small LLM
+## 5. Set Up and Running a Small LLM
 
 **Pull and run the smallest smollm2 model**
 ```bash
@@ -87,10 +87,22 @@ Test the model with a prompt!
    ollama pull qwen2:0.5b
    ollama run qwen2:0.5b
    ```
-Test the model with a prompt!
 
+## 6.  Clean Up
+
+When you're done, remember to stop or terminate your EC2 instance to avoid unnecessary charges:
+
+1. In the EC2 dashboard, select your instance
+2. Choose "Instance state" and select "Stop" or "Terminate"
+
+**Note**: Stopping the instance will preserve your data but still incur storage costs. Terminating the instance will delete all data.
+
+----
+
+
+# Alternatives
 
-## 6. Running Ollama as a Service
+## A. Run Ollama as a Service
 
 1. **Start Ollama service**
    ```bash
@@ -107,7 +119,7 @@ Test the model with a prompt!
    sudo systemctl status ollama
    ```
 
-## 7. Using the Ollama API
+## B. Use the Ollama API
 
 Ollama provides a REST API that you can use for more advanced usage:
 
@@ -124,21 +136,11 @@ Ollama provides a REST API that you can use for more advanced usage:
    ```bash
    curl http://localhost:11434/api/tags
    ```
-   ```
 
-## 8. Running Ollama in the Background
+## C. Run Ollama in the Background
 
 If you want to keep Ollama running after disconnecting:
 
 ```bash
 nohup ollama serve > ollama.log 2>&1 &
-```
-
-## 9.  Cleaning Up
-
-When you're done, remember to stop or terminate your EC2 instance to avoid unnecessary charges:
-
-1. In the EC2 dashboard, select your instance
-2. Choose "Instance state" and select "Stop" or "Terminate"
-
-**Note**: Stopping the instance will preserve your data but still incur storage costs. Terminating the instance will delete all data.
+```

docs/index.html

@@ -459,13 +459,12 @@ <h3 style="font-size: 0.9em; margin-bottom: 8px;">Ethical Challenges</h3>
         <h3>Hands-on Activity</h3>
         <h2>Deploying a Tiny LLM</h2>
         <div class="fragment fade-in">
-          <p>We'll deploy <span class="highlight">Qwen2.5</span>, a small but efficient LLM.</p>
+          <p>We'll deploy <span class="highlight">SmolLm2</span> and <span class="highlight">Qwen2.5</span>, small but powerful LLMs.</p>
           <br>
           <p>Using:</p>
           <ul>
             <li>AWS EC2 (Free Tier)</li>
             <li>Ollama - Open source tool for running models locally</li>
-            <li>Basic terminal commands</li>
           </ul>
         </div>
       </section>
@@ -481,6 +480,7 @@ <h3 class="fragment fade-in">Resources</h3>
                <li class="fragment fade-up" style="font-size: 0.8em; margin-bottom: 3px;"><a href="https://huyenchip.com/books/" target="_blank">Chip Huyen's "AI Engineering" and "Designing Machine Learning Systems"</a></li>
             <li class="fragment fade-up" style="font-size: 0.8em; margin-bottom: 3px;"><a href="https://ollama.com/docs" target="_blank">Ollama Documentation</a></li>
               <li class="fragment fade-up" style="font-size: 0.8em; margin-bottom: 3px;"><a href="https://huggingface.co/Qwen/Qwen2-7B" target="_blank">Qwen2 Model Card</a></li>
+              <li class="fragment fade-up" style="font-size: 0.8em; margin-bottom: 3px;"><a href="https://huggingface.co/HuggingFaceTB/SmolLM-1.7B" target="_blank">SmolLM Model Card</a></li>
               <li class="fragment fade-up" style="font-size: 0.8em; margin-bottom: 3px;"><a href="https://huggingface.co/docs/evaluate/llm_evaluation" target="_blank">LLM Evaluation Guide</a></li>
               <li class="fragment fade-up" style="font-size: 0.8em; margin-bottom: 3px;"><a href="https://www.geeksforgeeks.org/aws-certified-ai-practitioner-aif-c01/" target="_blank">AWS Certified AI Practitioner (AIF-C01) Guide</a></li>
             </ul>