Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

freeCodeCamp

Code DeepSeek V3 From Scratch in Python - Full Course

via freeCodeCamp

Start learning Write review
Scrimba Ad

Get 20% off all career paths from fullstack to AI

Learn More → Babbel Ad

Start speaking a new language. It’s just 3 weeks away.

Learn More →

Overview

Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This course implements DeepSeek V3 from scratch in Python. It covers attention mechanisms, KV caching, Multihead Latent Attention, RoPE, mixture-of-experts gating, and transformer blocks.

Syllabus

⌨️ 0:00:00 Intro
⌨️ 0:01:40 Attention Mechanism
⌨️ 0:13:34 Query, Key, Value
⌨️ 0:34:11 KV Cache
⌨️ 0:39:06 Multihead Latent Attention MLA
⌨️ 0:58:53 Coding MLA
⌨️ 1:28:41 RoPE
⌨️ 1:55:44 Coding KV Cache
⌨️ 2:00:25 MLA forward
⌨️ 2:28:24 MoE, Gate
⌨️ 2:49:25 Gate code
⌨️ 3:09:10 MoE code
⌨️ 3:28:36 Transformer Blocks

Taught by

freeCodeCamp.org

Reviews

Start your review of Code DeepSeek V3 From Scratch in Python - Full Course

Start learning

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.