Directory
Published directory entries matching your search.
GALACTICA is a general-purpose scientific language model trained on scientific text and data. This repository provides a Model API for GALACTICA, installable from pip or the repository, with five model sizes. The models can be used with the transformers library. It is a stand-alone model that is not instruction tuned, so correct prompts are needed for good results.
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.
ModelDB is an open-source system for versioning machine learning models, including their code, data, config and environment, and for tracking ML metadata across the model lifecycle. It supports reproducible models, experiment management and lifecycle tracking. It runs on Docker and Kubernetes, offers Python and Scala clients, and is maintained by Verta.ai.
Modelz LLM is an inference server for running open source large language models such as FastChat, LLaMA and ChatGLM on local or cloud environments with an OpenAI compatible API. It supports interaction through the OpenAI python SDK or LangChain and provides docker images for deployment on Kubernetes or Modelz.
modern-cpp-tricks is a GitHub repository or organization with source code, releases, documentation, or project resources.
Global, black box optimization engine for real world metric optimization by Yelp.
Montague is a semantic parsing library for Scala with an easy-to-use DSL.
MORT is a GitHub repository or organization with source code, releases, documentation, or project resources.
Machine learning model serving framework with dynamic batching and pipelined stages, provides an easy-to-use Python interface.
Mujoco is a GitHub repository or organization with source code, releases, documentation, or project resources.
N2D2 is an open source computer-aided design (CAD) framework developed for deep neural network (DNN) simulation and the construction of full DNN-based applications. It is maintained as a public code repository by the research organization CEA-LIST.
A notebook project that implements llama3 from scratch, one tensor and matrix multiplication at a time. It loads tensors directly from the model file Meta provided for llama3, and the weights must be downloaded before running the file. The author does not implement a BPE tokenizer and instead uses tiktoken.
NASGym is a proof-of-concept OpenAI Gym environment for Neural Architecture Search. It implements reinforcement learning steps for NAS and encodes networks using the Neural Structure Code from BlockQNN. A network is modeled as a list of NSCs, an action adds a layer, and the reward is accuracy after early-stop training. CIFAR-10 is the default dataset. The code and documentation may contain minor bugs.
General natural language facilities for node.
neuml/txtai is an all-in-one AI framework for semantic search, LLM orchestration, and language model workflows. It is open source and hosted on GitHub. The framework provides tools for building applications that understand and generate text.
NeuPy is a Python library built on Tensorflow for prototyping and building neural networks. The repository notes that the library is no longer actively maintained. It includes examples and notebooks covering algorithms such as Boltzmann machines and self-organizing maps.
A PyTorch implementation of the DeepDream algorithm hosted on GitHub. The repository provides code for running the DeepDream algorithm using the PyTorch framework, with support for features including specific channel selection and activation strength-based channel selection.
neural-style-pt is a PyTorch implementation of the neural style transfer algorithm from the paper A Neural Algorithm of Artistic Style. It combines the content of one image with the style of another using convolutional neural networks, and is based on Justin Johnson's Neural-Style. Options include content and style weighting, style scale, multiple style images and retaining original colors.
Neuraxle is an AutoML library that supports hyperparameter tuning via pipeline abstractions to build clean deep learning production pipelines. Pipeline steps can have associated hyperparameter spaces, and the library is compatible with Scikit-Learn, TensorFlow, and most other libraries, frameworks, and MLOps environments.
A software tool for easy and comprehensive assessment of predictive power, with support for neuroimaging features. The project is hosted on GitHub and includes sections for project news, overview, long-term goals, and citation information.
Nihonoari is a GitHub repository or organization with source code, releases, documentation, or project resources.
Nimi.li is a GitHub repository or organization with source code, releases, documentation, or project resources.
Compromise is a JavaScript natural-language processing library that turns text into data, offering tokenization of words, sentences and punctuation along with part-of-speech tagging, matching, and transformations such as verb conjugation and number handling. It runs on the client side, is about 250kb minified, and includes plugins, with multilingual support listed for French, German, Italian and Spanish.
nlp.js is a JavaScript library for building chatbots and bots, developed by AXA Group. It includes features such as entity extraction, sentiment analysis, and automatic language identification. The library is open-source and hosted on GitHub.
