VHellendoorn/Code-LMs
Guide to using pre-trained large language models of source code
AI4SE Researcher, Assistant Prof. at CMU
Repositories
VHellendoorn/ICLR20-Great
Data and Code for Reproducing "Global Relational Models of Source Code"
VHellendoorn/vhellendoorn.github.io
VHellendoorn/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
VHellendoorn/Completion-Artifact
VHellendoorn/sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
VHellendoorn/neural-nlp
[PNAS2021] The neural architecture of language: Integrative modeling converges on predictive processing
VHellendoorn/daikon
Dynamic detection of likely invariants
VHellendoorn/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.
VHellendoorn/flash-attention-jax
Implementation of Flash Attention in Jax
VHellendoorn/gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
VHellendoorn/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
VHellendoorn/StudyUp
VHellendoorn/Homework3
Base repo for homework 3