zichaow

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

screenshot-to-code

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

Mr.-Ranedeer-AI-Tutor

A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.

search_with_lepton

Building a quick conversation-based search demo with Lepton AI.

pdfminer.six

Community maintained fork of pdfminer - we fathom PDF

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

layout-parser

A Unified Toolkit for Deep Learning Based Document Image Analysis

EasyEdit

An Easy-to-use Knowledge Editing Framework for LLMs.

SoM

Set-of-Mark Prompting for LMMs

natural-questions

Natural Questions (NQ) contains real user questions issued to Google search, and answers found from Wikipedia by annotators. NQ is designed for the training and evaluation of automatic question answering systems.

textbook_quality

Generate textbook-quality synthetic LLM pretraining data

Awesome-LLM4RS-Papers

Large Language Model-enhanced Recommender System Papers

pawls

Software that makes labeling PDFs easy.

web-explorer

EduData

Edudata: Datasets in Education and convenient interface for downloading and preprocessing dataset in education

pykt-toolkit

pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models

UniSRec

[KDD'22] Official PyTorch implementation for "Towards Universal Sequence Representation Learning for Recommender Systems".

living-papers

Authoring tools for scholarly communication. Create interactive web pages or formal research papers from markdown source.

AutoLyrixAlign

Pre-trained model and script to automatically align lyrics to polyphonic audio

Get-Another-Label

Quality control code for estimating the quality of the workers in crowdsourcing environments

vrdu

We identify the desiderata for a comprehensive benchmark and propose Visually Rich Document Understanding (VRDU). VRDU contains two datasets that represent several challenges: rich schema including diverse data types, complex templates, and diversity of layouts within a single document type.

HGRN

[NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Sequence Modeling

GRACE

[NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

WikipediaQA

mathdial

🧮 MathDial: A Dialog Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems, EMNLP Findings 2023

SeqBoat

[NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling

living-papers-template

A Living Papers article starter template.

bubbleview

BubbleView: an interface for crowdsourcing image importance maps and tracking visual attention

halie

LLM-personalization

We enable LLM with personalization capability