Directory
Published directory entries matching your search.
An archived, read-only GitHub repository holding an open solution to the Google AI Open Images Object Detection Track. It offers starter code, configs and notebooks, with RetinaNet training and references to the Neptune experiment platform; Neptune use is optional and the code can run as a plain Python script. The README notes the competition used Open Images Dataset V4.
An archived, read-only GitHub repository holding an open solution to the Home Credit Default Risk challenge. It provides code, configs and notebooks plus documented solutions using LightGBM, sklearn and XGBoost with engineered features; the README lists cross-validation and leaderboard scores for each. References to Neptune are optional and the solution can run as a plain Python script.
A repository archived by its owner and now read-only. It is an open solution to the TGS Salt Identification Challenge. The project is listed with data science and image segmentation topics. The readme states that support can no longer be provided.
Optimum-TPU is a Hugging Face project providing Google TPU optimizations for transformers models, aiming to ease training and inference on TPUs. It supports text generation models including Gemma, Llama2, Llama3 and Mistral, and includes a text-generation-inference backend. The repository was archived in January 2026 and is read-only, with the project in maintenance mode.
Oryx 2 is a realization of the lambda architecture built on Apache Spark and Apache Kafka, specialized for real-time large scale machine learning. It is a framework for building applications and includes packaged end-to-end applications for collaborative filtering, classification, regression and clustering. The repository was archived by the owner on May 3, 2022, and is read-only.
Pattern is a web mining module for Python with tools for data mining, natural language processing, machine learning, and network analysis and visualization. The repository is archived and no longer maintained, receiving no further updates, bug fixes or security patches.
Flappy is an SDK for building applications and agents that use large language models, organized as a monorepo with libraries in several programming languages. The repository was archived by its owner on Jun 13, 2024, and the project was described at the time as still under development.
Ploomber is a tool for building data pipelines. It offers a YAML API and a Python API, and its features include caching previous pipeline results and running on Kubernetes, Airflow, AWS Batch or SLURM. It can convert monolithic notebooks into modular pipelines. The repository was archived on Jul 12, 2025 and is read-only.
A Python wrapper around the ZPar statistical natural language parser, providing a ctypes-based interface and an XML-RPC ZPar server for batch processing. It works only with English ZPar models and supports 64-bit Linux and OS X. The repository was archived on Sep 13, 2022 and is read-only; the project is no longer under active development.
Scikit-Optimize, or skopt, is a library for minimizing expensive and noisy black-box functions using sequential model-based optimization. It is built on NumPy, SciPy and Scikit-Learn and does not perform gradient-based optimization. The repository was archived by its owner on Feb 28, 2024, and is read-only.
simulate-sdk is a Python SDK for the Simulate pillar of Future AGI. It runs voice and text agents against persona-driven scenarios, captures transcripts and audio, and passes results into the Evaluate pillar for scoring. The repository was archived by the owner on Sep 29, 2026, and is now read-only.
Skale is a distributed data processing and machine learning engine that provides a high-level API in JavaScript and a parallel execution engine on top of Node.js. The repository was archived by its owner on May 29, 2021 and is read-only. It supports multiple data sources and formats, and can run in local or distributed mode.
Soorgeon is a tool that converts monolithic Jupyter notebooks into Ploomber pipelines. It is compatible with Python 3.7 and higher and installs via pip. The repository was archived by its owner on Feb 18, 2025, and is now read-only. The project describes itself as being in alpha.
Summingbird is a library for writing MapReduce programs that resemble native Scala or Java collection transformations and running them on distributed MapReduce platforms including Storm and Scalding. Programs can execute in batch mode, realtime mode, or a hybrid mode combining Scalding and Storm. The repository was archived by its owner on Jan 20, 2022 and is read-only.
Text Generation Inference is a toolkit for deploying and serving large language models, implemented as a Rust, Python and gRPC server. It supports models including Llama, Falcon, StarCoder, BLOOM and GPT-NeoX, with features such as token streaming, continuous batching and quantization. The repository is archived, read-only, and in maintenance mode, with pull requests limited to minor bug fixes and maintenance.
TF-GAN is a lightweight library for training and evaluating Generative Adversarial Networks in TensorFlow. It provides core training infrastructure, common GAN operations and normalization techniques, losses and penalties such as the Wasserstein loss and gradient penalty, and standard evaluation metrics including Inception Score, Frechet Distance and Kernel Distance. It can be installed with pip. The repository was archived and is now read-only.
TorchText provides models, data loaders and abstractions for language processing, powered by PyTorch. The library includes dataset iterators, basic NLP building blocks, text-processing transformations, pre-trained models and vocabulary classes. The repository was archived by its owner on Sep 10, 2025, and is now read-only; development is stopped with 0.18 the last stable release.
A public archive of acceleration techniques for the Stable Diffusion model intended to help generate images faster and more efficiently. It covers AITemplate, nvFuser, TensorRT and FlashAttention, with example images and benchmarks. The repository was archived by the owner on Oct 24, 2025, and is now read-only.
