Directory
Published directory entries matching your search.
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.
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.
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.
A GreasyFork userscript, also listed on GitHub, that exports the chat history of ChatGPT. It supports copying as text and exporting as screenshot, Markdown, HTML and JSON, and an Export All option handles many conversations at once. Installation requires Tampermonkey and enabled user scripts in browser settings.
d3py is a plotting library for Python based on D3. It builds on d3.js and the pandas DataFrame module to plot data from the command line or simple scripts into a browser window. Its README describes the code as an experiment, notes that it is not actively developed, and points to vincent as an alternative.
Fliki is an AI video and audio tool that turns text, scripts, and blog posts into videos using over 2,000 AI voices in 80+ languages. It also offers text to speech, voice cloning, AI avatars, video translation, and an AI ad generator.
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.
Jupyter Notebooks as Markdown Documents, Julia, Python or R scripts.
A GitHub repository holding code for the Kaggle acquire valued shoppers challenge, including feature generation scripts. The README points to Kaggle for rules and data and to a competition page and MLWave site for tutorials and discussion.
Slides, scripts and materials for the Machine Learning in Finance course at NYU Tandon, 2022.
A GitHub repository with a preliminary implementation of the paper "Improving Factuality and Reasoning in Language Models through Multiagent Debate." It contains code for running arithmetic, GSM, biography and MMLU tasks through multiagent debate, with scripts to generate and evaluate answers. More tasks and settings are stated as forthcoming.
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.
Lightweight Bash scripts that enhance your terminal coding workflow with web-based AI assistants like Claude or Grok.
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.
A GitHub repository for topic modeling the released Sarah Palin emails using latent Dirichlet allocation. It includes scripts to prepare the emails, train an LDA model with Stanford's TMT, infer topics, extract email dates, and explore topics over time. The repository also describes a demo email browser for viewing the organized documents.
StylePile is a prompt generation helper script and extension for AUTOMATIC1111/stable-diffusion-webui and compatible forks. It mixes and matches elements that affect the style of generated results, with elements placed in a specific order and given strength values. It appears under the Scripts dropdown in txt2img and img2img.
Lets you create apps for your ML projects with deceptively simple Python scripts.
tgpt is a cross-platform command-line interface tool for using AI chatbots in the terminal. It is available for GNU/Linux, macOS, FreeBSD and Windows, and can be installed through scripts, package managers such as Homebrew, Pacman, Scoop, Chocolatey and Go, or from release executables. The project is distributed under the GPL-3.0 license.
A repository collecting system prompts, custom instructions and jailbreak prompts for various LLM providers and solutions, including ChatGPT, Microsoft Copilot, Claude, Gab.ai, Gemini and Cohere. It also contains articles, tools, and scripts, and states that its content is intended for learning and informational purposes.
threestudio is a framework for 3D content generation, described by its repository as a unified framework. The project includes configuration files, documentation, scripts and a Gradio application. It is released under the Apache-2.0 license.
timm is a collection of PyTorch image encoders and backbones, including train, eval, inference and export scripts with pretrained weights. It covers architectures such as ResNet, EfficientNet, Vision Transformer, MobileNet and ConvNeXt.
