madaan

self-refine

LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

memprompt

A method to fix GPT-3 after deployment with user feedback, without re-training.

minimal-text-diffusion

A minimal implementation of diffusion models for text generation

pie-perf

Training language models to make programs faster

temporal-graph-gen

Pre-trained models for our work on Temporal Graph Generation

llm-reasoning-tutorial

Resources for few-shot reasoning tutorial

PML4DC-Comparable-Data-Collection

Code and Data for our work "Practical Comparable Data Collection for Low-Resource Languages via Images"

delic

Let's decrypt the License

defeasible_graphs

Graphs for defeasible reasoning

madaan.github.io

blog/website

pal

PaL: Program-Aided Language Models

Perfsim

Simulator for a system which has servers with load dependent service rates and customers with dynamic queue joining probabilities.

thinkaboutit

Code, data, and pre-trained models for our EMNLP 2021 paper "Think about it! Improving defeasible reasoning by first modeling the question scenario"

AIChallenge

CPP Player for AIChallenge at NSIT

aida_benchmark

ant_client

Android Client for a English to Hindi SMS Text translator

blog

Public repo for HF blog posts

char-rnn-names

Character Level RNNs for Modeling Names

chitter

Chit Distributor

cmu-10717-the-art-of-the-paper

Official repository for CMU Machine Learning Department's 10717: "The Art of the Paper".

dl2

funcs

Git 101

gcn_assignment

GCN assignment for 11441/641/741: Machine Learning for Text and Graph-based Mining (MLTGM) offered at CMU.

madaan

Config files for my GitHub profile.

pe

spell-corrector-ensemble

A repository of statistical and rule based spell correctors.

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.