Vadimbuildercxx
Follow
-
-
mamba_fast_simple Public
Minimal and efficient JAX implementation of the Mamba State Space Model in JAX/Flax. Inspired by 'Mamba: Linear-Time Sequence Modeling with Selective State Spaces,' this repo provides fast, scalabl…
-
-
Custom_nn Public
🧠 Collection of neural network implementations from scratch. Clean PyTorch implementations with educational comments and ready training loops.
-
-
NumpyGPT Public
A lightweight educational implementation of GPT (Generative Pre-trained Transformer) using NumPy/CuPy. Features PyTorch-like syntax, GPU acceleration, and complete transformer architecture with cus…
-
-
looped_transformer Public
Experimental implementation of "Looped Transformers are Better at Learning Learning Algorithms" showing superior performance with 12x fewer parameters. Includes complete environment setup, pre-trai…
-
-
-
-