💊 Comparing causality methods in a fair and just way.

Jupyter notebook tutorials about fundamental machine learning algorithms

Webapp for collaborative online retrospectives

MAGMA - a GPT-style multimodal model that can understand any combination of images and language. NOTE: The freely available model from this repo is only a demo. For the latest multimodal and multil…

💬🤖 Bring cutting-edge representation and transfer learning models to conversational AI systems

Master thesis: Exploring bias in German NLG (GPT-3 & GerPT-2). Applies regard classification and bias mitigation triggers.

🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d…

Hands-on Training for Recommender Systems

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

UIMA CAS processing library written in Python

Datafiles for justcause

trovilo collects and prepares files from Kubernetes ConfigMaps for Prometheus & friends

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

An open-source tool for sequence learning in NLP built on TensorFlow.

Train a neural slack bot from your slack team's conversations.

Deep recommender models using PyTorch.

Simple, cloud native infrastructure for Kubernetes.

Production-Grade Container Scheduling and Management

Scala DSL for Unit-Testing Processing Topologies in Kafka Streams

Turbodbc is a Python module to access relational databases via the Open Database Connectivity (ODBC) interface. The module complies with the Python Database API Specification 2.0.

Postgraas is a super simple PostgreSQL-as-a-service

Collection of software components for natural language processing (NLP) based on the Apache UIMA framework.

CNNs for sentence classification

A Python implementation of LightFM, a hybrid recommendation algorithm.

It is a forest of random projection trees

A port of Snappy, LZO, LZ4, and Zstandard to Java

Distributed, streaming anomaly detection and prediction with HTM in Apache Flink

DKPro C4CorpusTools is a collection of tools for processing CommonCrawl corpus, including Creative Commons license detection, boilerplate removal, language detection, and near-duplicate removal.