gystar

devign_lab

LLVMExploration

asm2vec-pytorch

Unofficial implementation of asm2vec using pytorch ( with GPU acceleration )

CLCDSA

CLCDSA: Cross Language Code Clone Detection using Syntactical Features and API Documentation

code_transformers

Empirical Study of Transformers for Source Code & A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code

CodeGen

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.

CodeT5

Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

concrete

Concrete: TFHE Compiler that converts python programs into FHE equivalent

deepvsa

DeepWukong

devign

cv_data_pipeline

dnn-binary-code-similarity

EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

EKLAVYA

G2SC

LLM_Tutorial2023

mbrl

MPCFormer

(ICLR 2023 Spotlight) MPCFormer: fast, performant, and private transformer inference with MPC

OSCAR

Code for ICML 2021 paper: How could Neural Networks understand Programs?

PlaNet

Deep Planning Network: Control from pixels by latent planning with learned dynamics

Private-LLM-Inference

ProGraML

Graph-based Program Representation & Models for Deep Learning

pyenv

Simple Python version management

pyHGT

Code for "Heterogeneous Graph Transformer" (WWW'20), which is based on pytorch_geometric

spu

SPU (Secure Processing Unit) aims to be a provable, measurable secure computation device, which provides computation ability while keeping your private data protected.

TransCoder

Public release of the TransCoder research project https://arxiv.org/pdf/2006.03511.pdf

V8-RVV

RISC-V Vector Support in V8

VulnerabilityDetectionResearch

VulnerabilityDetectionResearch

zsh-autosuggestions

Fish-like autosuggestions for zsh