Skip to content

Learning and side by side maintaining a set of architectures' code written in Burn cuz why not? AI wont do it for me.

License

Notifications You must be signed in to change notification settings

Ibzie/Burn-Deep-Learning-Implementations

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Burn Deep Learning Implementations

From-scratch implementations of ML/DL architectures in Rust using Burn. Built for learning — every layer, every gradient, every training loop written by hand.

Why Rust + Burn?

  • No hidden magic — No high-level wrappers hiding what's actually happening
  • Performance — Native speed with GPU acceleration via WGPU
  • Type safety — Tensor dimensions checked at compile time
  • Learning — If you can build it in Rust, you truly understand it

Implementations

Architecture Description Status
Transformer Decoder-only Transformer (GPT-style) trained on Urdu Wikipedia Done

Transformer

A ~10M parameter decoder-only Transformer for Urdu text completion. Includes:

  • Multi-head self-attention with causal masking
  • Pre-LayerNorm transformer blocks
  • Byte-level BPE tokenizer (10K vocab)
  • Full training pipeline with GPU acceleration (WGPU)
  • Interactive inference REPL

Trained on Urdu Wikipedia, generates Wikipedia-style Urdu prose.

Model on Hugging Face: Ibzie/Urdu-Completion-Transformer-10M

See the Transformer README for full details.

Getting Started

Each implementation is a standalone Rust project. To run one:

cd Transformer
cargo run --release --bin train   # Train the model
cargo run --release --bin infer   # Run inference

Prerequisites

  • Rust 1.70+
  • GPU with Vulkan/Metal/DX12 support (for WGPU backend)

Contributing

Contributions and new architecture implementations are welcome! If you'd like to add an implementation:

  1. Create a new directory for the architecture
  2. Include a README with architecture details and usage
  3. Open a PR

Stars are appreciated if you find this useful.

License

MIT - see LICENSE

Author

Ibrahim Akhtar (@Ibzie)

About

Learning and side by side maintaining a set of architectures' code written in Burn cuz why not? AI wont do it for me.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages