Implementations

Implementations of literally the most random things for my own practice.

Models

Transformer model with Multi-head attention. (a) Get it working (b) Implement KV-caching (c) Implement a mini GPT (maybe GPT-2 or something) model

TODOs:

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
cpp		cpp
cses/intro		cses/intro
data_structures		data_structures
llm		llm
models		models
notebooks		notebooks
ocaml		ocaml
papers		papers
rpc		rpc
.gitignore		.gitignore
README.md		README.md