The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”

DL course co-developed by YSDA, HSE and Skoltech

YSDA course in Natural Language Processing

A course in reinforcement learning in the wild

HERRO is a highly-accurate, haplotype-aware, deep-learning tool for error correction of Nanopore R10.4.1 or R9.4.1 reads (read length of >= 10 kbps is recommended).

Oxford Nanopore Technologies fast5 API software

Efficient Deep Learning Systems course materials (HSE, YSDA)

A dataset for training and benchmarking deep learning models for RNA structure prediction

Oxford Nanopore's Basecaller

Joint embedding of protein sequence and structure with discrete and continuous compressions of protein folding model latent spaces. https://www.biorxiv.org/content/10.1101/2024.08.06.606920v1

Примеры продвинутого RAG

Training models for basecalling Oxford Nanopore reads

Chai-1, SOTA model for biomolecular structure prediction

Math basics course materials

Trying to train LoRAs for ESM-2

PyTorch implementation of some attentions for Deep Learning Researchers.

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

p-IgGen: A Generative Paired Antibody Language Model

Open Machine Learning course

Official repository for discrete Walk-Jump Sampling (dWJS)

Official implementation of Generative Diffusion Models for Antibody Design, Docking, and Optimization.

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

Python library to handle Gene Ontology (GO) terms