Phase 3: Vision-Language Model · ~90 minutes · Python

Vision Transformer Encoder

Patches alone do not see.

Hiring signal: Can build vision transformer encoder end to end

What you will learn

Implement a pre-LN transformer block with multi-head self-attention and a feed-forward sub-layer.
Stack 12 blocks with 12 heads to form a ViT-Base encoder.
Wire the patch front end from lesson 58 into the encoder and run a forward pass.
Verify that the CLS token aggregates information from every patch.

Introduction

A 12-layer pre-LN transformer with 12 attention heads turns the sequence of patch tokens into a sequence of contextual tokens, with the CLS token pooling whole-image features in its final hidden state. This lesson is the engine room of every modern vision-language model.

Type: Build Languages: Python Prerequisites: Phase 19 lessons 30-37 (Track B foundations) Time: ~90 minutes

Objective

Learning objectives

Implement a pre-LN transformer block with multi-head self-attention and a feed-forward sub-layer.
Stack 12 blocks with 12 heads to form a ViT-Base encoder.
Wire the patch front end from lesson 58 into the encoder and run a forward pass.
Verify that the CLS token aggregates information from every patch.

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.