Transformer Architecture Courses and Certifications

Career Certificate

Introduction to Transformer Models for NLP

6 ratings at Coursera

Build and optimize NLP models with transformer architectures such as BERT, GPT, and T5, working through attention mechanisms, transfer learning, and fine-tuning in coding exercises.

• Coursera
• 4 weeks, 5 hours a week
• Self-Paced
• Paid Course
• 3 courses

Edureka

Transformer Architectures and Multimodal Models

Trace transformers from RNNs to multimodal systems: multi-head attention, encoder-decoder design, RoPE positional encoding, Flash Attention, Mixture of Experts, Vision Transformers, and distributed training.

• Coursera
• 4 weeks, 3 hours a week
• Self-Paced
• Paid Course

Packt

Foundations of Transformer Architectures for Natural Language Processing

Learn how transformer models work: self-attention, multi-head attention, positional encoding, SuperGLUE benchmarks, translation with BLEU scores, plus fine-tuning BERT and pretraining RoBERTa via Hugging Face.

• Coursera
• 6 weeks, 1 hour a week
• Self-Paced
• Paid Course

Andrej Karpathy

Let's Build GPT - From Scratch, in Code, Spelled Out

Build a GPT from scratch in PyTorch, progressing from a bigram language model to token embeddings, self-attention, and a decoder-only Transformer.

• YouTube
• 1 hour 56 minutes
• Self-Paced
• Free Video

Transformer Models and BERT Model

1 rating

Explore Transformer architecture, self-attention, and how BERT supports text classification, question answering, and natural language inference.

• Google Skills
• 30 minutes
• Self-Paced
• Free Online Course

Explore how transformer models power generative AI through Hugging Face text generation and sentiment analysis, including their carbon footprint.

• Codecademy
• 2 hours
• Self-Paced
• Free Trial Available

Build a GPT from scratch with PyTorch, training a transformer on a text corpus to generate new text.

• Codecademy
• 2 hours
• Self-Paced
• Free Trial Available

Mastering Generative AI: Language Models with Transformers

Build job-ready skills in NLP based applications using GPT and BERT in just 2 weeks! Add sought-after skills employers are looking for to your resume and power up your AI career.

• edX
• 2 weeks, 3-5 hours a week
• Self-Paced
• Free Online Course (Audit)

AI Mastery: LLMs Explained with Math (Transformers, Attention Mechanisms & More)

Work through the math inside transformers like GPT and BERT: tokenization, embeddings, sine-cosine positional encodings, query-key-value attention scores, softmax, and multi-head attention.

• Zero To Mastery
• 5 hours
• Self-Paced
• Paid Course

Stanford Seminar 2022 - DeepMind's Perceiver and Perceiver IO: New Data Family Architecture

Perceivers use asymmetric attention and a latent bottleneck to process large, varied inputs and outputs with fewer assumptions about data type.

• YouTube
• 59 minutes
• Self-Paced
• Free Video

Shaping the Future of AI from the History of Transformer Architectures - Stanford CS25

Explore the evolution of Transformer architectures and AI development with OpenAI researcher Hyung Won Chung, focusing on historical motivations and future projections in the field.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

Aladdin Persson

Pytorch Transformers from Scratch - Attention Is All You Need

Read the original Transformer paper and implement its attention, encoder, and decoder architecture from scratch in PyTorch.

• YouTube
• 57 minutes
• Self-Paced
• Free Video

Pascal Poupart

CS480-680 Lecture 19 - Attention and Transformer Networks

Lecture on attention mechanisms and transformer networks, including multihead attention, masking, recurrence, and normalization.

• YouTube
• 1 hour 23 minutes
• Self-Paced
• Free Video

Jay Alammar

The Narrated Transformer Language Model

A visual introduction to how Transformer language models tokenize text, use self-attention and feed-forward networks, and generate words from probability scores.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Alfredo Canziani

Self - Cross, Hard - Soft Attention and the Transformer

Explores self- and cross-attention through queries, keys, and values, then builds a Transformer encoder in PyTorch.

• YouTube
• 1 hour 12 minutes
• Self-Paced
• Free Video