VHellendoorn

Code-LMs

Guide to using pre-trained large language models of source code

ICLR20-Great

Data and Code for Reproducing "Global Relational Models of Source Code"

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Completion-Artifact

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

neural-nlp

[PNAS2021] The neural architecture of language: Integrative modeling converges on predictive processing

plur

PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets suitable for graph-based machine learning. We provide scripts for downloading, processing, and loading the datasets. This is done by offering a unified API and data structures for all datasets.

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

daikon

Dynamic detection of likely invariants

flash-attention-jax

Implementation of Flash Attention in Jax

Homework3

Base repo for homework 3

StudyUp

vhellendoorn.github.io