Building LLMs like ChatGPT from scratch and Cloud Deployment
- Buy now
- Learn more
- Discussions
Introduction

Course Introduction
What you'll learn
Colab Notebooks
Pre-requisites

RNNs and Attention Models
How the transformer works
Difference in training and inference
Building Mistral from scratch

Global Architecture of Mistral
Tokenization
Rotary Positional Encoding (RoPE)
RoPE Practice
Group Query Attention
Sliding Window Attention
Kv-caching
Transformer Block
Full Transformer Model
Deploying Mistral to the cloud (Runpod)

Deployment

Deployment

Lesson unavailable

Please login to your account or buy the course.