Yash Kumar Atri's starred repositories
mslr-shared-task
Multidocument Summarization for Literature Review Shared Task 2022
openhathi_instruct
This repository contains the code for dataset curation and finetuning of instruct variant of the Bilingual OpenHathi model. The resulting model is meant to follow instructions and chat in Hindi and Hinglish.
pubmed_parser
:clipboard: A Python Parser for PubMed Open-Access XML Subset and MEDLINE XML Dataset
awesome-fairness-papers
Papers on fairness in NLP
awesome-topological-deep-learning
A curated list of topological deep learning (TDL) resources and links.
flash-attention
Fast and memory-efficient exact attention
TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
episodic-transformer-memory-ppo
Clean baseline implementation of PPO using an episodic TransformerXL memory
transformers-interpret
Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.
accelerate
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
audiolm-pytorch
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
MLfromscratch
Machine Learning algorithm implementations from scratch.
tensorly-notebooks
Tensor methods in Python with TensorLy
wae-rnf-lm
Pytorch Implemetation for our NAACL2019 Paper "Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling" https://arxiv.org/abs/1904.02399
long-summarization
Resources for the NAACL 2018 paper "A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents"
multimodal
TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.
x-transformers
A simple but complete full-attention transformer with a set of promising experimental features from various papers
ODE-Transformer
This is a code repository for the ACL 2022 paper "ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation", which redesigns the Transformer architecture from the ODE perspective via using high-order ODE solvers to enhance the residual connections.