aws_marketplace/using_model_packages/creative-writing-using-gpt-2-text-generation/creative-writing-using-gpt-2-text-generation.ipynb

Author: EC2 Default User

aws_marketplace/using_model_packages/creative-writing-using-gpt-2-text-generation/creative-writing-using-gpt-2-text-generation.ipynb

@@ -22,15 +22,15 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Overview:\n",
+    "## Overview\n",
     "In [step 1](#Step-1:-Determine-input-prompt-and-visualize-word-dependencies) of this notebook, you will determine an input prompt that will be used to condition the GPT-2 model for text generation. You will also [visualize attention](#Step-1.1-Introduction-to-attention) mechanism of GPT-2 model. In [step 2](#Step-2:-Use-an-ML-model-to-generate-text-based-on-prompt), you will create the model from an AWS Marketplace subscription, and deploy to an Amazon SageMaker endpoint. In [step 3](#Step-3:-Explore-use-cases-and-model-parameters), you will explore text generation use cases with various model parameter settings. In [step 4](#Step-4:-Use-Amazon-SageMaker-batch-transform), you will perform inference asynchronously using SageMaker batch transform instead of the endpoint. In [Step 5](#Step-5:-Next-steps) you will find additional models to explore and experiment with."
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Contents:\n",
+    "## Contents\n",
     "* [Pre-requisites](#Pre-requisites)\n",
     "* [Step 1: Determine input prompt and visualize word dependencies](#Step-1:-Determine-input-prompt-and-visualize-word-dependencies)\n",
     "    * [Step 1.1 Introduction to attention](#Step-1.1-Introduction-to-attention)\n",
@@ -54,7 +54,7 @@
     "    * [Step 5.1: Additional resources](#Step-5.1:-Additional-resources)\n",
     "    * [Step 5.2: Cancel AWS Marketplace subscription](#Step-5.2:-Cancel-AWS-Marketplace-subscription)\n",
     "\n",
-    "#### Usage instructions\n",
+    "## Usage instructions\n",
     "You can run this notebook one cell at a time (By using Shift+Enter for running a cell)."
    ]
   },
@@ -170,7 +170,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Step 1: Determine input prompt and visualize word dependencies"
+    "## Step 1: Determine input prompt and visualize word dependencies"
    ]
   },
   {
@@ -186,7 +186,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 1.1 Introduction to attention\n",
+    "### Step 1.1 Introduction to attention\n",
     "\n",
     "[Self-Attention mechanism](https://arxiv.org/abs/1706.03762) is one of the key components for Transformers architectures, including GPT-2. It helps to relate different positions of a specific sequence of tokens in order to compute contextual representation of the sequence.\n",
     "\n",
@@ -219,7 +219,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 1.2 Specify input prompt \n",
+    "### Step 1.2 Specify input prompt \n",
     "\n",
     "You can experiment with different prompts and see what contextual dependencies exist in your own examples. "
    ]
@@ -237,7 +237,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 1.3 Visualize attention mechanism\n",
+    "### Step 1.3 Visualize attention mechanism\n",
     "\n",
     "In this step, let's call BertViz package to produce attention visualization of our input."
    ]
@@ -303,7 +303,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Step 2: Use an ML model to generate text based on prompt\n",
+    "## Step 2: Use an ML model to generate text based on prompt\n",
     "\n",
     "Because you utilize [GPT-2 XL - Text generation](https://aws.amazon.com/marketplace/pp/prodview-cdujckyfypprg) algorithm from AWS Marketplace - all you need to do to start using it - is to deploy it as an inference endpoint in your account. Alternatively, we can use SageMaker Batch Transformation to run inference on batch payloads. \n",
     "\n",
@@ -355,7 +355,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 2.1: Specify model arn from AWS Marketplace subscription"
+    "### Step 2.1: Specify model arn from AWS Marketplace subscription"
    ]
   },
   {
@@ -380,7 +380,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 2.2: Create model from model package and deploy to endpoint"
+    "### Step 2.2: Create model from model package and deploy to endpoint"
    ]
   },
   {
@@ -406,7 +406,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Step 3: Explore use cases and model parameters"
+    "## Step 3: Explore use cases and model parameters"
    ]
   },
   {
@@ -445,7 +445,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 3.1: Use case 1: Assisted writing of prose"
+    "### Step 3.1: Use case 1: Assisted writing of prose"
    ]
   },
   {
@@ -511,7 +511,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 3.2: Use case 2: Autonomous authoring of poem"
+    "### Step 3.2: Use case 2: Autonomous authoring of poem"
    ]
   },
   {
@@ -619,7 +619,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 3.3: Additional Use-Cases"
+    "### Step 3.3: Additional Use-Cases"
    ]
   },
   {
@@ -812,7 +812,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 3.4: Delete Amazon SageMaker endpoint"
+    "### Step 3.4: Delete Amazon SageMaker endpoint"
    ]
   },
   {
@@ -836,7 +836,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Step 4: Use Amazon SageMaker batch transform"
+    "## Step 4: Use Amazon SageMaker batch transform"
    ]
   },
   {
@@ -854,7 +854,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 4.1: Create input file for batch transform job"
+    "### Step 4.1: Create input file for batch transform job"
    ]
   },
   {
@@ -886,7 +886,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 4.2: Upload file to S3"
+    "### Step 4.2: Upload file to S3"
    ]
   },
   {
@@ -904,7 +904,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 4.3: Execute the batch transform job"
+    "### Step 4.3: Execute the batch transform job"
    ]
   },
   {
@@ -948,7 +948,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 4.4: Visualize output"
+    "### Step 4.4: Visualize output"
    ]
   },
   {
@@ -983,7 +983,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 4.5: Delete the model"
+    "### Step 4.5: Delete the model"
    ]
   },
   {
@@ -999,14 +999,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Step 5: Next steps"
+    "## Step 5: Next steps"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 5.1: Additional resources"
+    "### Step 5.1: Additional resources"
    ]
   },
   {
@@ -1025,7 +1025,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Step 5.2: Cancel AWS Marketplace subscription"
+    "### Step 5.2: Cancel AWS Marketplace subscription"
    ]
   },
   {