Stefan Schweter's starred repositories
torchtitan
A native PyTorch Library for large model training
recurrentgemma
Open weights language model from Google DeepMind, based on Griffin.
community-content
Hetzner Online Community Project
improved-t5
Experiments for efforts to train a new and improved t5
transformer-smaller-training-vocab
Temporary remove unused tokens during training to save ram and speed.
fundus-evaluation
Evaluation of the Fundus News Scraper https://github.com/flairNLP/fundus
eacl24-german-legal-questions
Data and code: "Answering legal questions from laymen in German civil law system", Büttner & Habernal, EACL'24
tech-report
Raw data, scripts, etc. to produce the tables and figures of our technical report
ChroniclingAmericaQA
ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper Pages
Multi-Level-Training-Framework
Official implementation of "A Multi-level Framework for Accelerating Training Transformer Models""
umLabeller
Inspection tool for characterizing the semantic compositionality of subword tokenization in English
newsagency-classification
Recognition of news agency mentions in historical news articles (BERT-based token classification).
maibaam-code
Code for preprocessing data for UD annotations and for tagging/parsing experiments of MaiBaam
turkish-lm-bias
Investigating Gender Bias in Turkish Language Models