Lecture 2.1 – Practical AI Tools (MIT How to AI Almost Anything, Spring 2025) | Paul Liang

This podcast features a presentation and discussion about practical tips for PyTorch and Hugging Face, focusing on building, iterating, and debugging machine learning models. David, a TA for the course, leads the tutorial, covering PyTorch tensors, operations, and a small project using smell sensor data for classification. He emphasizes data preprocessing, normalization, and model design, including the use of simple models like Random Forest. The discussion extends to Hugging Face, where David explains how to fine-tune large language models using LoRa and tools like bit and bytes. Chanakya joins in to share a debugging checklist for AI models, stressing the importance of understanding data, simplifying models, and hyperparameter tuning.

Outlines

Part 1: Course Setup and Introduction to Tools

Part 2: Model Training and Evaluation

Part 3: Large Language Models with Hugging Face

Part 4: AI Model Debugging

Sign in to continue reading, translating and more.

Open full episode in Podwise

Lecture 2.1 – Practical AI Tools (MIT How to AI Almost Anything, Spring 2025)

Paul Liang

Part 1: Course Setup and Introduction to Tools

Course Introduction and Project Proposal Overview

Introduction to PyTorch and Tensor Operations

Data Exploration and Preprocessing for Smell Detection

Part 2: Model Training and Evaluation

Data Normalization, Model Design, and Training Loop

Evaluation, Model Improvement, and Random Forest Comparison

Part 3: Large Language Models with Hugging Face

Introduction to Hugging Face and Large Language Models

Setting Up and Training a Large Language Model with Hugging Face

Part 4: AI Model Debugging

Debugging AI Models: A Checklist and Practical Tips

Lecture 2.1 – Practical AI Tools (MIT How to AI Almost Anything, Spring 2025)

Paul Liang

Part 1: Course Setup and Introduction to Tools

00:00Course Introduction and Project Proposal Overview

Course Introduction and Project Proposal Overview

01:45Introduction to PyTorch and Tensor Operations

Introduction to PyTorch and Tensor Operations

10:08Data Exploration and Preprocessing for Smell Detection

Data Exploration and Preprocessing for Smell Detection

Part 2: Model Training and Evaluation

16:01Data Normalization, Model Design, and Training Loop

Data Normalization, Model Design, and Training Loop

25:02Evaluation, Model Improvement, and Random Forest Comparison

Evaluation, Model Improvement, and Random Forest Comparison

Part 3: Large Language Models with Hugging Face

31:03Introduction to Hugging Face and Large Language Models

Introduction to Hugging Face and Large Language Models

37:53Setting Up and Training a Large Language Model with Hugging Face

Setting Up and Training a Large Language Model with Hugging Face

Part 4: AI Model Debugging

45:10Debugging AI Models: A Checklist and Practical Tips

Debugging AI Models: A Checklist and Practical Tips