avi-jit

SWOW-eval

Intrinsic Evaluation of pre-trained word embeddings, using large Word Association Dataset: SWOW (Small World of Words)

eTok

end to end Tokenization implementation of minGPT

RateMDs

A quantitative and qualitative analysis of RateMDs.com dataset: scraped online physician reviews.

numeracy-literacy

Code for paper: "Numeracy Enhances the Literacy of Language Models"

Augmented-LMs

Living Survey of Augmented LMs

ballparkGamma

memestock-lit-review

Living Literature Review on Memestock identification using NLP

blocker

Free chrome browser extension for when you try to access a customizable set of websites.

codeLM-lit-review

Living Literature Review for Code based Language Models

compositional-generalization-lit-review

Living Survey for papers on Compositional Generalization in NLP

RadiologyQA

MSR Cambridge Internship Summer 2023

avi-jit

My personal repository

CompGen

compositional generalization experiments for fairer baselines

avi-jit.github.io

Personal webpage

chatpad

Not just another ChatGPT user-interface!

covid-india

anchoring Covid19 deaths in India to facts relatable to USC Trojans

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

factorizer

extended factorizer tokenizer

fructose

jaunts

JAUNTS Lab Webpage

lobe-chat

lobe chat local

mediumish-theme-jekyll

Jekyll Template - Mediumish

numbers-in-text

numeracy-lit-review

Living survey of NLP papers on Numeracy

pegah-lit-review

SIMOR

Single Input Multiple Output literature review

streamlit

Experiments with Streamlit

tokenization

Living Survey of Papers on Tokenization in NLP

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

work-fetch