burtenshaw

advent

agenta

The LLMOps platform to build robust LLM apps. Easily experiment and evaluate different prompts, models, and workflows.

argilla

✨ Open-source tool for data-centric NLP. Argilla helps domain experts and data teams to build better NLP datasets in less time.

AutoOPRO

bs4_scraping

A quick introductory class to scraping with beautiful soup and wrangling scraped tables with pandas.

burtenshaw.github.io

Personal for website research, design, code, and life.

ccnlg

CCNLG Proceedings

CCNLG_2019

Convert data from EasyChair for use with aclpub

movie-chatter

See-Whence

Sequence classification base code, used for PhD thesis and SemEval 2020 sarcasm detection.

soft_conv

Parsing and wrangling package for Whatsapp and Facebook conversations. Interprets multiple formats and incorporates annotator validation.

spanwijdte

Binary and Multilabel toxic span detection in Dutch.

wingspan

Toxic span detection system submitted to SemEval Task 5 2021.

burtenshaw

data-is-better-together

Let's build better datasets, together!

distilabel

⚗️ AI Feedback framework for scalable LLM alignment

doccano

Open source text annotation tool for machine learning practitioner.

dta

faqscraper

instructdantic

kidscrawler

A child safe web crawler

llm-autoeval

Automatically evaluate your LLMs in Google Colab

OpenNMT-py

Open-Source Neural Machine Translation in PyTorch http://opennmt.net/

orpo

Official repository for ORPO

productizing_os_llms

RelGraph

Data Science project on topic and relationship analysis, using the Harry Potter series as a case study.

seqmod

Sequence modelling with pytorch

share-lm

ShareLM is a Chrome extension that lets you share your open-source conversations

trl

Train transformer language models with reinforcement learning.

weasimov-documentation