Merge pull request #2152 from madeline-underwood/Arcee

Arcee_JA to sign off

Author: jasonrandrews

content/learning-paths/servers-and-cloud-computing/arcee-foundation-model-on-aws/00_overview.md

@@ -0,0 +1,37 @@
+---
+title: Overview
+weight: 2
+ 
+### FIXED, DO NOT MODIFY
+layout: learningpathall
+---
+
+## The AFM-4.5B model
+
+AFM-4.5B is a 4.5-billion-parameter foundation model designed to balance accuracy, efficiency, and broad language coverage. Trained on nearly 7 trillion tokens of carefully filtered data, it performs well across a wide range of languages, including Arabic, English, French, German, Hindi, Italian, Korean, Mandarin, Portuguese, Russian, and Spanish.
+
+In this Learning Path, you'll deploy AFM-4.5B using [Llama.cpp](https://github.com/ggerganov/llama.cpp) on an Arm-based AWS Graviton4 instance. You’ll walk through the full workflow, from setting up your environment and compiling the runtime, to downloading, quantizing, and running inference on the model. You'll also evaluate model quality using perplexity, a common metric for measuring how well a language model predicts text.
+
+This hands-on guide helps developers build cost-efficient, high-performance LLM applications on modern Arm server infrastructure using open-source tools and real-world deployment practices.
+
+### LLM deployment workflow on Arm Graviton4
+
+- **Provision compute**: launch an EC2 instance using a Graviton4-based instance type (for example, `c8g.4xlarge`)
+
+- **Set up your environment**: install the required build tools and dependencies (such as CMake, Python, and Git)
+
+- **Build the inference engine**: clone the [Llama.cpp](https://github.com/ggerganov/llama.cpp) repository and compile the project for your Arm-based environment
+
+- **Prepare the model**: download the **AFM-4.5B** model files from Hugging Face and use Llama.cpp's quantization tools to reduce model size and optimize performance
+
+- **Run inference**: load the quantized model and run sample prompts using Llama.cpp.
+
+- **Evaluate model quality**: calculate **perplexity** or use other metrics to assess model performance
+
+{{< notice Note>}}
+You can reuse this deployment flow with other models supported by Llama.cpp by swapping out the model file and adjusting quantization settings.
+{{< /notice >}}
+
+
+
+

content/learning-paths/servers-and-cloud-computing/arcee-foundation-model-on-aws/01_launching_a_graviton4_instance.md

@@ -1,171 +1,118 @@
 ---
-title: Launching a Graviton4 instance
-weight: 2
+title: Provision your Graviton4 environment
+weight: 3
 
 ### FIXED, DO NOT MODIFY
 layout: learningpathall
 ---
 
 ## Requirements
 
-  - An AWS account
+Before you begin, make sure you have the following:
 
-  - Access to launch an EC2 instance of type `c8g.4xlarge` (or larger) with at least 128 GB of storage
+- An AWS account  
+- Permission to launch a Graviton4 EC2 instance of type `c8g.4xlarge` (or larger)  
+- At least 128 GB of available storage
 
-For more information about creating an EC2 instance using AWS refer to [Getting Started with AWS](/learning-paths/servers-and-cloud-computing/csp/aws/).
+If you're new to EC2, check out the Learning Path [Getting Started with AWS](/learning-paths/servers-and-cloud-computing/csp/aws/).
 
-## AWS Console Steps
+## Create an SSH key pair
 
-Follow these steps to launch your EC2 instance using the AWS Management Console:
+To deploy the Arcee AFM-4.5B model, you need an EC2 instance running on Arm-based Graviton4 hardware.
 
-### Step 1: Create an SSH Key Pair
+To do this, start by signing in to the [AWS Management Console](https://console.aws.amazon.com), then navigate to the **EC2** service.
 
-1. **Navigate to EC2 Console**
+From there, you can create an SSH key pair that allows you to connect to your instance securely.
 
-   - Go to the [AWS Management Console](https://console.aws.amazon.com)
+## Set up secure access 
 
-   - Search for "EC2" and click on "EC2" service
+Open the **Key Pairs** section under **Network & Security** in the sidebar, and create a new key pair named `arcee-graviton4-key`. 
 
-2. **Create Key Pair**
+Next, select **RSA** as the key type, and **.pem** as the file format. Once you create the key, your browser will download the `.pem` file automatically.
 
-   - In the left navigation pane, click "Key Pairs" under "Network & Security"
+To ensure the key remains secure and accessible, move the `.pem` file to your SSH configuration directory, and update its permissions to restrict access.
 
-   - Click "Create key pair"
+To do this, on macOS or Linux, run:
 
-   - Enter name: `arcee-graviton4-key`
+```bash
+mkdir -p ~/.ssh
+mv arcee-graviton4-key.pem ~/.ssh/
+chmod 400 ~/.ssh/arcee-graviton4-key.pem
+```
+internet
+## Launch and configure the EC2 instance
 
-   - Select "RSA" as the key pair type
+In the left sidebar of the EC2 dashboard, select **Instances**, and then **Launch instances**.
 
-   - Select ".pem" as the private key file format
+Use the following settings to configure your instance:
 
-   - Click "Create key pair"
+- **Name**: `Arcee-Graviton4-Instance`  
+- **Application and OS image**:  
+  - Select the **Quick Start** tab  
+  - Select **Ubuntu Server 24.04 LTS (HVM), SSD Volume Type**  
+  - Ensure the architecture is set to **64-bit (ARM)**  
+- **Instance type**: select `c8g.4xlarge` or larger  
+- **Key pair name**: select `arcee-graviton4-key` from the list
 
-   - The private key file will automatically download to your computer
+## Configure network
 
-3. **Secure the Key File**
+To enable internet access, choose a VPC with at least one public subnet.  
 
-   - Move the downloaded `.pem` file to the SSH configuration directory
+Then select a public subnet from the list.
 
-     ```bash
-     mkdir -p ~/.ssh
-     mv arcee-graviton4-key.pem ~/.ssh
-     ```
+Under **Auto-assign public IP**, select **Enable**.
 
-   - Set proper permissions on macOS or Linux:
+## Configure firewall
 
-     ```bash
-     chmod 400 ~/.ssh/arcee-graviton4-key.pem
-     ```
+Select **Create security group**. Then select **Allow SSH traffic from** and select **My IP**.
 
-### Step 2: Launch EC2 Instance
+{{% notice Note %}}
+You'll only be able to connect to the instance from your current host, which is the most secure setting. Avoid selecting **Anywhere** unless absolutely necessary, as this setting allows anyone on the internet to attempt a connection.
 
-1. **Start Instance Launch**
-
-   - In the left navigation pane, click "Instances" under "Instances"
-
-   - Click "Launch instances" button
-
-2. **Configure Instance Details**
-
-   - **Name and tags**: Enter `Arcee-Graviton4-Instance` as the instance name
-
-   - **Application and OS Images**: 
-     - Click "Quick Start" tab
-
-     - Select "Ubuntu" 
-
-     - Choose "Ubuntu Server 24.04 LTS (HVM), SSD Volume Type"
-
-     - **Important**: Ensure the architecture shows "64-bit (ARM)" for Graviton compatibility
-
-   - **Instance type**: 
-     - Click on "Select instance type"
-
-     - Select `c8g.4xlarge` or larger
-
-3. **Configure Key Pair**
-
-     In "Key pair name", select the SSH keypair you created earlier (`Arcee-Graviton4-Instance`)
-   
-4. **Configure Network Settings**
-
-   - **Network**: Select a VPC with a least one public subnet. 
-
-   - **Subnet**: Select a public subnet in the VPC
-
-   - **Auto-assign Public IP**: Enable
-
-   - **Firewall (security groups)**
-
-     - Click on "Create security group"
-
-     - Click on "Allow SSH traffic from"
-
-     - In the dropdown list, select "My IP". 
-     
-
-{{% notice Notes %}}
-You will only be able to connect to the instance from your current host, which is the safest setting. Selecting "Anywhere" allows anyone on the Internet to attempt to connect; use at your own risk.
-
-Although this demonstration only requires SSH access, it is possible to use one of your existing security groups as long as it allows SSH traffic.
+You only need SSH access for this Learning Path. If you already have a security group that allows inbound SSH traffic, you can reuse it.
 {{% /notice %}}
 
-5. **Configure Storage**
-
-   - **Root volume**: 
-     - Size: `128` GB
-
-     - Volume type: `gp3`
-
-7. **Review and Launch**
-
-   - Review all settings in the "Summary" section
+## Configure storage
 
-   - Click "Launch instance"
+Set the **root volume size** to `128` GB, then select **gp3** as the volume type.
 
-### Step 3: Monitor Instance Launch
+## Review and launch the instance
 
-1. **View Launch Status**
+Review all your configuration settings, and when you're ready, select **Launch instance** to create your EC2 instance.
 
-   After a few seconds, you should see a message similar to this one:
+## Monitor the instance launch
 
-   `Successfully initiated launch of instance (i-<unique instance ID>)`
+After a few seconds, you should see a confirmation message like this:
 
-   If instance launch fails, please review your settings and try again.
+```
+Successfully initiated launch of instance (i-xxxxxxxxxxxxxxxxx)
+```
 
-2. **Get Connection Information**
+If the launch fails, double-check the instance type, permissions, and network settings.
 
-   - Click on the instance id, or look for the instance in the Instances list in the EC2 console.
+To retrieve the connection details, go to the **Instances** list in the EC2 dashboard.  
 
-   - In the "Details" tab of the instance, note the "Public DNS" host name
+Then select your instance by selecting **Instance ID**.  
 
-   - This is the host name you'll use to connect via SSH, aka `PUBLIC_DNS_HOSTNAME`
+In the **Details** tab, copy the **Public DNS** value - you’ll use this to connect through SSH.
 
-### Step 4: Connect to Your Instance
+## Connect to your instance
 
-1. **Open Terminal/Command Prompt**
+Open a terminal and connect to the instance using the SSH key you downloaded earlier:
 
-2. **Connect via SSH**
-   ```bash
-   ssh -i ~/.ssh/arcee-graviton4-key.pem ubuntu@<PUBLIC_DNS_HOSTNAME>
-   ```
+```bash
+ssh -i ~/.ssh/arcee-graviton4-key.pem ubuntu@<PUBLIC_DNS_HOSTNAME>
+```
 
-3. **Accept Security Warning**
+When prompted, type `yes` to confirm the connection.
 
-   - When prompted about authenticity of host, type `yes`
-
-   - You should now be connected to your Ubuntu instance
-
-### Important Notes
-
-- **Region Selection**: Ensure you're in your preferred AWS region before launching
-
-- **AMI Selection**: The Ubuntu 24.04 LTS AMI must be ARM64 compatible for Graviton processors
-
-- **Security**: Think twice about allowing SSH from anywhere (0.0.0.0/0). It is strongly recommended to restrict access to your IP address.
-
-- **Storage**: The 128GB EBS volume is sufficient for the Arcee model and dependencies
-
-- **Backup**: Consider creating AMIs or snapshots for backup purposes
+You should now be connected to your Ubuntu instance running on Graviton4.
 
+{{% notice Note %}}
+**Region**: make sure you're launching in your preferred AWS region.  
+**AMI**: confirm that the selected AMI supports the Arm64 architecture. 
+**Security**: for best practice, restrict SSH access to your own IP.  
+**Storage**: 128 GB is sufficient for the AFM-4.5B model and dependencies.  
+**Backup**: consider creating an AMI or snapshot after setup is complete.
+{{% /notice %}}
 

content/learning-paths/servers-and-cloud-computing/arcee-foundation-model-on-aws/02_setting_up_the_instance.md

@@ -1,51 +1,58 @@
 ---
-title: Setting up the instance
-weight: 3
+title: Configure your Graviton4 environment
+weight: 4
 
 ### FIXED, DO NOT MODIFY
 layout: learningpathall
 ---
 
-In this step, you'll set up the Graviton4 instance with all the necessary tools and dependencies required to build and run the Arcee Foundation Model. This includes installing the build tools and Python environment.
+In this step, you'll set up the Graviton4 instance with the tools and dependencies required to build and run the Arcee Foundation Model. This includes installing system packages and a Python environment.
 
-## Step 1: Update Package List
+## Update the package list
+
+Run the following command to update your local APT package index:
 
 ```bash
 sudo apt-get update
 ```
 
-This command updates the local package index from the repositories:
+This step ensures you have the most recent metadata about available packages, including versions and dependencies. It helps prevent conflicts when installing new packages.
 
-- Downloads the latest package lists from all configured APT repositories
-- Ensures you have the most recent information about available packages and their versions
-- This is a best practice before installing new packages to avoid potential conflicts
-- The package index contains metadata about available packages, their dependencies, and version information
+## Install system dependencies
 
-## Step 2: Install System Dependencies
+Install the build tools and Python environment:
 
 ```bash
 sudo apt-get install cmake gcc g++ git python3 python3-pip python3-virtualenv libcurl4-openssl-dev unzip -y
 ```
 
-This command installs all the essential development tools and dependencies:
+This command installs the following tools and dependencies:
+
+- **CMake**: cross-platform build system generator used to compile and build Llama.cpp
+
+- **GCC and G++**: GNU C and C++ compilers for compiling native code
+
+- **Git**: version control system for cloning repositories
+
+- **Python 3**: Python interpreter for running Python-based tools and scripts
+
+- **Pip**: Python package manager
+
+- **Virtualenv**: tool for creating isolated Python environments
+
+- **libcurl4-openssl-dev**: development files for the curl HTTP library
 
-- **cmake**: Cross-platform build system generator used to compile Llama.cpp
-- **gcc & g++**: GNU C and C++ compilers for building native code
-- **git**: Version control system for cloning repositories
-- **python3**: Python interpreter for running Python-based tools and scripts
-- **python3-pip**: Python package installer for managing Python dependencies
-- **python3-virtualenv**: Tool for creating isolated Python environments
-- **libcurl4-openssl-dev**: client-side URL transfer library
+- **Unzip**: tool to extract `.zip` files (used in some model downloads)
 
-The `-y` flag automatically answers "yes" to prompts, making the installation non-interactive.
+The `-y` flag automatically approves the installation of all packages without prompting.
 
-## What's Ready Now?
+## Ready for build and deployment
 
-After completing these steps, your Graviton4 instance has:
+After completing the setup, your instance includes the following tools and environments:
 
 - A complete C/C++ development environment for building Llama.cpp
-- Python 3 with pip for managing Python packages
+- Python 3, pip, and virtualenv for managing Python tools and environments
 - Git for cloning repositories
-- All necessary build tools for compiling optimized ARM64 binaries
+- All required dependencies for compiling optimized Arm64 binaries
 
-The system is now prepared for the next steps: building Llama.cpp and downloading the Arcee Foundation Model.
+You're now ready to build Llama.cpp and download the Arcee Foundation Model.