Tushaar Gangavarapu's repositories
backprop-lecture-notes-CS-4740
Lecture notes on backpropagation
NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
phd-advice
A repository of links with advice related to grad school applications, research, phd etc
bea-2023
BEA 2023
annotated-mamba
Annotated version of the Mamba paper
attorch
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
ConvoKit
ConvoKit is a toolkit for extracting conversational features and analyzing social phenomena in conversations. It includes several large conversational datasets along with scripts exemplifying the use of the toolkit on these datasets.
CRAFT
Author's implementation of the CRAFT neural architecture from "Trouble on the Horizon" (EMNLP '19)
cs4220-s23
Course materials for Cornell CS 4220 / Math 4260 / CS 5223 for Spring 2023.
cs4300-project-sp-2023
CS 4300 project template (sp23)
DeepLearningExamples
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
ecco
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).
fft-conv-pytorch
Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
GPT
Implementation of Generative Pre-trained Transformer Model in Tensorflow
graduate-admissions
Repository containing SoPs and other reference material for Graduate admission process.
jpc-job-apps-2023
Repository for my application materials for 2023 teaching-track openings. Freely available as a resource to the public!
LLMTest_NeedleInAHaystack
Doing simple retrieval from LLM models at various context lengths to measure accuracy
mamba-minimal
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
memory-efficient-attention-pytorch
Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
nlp-library
curated collection of papers for the nlp practitioner 📖👩🔬
nlp-recipes
Natural Language Processing Best Practices & Examples
recurrentgemma-xai
Open weights language model from Google DeepMind, based on Griffin.
RL4LMs
A modular RL library to fine-tune language models to human preferences
sotawhat
Returns latest research results by crawling arxiv papers and summarizing abstracts. Helps you stay afloat with so many new papers everyday.
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
tushaargvs.github.io
Personal (academic) website