Learn to do Machine Learning using the Hugging Face ecosystem from scratch. This project-based course will teach you everything from training to deployment using Hugging Face. We’ll start from the basics, learn real skills used by Machine Learning Engineers, and have fun along the way!

What you’ll learn

Find and load datasets with Hugging Face Datasets
Clean, label, and batch text the simple way
Fine-tune a small Transformer for classification
Measure accuracy and improve step by step
Save and share your model on the Hugging Face Hub
Build an easy demo with Gradio
Publish your app on Hugging Face Spaces
Explain your projects with a clear model card

Table of Contents

1 Machine Learning with Hugging Face Bootcamp: Zero to Mastery
2 Overview
3 Introduction to Text Classification
4 What We’re Going To Build!
5 Getting Setup: Adding Hugging Face Tokens to Google Colab
6 Getting Setup: Importing Necessary Libraries to Google Colab
7 Downloading a Text Classification Dataset from Hugging Face Datasets
8 Preparing Text Data for Use with a Model – Part 1: Turning Our Labels into Numbers
9 Preparing Text Data for Use with a Model – Part 2: Creating Train and Test Sets
10 Preparing Text Data for Use with a Model – Part 3: Getting a Tokenizer
11 Preparing Text Data for Use with a Model – Part 4: Exploring Our Tokenizer
12 Preparing Text Data for Use with a Model – Part 5: Creating a Function to Tokenize Our Data
13 Setting Up an Evaluation Metric (to measure how well our model performs)
14 Introduction to Transfer Learning (a powerful technique to get good results quickly)
15 Model Training – Part 1: Setting Up a Pretrained Model from the Hugging Face Hub
16 Model Training – Part 2: Counting the Parameters in Our Model
17 Model Training – Part 3: Creating a Folder to Save Our Model
18 Model Training – Part 4: Setting Up Our Training Arguments with TrainingArguments
19 Model Training – Part 5: Setting Up an Instance of Trainer with Hugging Face Transformers
20 Model Training – Part 6: Training Our Model and Fixing Errors Along the Way
21 Model Training – Part 7: Inspecting Our Models Loss Curves
22 Model Training – Part 8: Uploading Our Model to the Hugging Face Hub
23 Making Predictions on the Test Data with Our Trained Model
24 Turning Our Predictions into Prediction Probabilities with PyTorch
25 Sorting Our Model’s Predictions by Their Probability
26 Performing Inference – Part 1: Discussing Our Options
27 Performing Inference – Part 2: Using a Transformers Pipeline (one sample at a time)
28 Performing Inference – Part 3: Using a Transformers Pipeline on Multiple Samples at a Time (Batching)
29 Performing Inference – Part 4: Running Speed Tests to Compare One at a Time vs. Batched Predictions
30 Performing Inference – Part 5: Performing Inference with PyTorch
31 OPTIONAL – Putting It All Together: from Data Loading, to Model Training, to making Predictions on Custom Data
32 Turning Our Model into a Demo – Part 1: Gradio Overview
33 Turning Our Model into a Demo – Part 2: Building a Function to Map Inputs to Outputs
34 Turning Our Model into a Demo – Part 3: Getting Our Gradio Demo Running Locally
35 Making Our Demo Publicly Accessible – Part 1: Introduction to Hugging Face Spaces and Creating a Demos Directory
36 Making Our Demo Publicly Accessible – Part 2: Creating an App File
37 Making Our Demo Publicly Accessible – Part 3: Creating a README File
38 Making Our Demo Publicly Accessible – Part 4: Making a Requirements File
39 Making Our Demo Publicly Accessible – Part 5: Uploading Our Demo to Hugging Face Spaces and Making it Publicly Available
40 Summary Exercises and Extensions
41 Introduction
42 Setting Up Google Colab with Hugging Face Tokens
43 Installing Necessary Dependencies
44 Getting an Object Detection Dataset
45 Inspecting the Features of Our Dataset
46 Creating a Colour Palette to Visualize Our Classes
47 Creating a Helper Function to Halve Our Image Sizes
48 Creating a Helper Function to Halve Our Box Sizes
49 Testing our Helper Functions
50 Outlining the Steps to Draw Boxes on an Image
51 Plotting Bounding Boxes on a Single Image Step by Step
52 Different Bounding Box Formats
53 Getting an Object Detection Model
54 Transfer Learning Overview
55 Downloading our Model from the Hugging Face Hub and Trying it Out
56 Inspecting the Layers of Our Model
57 Counting the Number of Parameters in Our Model
58 Creating a Function to Build Our Custom Model
59 Passing a Single Image Sample Through Our Model – Part 1
60 OPTIONAL: Data Preprocessor Model Workflow
61 Loading Our Models Image Preprocessor and Customizing it for Our Use Case
62 Exercise: Imposter Syndrome
63 Discussing the Format Our Model Expects Our Annotations In (COCO)
64 Creating Dataclasses to Hold the COCO Format
65 Creating a Function to Turn Our Annotations into COCO Format
66 Preprocessing a Single Image Sample and COCO Formatted Annotations
67 Post Processing a Single Output
68 Plotting a Single Post Processed Sample onto an Image
69 OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand – Part 1: Overview
70 OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand – Part 2: Replicating Scores by Hand
71 OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand – Part 3: Replicating Labels by Hand
72 OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand – Part 4: Replicating Boxes by Hand Overview
73 OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand – Part 5: Replicating Boxes by Hand Implementation
74 OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand – Part 6: Plotting Our Manual Post Processed Outputs on an Image
75 Preparing Our Data at Scale – Part 1: Concept Overview
76 Preparing Our Data at Scale – Part 2: Creating Train Validation and Test Splits
77 Preparing Our Data at Scale – Part 3: Preprocessing Multiple Samples at a Time Overview
78 Preparing our Data at Scale – Part 4: Making a Function to Preprocess Multiple Samples at a Time
79 Preparing our Data at Scale – Part 5: Applying Our Preprocessing Function to Our Datasets
80 Preparing Our Data at Scale – Part 6: Creating a Data Collation Function
81 Training a Custom Model – Part 1: Overview
82 Training a Custom Model – Part 2: Creating a Model and Folder to Save Our Model to
83 Training a Custom Model – Part 3: Creating TrainingArguments for Our Model Overview
84 Training a Custom Model – Part 4: Creating our First TrainingArguments
85 Training a Custom Model – Part 5: Finishing Off the TrainingArguments
86 Training a Custom Model – Part 6: OPTIONAL – Creating a Custom Optimizer for Different Learning Rates
87 Training a Custom Model – Part 7: Creating an Evaluation Function for Our Model Overview
88 Training a Custom Model – Part 8: Creating an Evaluation Function for Our Model Targets Processing
89 Training a Custom Model – Part 9: Creating an Evaluation Function for Our Model Predictions Processing
90 Training a Custom Model – Part 10: Training Our Model with Trainer
91 Training a Custom Model – Part 11: Plotting Our Models Loss Curves
92 Evaluating Our Model on the Test Dataset
93 Making Predictions on Test Data and Visualizing Them
94 Plotting Our Models Predictions vs. the Ground Truth Images
95 Trying Our Model on Images from the Wild
96 Uploading Our Trained Model to the Hugging Face Hub
97 Turning Our Model into a Demo – Part 1: Gradio and Hugging Face Spaces Overview
98 Turning Our Model into a Demo – Part 2: Creating an App File Overview
99 Turning Our Model into a Demo – Part 3: Building the Main Function of Our App File
100 Turning Our Model into a Demo – Part 4: Finishing Off Our App File and Testing Our Demo
101 Turning Our Model into a Demo – Part 5: Creating a Readme and Requirements File
102 Turning Our Model into a Demo – Part 6: Getting Example Images for Our Demo
103 Turning Our Model into a Demo – Part 7: Uploading Our Demo to the Hugging Face Hub
104 Turning Our Model into a Demo – Part 8: Embedding Our Demo into Our Notebook
105 Summary, Extensions and Extra-Curriculum
106 Overview and Introduction to Small Language Models (SLMs) + Resources
107 What We’re Going to Cover
108 Setting Up Google Colab with Hugging Face Tokens
109 Getting Our Google Colab Instance Ready for Coding
110 Summary: Extensions and Extra Curriculum
111 Setting Up Our Base Model and Inspecting the Tokenizer
112 How to Convert Input and Output Tokens to Text
113 Counting the Parameters in Our Model and Comparing it to the Teacher Model
114 Downloading a Text Dataset for Our Model
115 Formatting Our Dataset Ready to Be Used with a Language Model
116 Splitting Our Dataset into Train and Test Sets
117 Using Our Base Model with a Hugging Face Pipeline
118 Attempt 0: Trying the Base Model Pipeline with One of Our Own Samples
119 Attempt 1: Trying the Base Model Pipeline with One of Our Own Samples and an Instruction Prompt
120 Fine-Tuning Our Model – Part 1: Discussing the Ingredients We Need for Fine-Tuning
121 Fine-Tuning Our Model – Part 2: Setting Up Our SFTConfig with Hyperparameters for Model Training
122 Fine-Tuning Our Model – Part 3: Setting Up Our SFTTrainer and Fine-Tuning Our Model and Fixing Errors Along the Way
123 Fine-Tuning Our Model – Part 4: Plotting Our Models Loss Curves
124 Fine-Tuning Our Model – Part 5: Saving Our Best Model to File
125 Loading In Our Best Model from File and Preparing to Make Predictions
126 Making Predictions on Test Samples with Our Loaded Fine-tuned Model
127 Comparing Our Fine-Tuned Model’s Predictions to the Test Labels
128 Writing a Helper Function to Make Predictions on Any Sample and Inspecting the Results
129 Discussing what Uploading Our Model to the Hugging Face Hub Looks Like
130 Creating a Hugging Face Hub Model Repo to Store Our Model
131 Creating a README Model Card for Our Fine Tuned Model
132 Uploading Our Fine-Tuned Model to the Hugging Face Hub
133 Turning Our Model into a Demo – Part 1: Discussing the Required Components
134 Turning Our Model into a Demo – Part 2: Building an app.py File to Launch Our Demo
135 Turning Our Model into a Demo – Part 3: Creating Requirements and README Files for Our Demo
136 Turning Our Model into a Demo – Part 4: Uploading Our Demo to the Hugging Face Hub and Publishing it
137 Turning Our Model into a Demo – Part 5: Embedding Our Demo Right within Google Colab
138 Thank You!