Fondant is an open source framework for data preparation and fine-tuning of foundation models, developed by ML6 together with the open source community. Our goal is to make it easy and efficient to fine-tune large foundation models based on specific knowledge domain data.

Connexion

Connexion is the Python web framework that enables you to build API-first. We have been maintaining it since 2021, working towards a major 3.0 release. With around 5 million downloads per month, it is a staple of the Python API ecosystem.

Connexion Docs

View more
Infrastructure

Connexion Repository

View more

Why we decided to help maintain connexion

View more

Apache Beam

Apache Beam is a framework for unified batch and streaming pipelines, which is mostly known as the framework underlying Google Cloud Dataflow, but can be run on almost any distributed processing backend such as Apache Flink or Spark. We have ported Apache Beam to Python 3, added ML inference functionality, and created a lot of content for the community.

Apache Beam Blogpost

View more

Apache Beam AI/ML Docs

View more

Apache Beam Repo

View more

Hugging face

We leverage Hugging Face a lot in our solutions, but we also contribute back. We have published models, datasets, and demos for the community. Check our space for more.

Natural language processing

German Toxic Comment Detection

View more
Structured Data

Dynamic Pricing

View more
Natural language processing

Semantic Search Demo

View more
Natural language processing

Terms & Conditions Summarizer

View more
Generative AI

Logo Generator

View more

GitHub

Github is the home for all our open source code projects. Check our Github page for an overview of all our repositories.

Natural language processing

Explainable transformers using SHAP

View more
Natural language processing

Neural Keyword Extraction

View more
Natural language processing

Text Augmentation using large-scale LMs and prompt engineering

View more
Natural language processing

Gender debaising of datasets using CDA

View more
Natural language processing

GPT2 Quantization using ONNXRuntime

View more
Structured Data

Vertex AI TensorBoard alternative for smaller budgets

View more