Search Results for "foundation" - Page 6
Sort By:
Showing 425 open source projects for "foundation"
View related business solutions-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
Fondant
Production-ready data processing made easy and shareable
Fondant is a modular, pipeline-based framework designed to simplify the preparation of large-scale datasets for training machine learning models, especially foundation models. It offers an end-to-end system for ingesting raw data, applying transformations, filtering, and formatting outputs—all while remaining scalable and traceable. Fondant is designed with reproducibility in mind and supports containerized steps using Docker, making it easy to share and reuse data processing components. It’s built for use in research and production, empowering data scientists to streamline dataset curation and preprocessing workflows efficiently. -
2
DeepSeek VL
Towards Real-World Vision-Language Understanding
DeepSeek-VL is DeepSeek’s initial vision-language model that anchors their multimodal stack. It enables understanding and generation across visual and textual modalities—meaning it can process an image + a prompt, answer questions about images, caption, classify, or reason about visuals in context. The model is likely used internally as the visual encoder backbone for agent use cases, to ground perception in downstream tasks (e.g. answering questions about a screenshot). The repository... -
3
Improved Diffusion
Release for Improved Denoising Diffusion Probabilistic Models
...The implementation is intended for researchers and practitioners who want to explore the theoretical and practical aspects of diffusion models in deep learning. By making this code available, OpenAI provides a foundation for further experimentation and development in generative modeling research. -
4
Autodistill
Images to inference with no labeling
Autodistill uses big, slower foundation models to train small, faster supervised models. Using autodistill, you can go from unlabeled images to inference on a custom model running at the edge with no human intervention in between. You can use Autodistill on your own hardware, or use the Roboflow hosted version of Autodistill to label images in the cloud. -
Paessler - Monitor Your Whole Network in MinutesWaiting weeks for a monitoring rollout isn't an option when infrastructure doesn't stop running. PRTG's auto-discovery scans your network and suggests from over 200 pre-configured sensor types, so you're watching servers, applications and devices within minutes, not after a multi-week deployment. Enterprise-strength monitoring, without the enterprise complexity. Start your free trial today.
-
5
Plugins Quickstart
Get a ChatGPT plugin up and running in under 5 minutes
plugins-quickstart is a starter project created by OpenAI to help developers build and deploy ChatGPT plugins quickly. It provides a minimal but complete example of how to structure a plugin, implement an API, and define the necessary configuration files. The repository demonstrates how a plugin can be served, authenticated, and integrated with ChatGPT for real-world use. By including both the backend code and plugin manifest, it guides developers through the end-to-end development workflow.... -
6
InternLM
Official release of InternLM series
InternLM is an open-source family of multilingual foundation and chat models, accompanied by an ecosystem that supports training, inference, and application development. The repository highlights multiple model sizes intended to serve different needs, from efficient research and prototyping to more capable deployments for complex scenarios. Beyond model weights, the project emphasizes an ecosystem view, pointing developers to compatible tools and projects across training and inference so teams can build end-to-end workflows. ... -
7
RWKV
RNN with great LLM performance
...This gives RWKV important advantages for long-context use, including lower memory pressure and no traditional key-value cache requirement. The repository includes training code, model notes, research material, and references to current RWKV weights. Its main value is providing the foundation for experimenting with efficient large language models that combine transformer-like scalability with RNN-like runtime behavior. -
8
MahaKurawa.My.ID URL Extractor
MahaKurawa.My.ID URL Extractor is Simple Tool to extract unique URL
MahaKurawa.My.ID URL Extractor is Simple Tool to extract unique URL from any text content in instant. It's useful when you lazy enough to identify and copy-paste URL from your content one by one by yourself. -
9
Example Streamlit
Example Streamlit app that you can fork to test out share.streamlit.io
...The project includes basic dependencies defined in requirements.txt and supports containerized development via .devcontainer. As a teaching and testing resource, it provides a foundation for experimenting with Streamlit’s rapid prototyping features. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
MAIA (MyApp Intelligence Artificial) is designed to provide a foundation for building your own voice-controlled assistant with Python. It uses various libraries and modules for speech recognition, text-to-speech synthesis, and custom functionality.
-
11
WizardLM
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
WizardLM empowers large pre-trained language models to follow complex instructions. We adopt the automatic evaluation framework based on GPT-4 proposed by FastChat to assess the performance of chatbot models. Evol-Instruct is a novel method using LLMs instead of humans to automatically mass-produce open-domain instructions of various difficulty levels and skills range, to improve the performance of LLMs. You can easily embark on your own evolutionary journey with the Evol Script we... -
12
MetaTransformer
Meta-Transformer for Unified Multimodal Learning
We're thrilled to present OneLLM, an ensembling Meta-Transformer framework with Multimodal Large Language Models, which performs multimodal joint training, supports more modalities including fMRI, Depth, and Normal Maps, and demonstrates very impressive performances on 25 benchmarks. -
13
TaskMatrix
Enable sending and receiving images during chatting
...The architecture focuses on modularity, allowing new APIs and foundation models to be integrated as interchangeable task-solving components. The project also explores low-code human-AI interaction workflows that improve controllability and transparency during complex task execution. -
14
MusicBot
The original MusicBot for Discord
MusicBot is one of the original open-source Discord music bots and is written for Python using the discord.py library. It lets users play requested songs from YouTube and other supported services into one or more Discord servers. The bot includes a configurable queue system and can automatically continue playback from an existing song list when the queue is empty. It also includes a permissions system so server owners can restrict commands to specific people or roles. Configuration is... -
15
RasaGPT
Headless Rasa chatbot platform with LLM integration and APIs
...It also enables Telegram bot integration and remote access via ngrok. Docker support allows easier setup and deployment, particularly on macOS environments. While designed as a working prototype, it provides a practical foundation for developers building LLM-powered chatbot applications with extensible architecture and preconfigured components. -
16
pyllama
LLaMA: Open and Efficient Foundation Language Models
📢 pyllama is a hacked version of LLaMA based on original Facebook's implementation but more convenient to run in a Single consumer grade GPU. -
17
Python library to automate X11. Simulate mouse movement and mouse clicks, keystrokes, and manipulate windows from Python. Alter the state of caps lock, num lock, and scroll lock. Also access the X11 clipboard. The C library would be useful for those wishing to automate X from another language as well.
-
18
rust.vim
Vim configuration for Rust
...Because Rust’s macro system and language features are more complex than many languages, rust.vim handles special tokens and highlights accordingly. Though it doesn’t itself provide full language-server (LSP) capabilities, it lays the foundation so you can plug in LSP or other completion/diagnostic plugins. Many Rust users say that rust.vim is a reliable baseline for making Vim feel like a competent Rust editor rather than a bare text editor. -
19
MaskFormer
Per-Pixel Classification is Not All You Need for Semantic Segmentation
MaskFormer is a unified framework for image segmentation developed by Facebook Research, designed to bridge the gap between semantic, instance, and panoptic segmentation within a single architecture. Unlike traditional segmentation pipelines that treat these tasks separately, MaskFormer reformulates segmentation as a mask classification problem, enabling a consistent and efficient approach across multiple segmentation domains. Built on top of Detectron2, it supports a wide range of datasets... -
20
deoplete.nvim
Dark powered asynchronous completion framework for neovim/Vim8
deoplete.nvim is an asynchronous completion framework for Neovim and Vim 8. It was designed to provide extensible code-completion behavior while avoiding the blocking feel of older synchronous completion plugins. The framework can display completion candidates through Vim’s built-in completion interface and can be extended with dedicated completion sources. It supports a plugin ecosystem where different languages, tools, and contexts can provide their own candidate sources. deoplete.nvim is... -
21
PyG2Plot
Python3 binding Plotting Library
PyG2Plot is a Python 3 binding for AntV G2Plot, an interactive and responsive charting library. It lets Python users create statistical charts through a small amount of code while relying on G2Plot’s grammar-of-graphics foundation. The library is inspired by pyecharts and is designed to make web-based charts available from Python workflows. Users create a Plot instance, set chart options, and render the result as an HTML file, HTML string, notebook preview, or JupyterLab output. It also supports JavaScript callbacks through a JS helper, which makes advanced customization possible when chart behavior needs JavaScript logic. ... -
22
...By leveraging CNN architectures, the project showcases how learned embeddings can capture semantic similarity across varied images. This resource serves as both an educational reference and a foundation for further exploration in image retrieval research.
-
23
Sparse Attention
"Generating Long Sequences with Sparse Transformers" examples
Sparse Attention is OpenAI’s code release for the Sparse Transformer model, introduced in the paper Generating Long Sequences with Sparse Transformers. It explores how modifying the self-attention mechanism with sparse patterns can reduce the quadratic scaling of standard transformers, making it possible to model much longer sequences efficiently. The repository provides implementations of sparse attention layers, training code, and evaluation scripts for benchmark datasets. It highlights... -
24
Retro
Retro Games in Gym
...It includes example configurations, datasets, and utilities for building retrieval-augmented generation systems. RETRO represents an important step toward combining large-scale language modeling with information retrieval, offering researchers a foundation to study hybrid approaches for scaling AI responsibly. -
25
PixelCNN
Code for the paper "PixelCNN++: A PixelCNN Implementation..."
PixelCNN is the official implementation from OpenAI of the autoregressive generative model described in the paper Conditional Image Generation with PixelCNN Decoders. It provides code for training and evaluating PixelCNN models on image datasets, focusing on conditional image modeling where pixels are generated sequentially based on the values of previously generated pixels. The repository demonstrates how to apply masked convolutions to enforce autoregressive dependencies and achieve...
