This repository contains my personal solutions to the CS336 (Language Modeling from Scratch) course assignments from Stanford's Spring 2025 offering.
CS336 is a course focused on building language models from the ground up, covering fundamental concepts in natural language processing, tokenization, model architectures, and optimization techniques.
.
├── assignment1-basics/ # Assignment 1: Basics
│ ├── cs336_basics/ # Core implementation code
│ ├── tests/ # Unit tests
│ └── README.md # Assignment-specific instructions
└── README.md # This file
The first assignment covers fundamental concepts including:
- Tokenization and pretokenization
- Basic model implementation
- Optimization techniques
See assignment1-basics/README.md for detailed instructions and assignment1-basics/cs336_spring2025_assignment1_basics.pdf for the full assignment handout.
- Stanford CS336 course staff for providing the assignment framework and materials
- Original assignment repository and course resources