wang-cr Goto Github PK

bert-tools

A set of simple scripts to download and process the Wikitext dataset as TFRecords and make index files for NVIDIA DALI.

bertlocrna

Using Large language model to predict localization

colossalai

Colossal-AI: A Unified Deep Learning System for Large-Scale Parallel Training

colossalai-examples

Examples of training models with hybrid parallelism using ColossalAI

colossalai-languagemodel

deeplearning

深度学习入门教程, 优秀文章, Deep Learning Tutorial

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

eigenfold

EigenFold: Generative Protein Structure Prediction with Diffusion Models

esm-diffusion

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

folding_tools

A collection of *fold* tools

homework3

ift6135_h2023_programming

ift6390-kaggle1

imagenet-tools

A set of simple scripts to process the Imagenet-1K dataset as TFRecords and make index files for NVIDIA DALI.

jointproteinfolding

kaggle2

knowreqa

megatron-lm

Ongoing research training transformer language models at scale, including: BERT & GPT-2

ncsn_excercise

Noise Conditional Score Networks (NeurIPS 2019, Oral)

openfold

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

openwebtext

An open clone of the GPT-2 WebText dataset by OpenAI. Still WIP.

pdb-struct

Source code of the paper "PDB-Struct: A Comprehensive Benchmark for Structure-based Protein Design"

peer_benchmark

PEER Benchmark, appear at NeurIPS 2022 Dataset and Benchmark Track (https://arxiv.org/abs/2206.02096)

projectchinesechess

Site of Chinese chess for WEB

refinegnn

research-paper-reading-template

A markdown template for taking notes to summarize research papers.

training

Reference implementations of MLPerf™ training benchmarks

training_results_v1.1

wang-cr.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes