Starred repositories
A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/
TopicGPT: A Prompt-Based Framework for Topic Modeling [NAACL'24]
AlphaGo Moment for Model Architecture Discovery.
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
JavaScript class for recording typing biometrics information/typing patterns in the browser.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
AI PDF chatbot agent built with LangChain & LangGraph
S2ORC: The Semantic Scholar Open Research Corpus: https://www.aclweb.org/anthology/2020.acl-main.447/
A Python application to upload and submit multiple files to the AssemblyAI API for transcription.
[ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Codes and Datasets for our ACL 2023 paper on cognitive reframing of negative thoughts
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.
An LLM playground you can run on your laptop
A list of pretrained Transformer models for the Russian language.
Indonesian Language Models and its Usage
Code for the paper "Measuring Bias in Contextualized Word Representations"
Library for fast text representation and classification.
AraVec is a pre-trained distributed word representation (word embedding) open source project which aims to provide the Arabic NLP research community with free to use and powerful word embedding mod…
Bias test specifications in Arabic from the paper "AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings"
3
Updated Feb 3, 2021
Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning
Code and validation datasets used to generate ValNorm scores