Rustam Akimov

numpy-nn-model. Сustom torch style machine learning framework with automatic differentiation implemented on numpy, allows build GANs, VAEs, etc.

numpy-transformer. A numpy implementation of the Transformer model in "Attention is All You Need"

llm-agent. LLM using long-term memory through vector database

CLIP-search. An impelementation of image search engine using CLIP (Contrastive Language-Image Pre-Training

basic-ml-algorithms. Python implementations of basic machine learning algorithms

python-2d-physics. A simple 2D physics simulation implemented in Python

numpy-diffusion. A numpy Denoising Diffusion Probabilistic Model (DDPM) implementation

GPT. A PyTorch implementation of the GPT (Generative Pre-trained Transformer) model.

reinforcement-learning. Different RL Algorithms

cats-dogs-classifier. Свёрточная нейронная сеть, распознающая кошек и собак на изображении

digits-recognizer. Полносвязная нейронная сеть, распознающая цифры

cuda-python-kernels. Just a few cuda kernels with ability to use it from python as dll

stable-diffusion-gradio. Hugging Face Stable Diffsuion interface implemented on gradio library

itmo-lama. Jupyter Notebook

itmo-clearml-pipelines.