chkla

WebBot

Browser extension to simulate browsing behaviour in search engines.

scripts-to-rule-them-all

Set of boilerplate scripts describing the normalized script pattern that GitHub uses in its projects.

PolData

A dataset with political datasets

mamba

cleanlab

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

gov2002-f23

Course website for Gov 2002 at Harvard (Fall 2023)

gov2002-book

An Introduction to Statistical Inference and Regression

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

nlp-research-template

An opinionated NLP research template

SBSCD

reference-framing-perspective

Workshop website

Data-Provenance-Collection

typst

A new markup-based typesetting system that is powerful and easy to learn.

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

codecarbon

Track emissions from Compute and recommend ways to reduce their impact on the environment.

pol_emo_mDeBERTa2

A multilingual DeBERTa model fine-tuned on political communication to classify discrete emotions

modified_adsorption

Python implementation of the random-walk inductive classification algorithm Modified Adsorption from P. Talukdar

rix

Reproducible development environments for R with Nix

hfapi

Thin R wrapper around the Huggingface Inference API

atrrr

AT Protocol (Authenticated Transfer Protocol behind Bluesky) R package

fastembed

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

dolma

Data and tools for generating and inspecting OLMo pre-training data.

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

ecosystem-graphs

political-moral-emotional-mDeBERTa

A mDeBERTa model fine-tuned to classify positive and negative moral and emotional appeals in political communication.

open-interpreter

A natural language interface for computers

prompt2model

prompt2model - Generate Deployable Models from Natural Language Instructions

openLLMs-LearningAID

Talk 🗣️ on "Standards and Open-Source Large Language Models for Academic Writing" @ LearningAID 2023

dspy

DSPy: The framework for programming—not prompting—foundation models

Populism-Text-Analysis

Literature 📄 and datasets 📚 on automatic populism detection