Manas-Embold's repositories
AI-Expert-Roadmap
Roadmap to becoming an Artificial Intelligence Expert in 2021
aroma-paper-artifacts
Paper Artifacts for "Aroma: Code Recommendation via Structural Code Search"
BASTS
This is the code repository for our ICPC 2021 paper "Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting"
code-maat
A command line tool to mine and analyze data from version-control systems
CodeBERT
CodeBERT
CodeTrans
Pretrained Language Models for Source code
commit-autosuggestions
A tool that AI automatically recommends commit messages.
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
fastT5
⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
FUNDED_NISL
FUNDED is a novel learning framework for building vulnerability detection models.
ghs
GitHub Search Engine: Web Application used to retrieve, store and present projects from GitHub, as well as any statistics related to them.
gpt-neo
An implementation of model parallel GPT2& GPT3-like models, with the ability to scale up to full GPT3 sizes (and possibly more!), using the mesh-tensorflow library.
gpt-neox
An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.
GraphRepo
Github repo to Neo4j (and back)
horusec
Horusec is an open source tool that improves identification of vulnerabilities in your project with just one command.
hybrid-linker
A hybrid method for recovering links between issue reports and their respective commits
Megatron-LM
Ongoing research training transformer language models at scale, including: BERT & GPT-2
mesh-transformer-jax
Model parallel transformers in JAX and Haiku
OCTIS
OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)
outrun
Execute a local command using the processing power of another Linux machine.
porting
Helper scripts and notes that were used while porting various nlp models
Project_CodeNet
This repository is to support contributions for tools for the Project CodeNet dataset hosted in DAX
PyART
DataSet and source code for PyART
tourniquet
A Python library for easy and fast program transformation/repair
vulnerablecode
A free and open vulnerabilities database and the packages they impact. And the tools to aggregate and correlate these vulnerabilities. Sponsored by NLnet https://nlnet.nl/project/vulnerabilitydatabase/ for https://www.aboutcode.org/ Chat at https://gitter.im/aboutcode-org/vulnerablecode