A self-hosted ML coding practice platform. 68 problems from ReLU to flow matching — attention, training, RLHF, diffusion, and more. Instant feedback in the browser.
Pulse
96
Velocity
3.2x
Stars
490
Self-hosted ML coding platform to implement AI internals from scratch.
Implement complex AI model internals from scratch in a browser-based coding environment.
Learn AI by implementing Transformers, vLLM, and diffusion models from scratch, no GPU needed.
Why Trending
Hands-on learning of cutting-edge AI architectures like diffusion and RLHF.
Target Audience
ML engineers and researchers wanting to understand AI model internals.
Similar Projects