markusdr

simpletransformers

Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

gdown

Google Drive Public File Downloader when Curl/Wget Fails

lmql

A language for constraint-guided and efficient LLM programming.

RL4LMs

A modular RL library to fine-tune language models to human preferences

lichobile

lichess.org mobile application

python-tabulate

Pretty-print tabular data in Python, a library and a command-line utility. Repository migrated from bitbucket.org/astanin/python-tabulate.

libfsm

DFA regular expression library & friends

st-annotated-text

A simple component to display annotated text in Streamlit apps.

falcontune

Tune any FALCON in 4-bit

python_example

Example pybind11 module built with a Python-based build system

alexa-teacher-models

openskill.py

Multiplayer Rating System. No Friction.

ACLPUB

The official tool for creating proceedings for conferences of the Association for Computational Linguistics (ACL).

seahorse

Seahorse is a dataset for multilingual, multi-faceted summarization evaluation. It consists of 96K summaries with human ratings along 6 quality dimensions: comprehensibility, repetition, grammar, attribution, main idea(s), and conciseness, covering 6 languages, 9 systems and 4 datasets.

Commonsense-Dialogues

A crowdsourced dataset of dialogues grounded in social contexts involving utilization of commonsense.

MACE

Multi-Annotator Competence Estimation tool

qags

Question Answering and Generation for Summarization

chess-image-generator

Accepts FEN, PGN or array data for chess board and generates PNG or buffer.

chess-graph

A program that will produce a graphical sunburst chart of chess openings from the PGN that is provided to it

fact-graph

Implementation of the paper "FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations (NAACL 2022)"

MathWithLLMs

cnn-dailymail

Code to obtain the CNN / Daily Mail dataset (non-anonymized) for summarization (Python3)

lattice-generation

Code for Massive-scale Decoding for Text Generation using Lattices

streamlit-permalink

BartGraphSumm

Implementation of the paper "Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters (NAACL 2021)"

Star-rating-using-pure-css

pure css rating

abstractive-factual-tradeoff

Code and data for the Dreyer et al (2023) paper on abstractiveness and factuality in abstractive summarization

py_common_subseq

A re-usable Python micro-library that finds all of the subsequences shared between two sequences (like strings or lists) in polynomial time.

bouncing-ball-game-with-pygame

simple bouncing ball with python and pygame

Bouncing_Balls

Simple python pygame program with basic physics.