Skip to content
View Tsuskov's full-sized avatar
🦇
Locked in
🦇
Locked in
  • Berlin
  • 19:30 (UTC +02:00)

Highlights

  • Pro

Block or report Tsuskov

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Tsuskov/README.md

Tim Suskov

Berlin. Incoming mathematics student, interested in machine learning systems built from first principles.

Portfolio: tsuskov.github.io

Selected projects

LLM stack from scratch (Rust)

A complete language-model pipeline, written by hand without ML frameworks:

Stage Repository
Tokenization Cadmus Byte-level BPE tokenizer — the merge-learning algorithm implemented from scratch
Training Hephaistos GPT/Llama-style model with hand-written forward pass and backpropagation, every gradient numerically verified; exports to GGUF
Inference Talos Minimal inference engine with an opt-in Metal GPU backend (2.8–3.7× the CPU path)
Deployment Talos Forge The full stack compiled to WebAssembly — live demo

Other work

  • raytracing — real-time CPU raytracer in Rust: multithreaded, BVH-accelerated, 4K export
  • strange-attractors — interactive 3D visualization of the Lorenz and Rössler attractors, RK4 integration
  • AloeGarden — SwiftUI focus-reading app for iOS with Home and Lock Screen widgets
  • orbitale — hydrogen-atom orbitals (s, p, d, f) rendered as electron-density plots in the terminal

Currently

Learning theorem proving in Lean 4 (Mathematics in Lean) in preparation for university mathematics.

Pinned Loading

  1. Posaidon Posaidon Public

    A small GPT built from scratch in MLX, grown from a char-level toy into a Llama-style model.

    Python

  2. Hephaistos Hephaistos Public

    A GPT/Llama-style language model built from scratch in Rust — hand-written forward & backprop, every gradient numerically verified, trained on CPU, exported to GGUF for llama.cpp & Ollama.

    Rust

  3. nbapredictions nbapredictions Public

    Python

  4. ren-ascii-sance ren-ascii-sance Public

    Renaissance-Figuren als Konturen und farbige Block-ASCII-Art (YOLO-Segmentierung)

    Python

  5. U-Net_sandbox U-Net_sandbox Public

    Python

  6. strange-attractors strange-attractors Public

    Interactive 3D visualization of the Lorenz and Rössler attractors in Rust, with real-time RK4 integration

    Rust