Directory
Published directory entries matching your search.
SD Dynamic Prompts is a custom script built for the AUTOMATIC1111 stable-diffusion-webui. It implements a small template language that enables random generation of prompts for use with Stable Diffusion image generation workflows.
AI Models Catalog is a structured YAML catalog of AI model providers and their models, sourced from first-party APIs and official documentation. It includes TypeScript type definitions and Zod runtime validation schemas, plus scripts to sync data from providers and validate YAML files against schemas.
A repository holding the paper source, analysis notebook, and data generation and analysis scripts for the diginorm paper. It is forked from another repository and includes LaTeX sources, bibliography files, figures and a pipeline folder.
alpaca-lora is a repository with code for reproducing the Stanford Alpaca results using low-rank adaptation (LoRA). It provides an Instruct model and training code that can be easily extended to the 13b, 30b and 65b models, along with a script for downloading and inference.
Scripts to generate a dataset with static frames from the Arcade Learning Environment. Instructions cover getting Torch, placing supported Atari ROMs (freeway, pong, riverraid, seaquest, space_invaders), building the environment and Lua wrapper, and producing frames.
bitnet.cpp is the official inference framework for 1-bit LLMs such as BitNet b1.58. It provides optimized kernels for inference of 1.58-bit models on CPU and GPU, with NPU support stated as coming next. The repository includes documentation and setup scripts, and the project is released under the MIT license.
cl-online-learning is a Common Lisp library collecting machine learning algorithms for online linear classification. It implements binary classifiers including Perceptron, AROW, SCW-I, logistic regression with SGD or ADAM, and FTRL-Proximal, plus multiclass approaches such as one-vs-rest, one-vs-one, multiclass AROW and softmax with FTRL-Proximal. Command line tools are provided as a roswell script, and the package is available from Quicklisp.
DALL·E Mini is a project for generating images from a text prompt. The repository provides installation for inference and development, a training script, and links to trained models on the Hugging Face Model Hub. The model can be used on Craiyon, and community projects include DALL-E Playground and DALL·E Flow. It is released under the Apache-2.0 license.
Generating videos from scripted prompts.
EmotiVoice is an open-source text-to-speech engine that speaks English and Chinese with over 2000 voices. Its main feature is emotional synthesis across emotions such as happy, excited, sad and angry. It provides a web interface and a scripting interface for batch generation.
Glue is a Python library for exploring relationships within and among related datasets. It provides linked statistical graphics such as scatter plots, histograms and 2D and 3D images, with selections in one graph propagating to others. It supports user-specified links across datasets and scripting through Python's scientific libraries.
Guild AI is the source repository for an open source toolkit that automates and optimizes machine learning experiments. It runs unmodified training scripts, captures each run result as a unique experiment, and automates trials using grid search, random search and Bayesian optimization.
Image Super-Resolution (ISR) is a project that aims to upscale and improve the quality of low resolution images. It contains Keras implementations of Residual Dense Networks for Single Image Super-Resolution, along with scripts to train these networks using content and adversarial loss components. Pre-trained models include RDN and RRDN variants.
InVideo is an AI video editing platform that offers Agent Two, an agentic video editor designed for creatives. It enables users to edit multiple shots simultaneously, describe edits in plain language without needing prompt engineering expertise, use multiplayer mode, access storyboarding and script writing tools, and build custom editing agents.
Jinming Yang's GitHub profile describes him as a frontend engineer and AI-first builder based in Shenzhen, China. It links to current projects including ai-workflow, Vsync, UnMarket and aide, and lists legacy projects such as dom-to-code, gpt-runner and ios-scriptable-tsx.
MCP Inspector is a developer tool for inspecting Model Context Protocol (MCP) servers, shipped as a single package. It provides four ways to inspect a server: a web app with a Node backend, a scriptable command-line client, an interactive terminal UI, and an experimental connection CLI. The tool manages secrets such as OAuth tokens and stdio env values, storing them in the OS keychain by default.
An open solution to the Data Science Bowl 2018, based on the topcoders winning solution from ods.ai. The repository was archived by the owner on Jun 22, 2022 and is now read-only. It uses PyTorch and references neptune.ml, though running it as a plain Python script is possible.
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.
Pipcook is a JavaScript application framework for machine learning and its engineering, aimed at Web developers. It provides subprojects including a machine learning pipeline framework, management tools and a JavaScript runtime for machine learning. A Pipcook Pipeline composes scripts and outputs an NPM package containing the trained model and JavaScript functions. The documentation describes a workflow of install, train, test and deploy using the Pipcook command-line tool.
PyBrain is a Python machine learning library distributed under a BSD-3-Clause license. The repository includes documentation, examples, and a setup script; installation requires SciPy and is performed with python setup.py install or by cloning the repository. The project provides a quickstart, tutorials, and an API reference in its documentation.
python-timbl is a Python extension module wrapping the full TiMBL C++ programming interface, exposing all functionality of the C++ interface to Python scripts for prototyping TiMBL-based applications. It was originally developed by Sander Canisius, with a 2013 release by Maarten van Gompel, and since 2020 supports only Python 3. It is distributed under the GNU General Public License.
RedPajama-Data-v2 is a 30 trillion token open dataset from 84 CommonCrawl dumps across five languages, with over 40 precomputed quality annotations. Data processing scripts are open source on GitHub and all data are available on HuggingFace. The dataset is intended for further filtering and weighting of data, and the release notes describe it as an open dataset for training large language models.
Retext is an ecosystem of plugins that work with natural language as structured data, specifically concrete syntax trees. It is a tool that transforms natural language with plugins, which can inspect and change the natural language. The repository is a monorepo containing packages for parsing English, Dutch and Latin-script prose and serializing syntax trees.
