Search Results for "example" - Page 8
Sort By:
Showing 317 open source projects for "example"
View related business solutions-
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
OnnxStream
Lightweight inference library for ONNX files, written in C++
The challenge is to run Stable Diffusion 1.5, which includes a large transformer model with almost 1 billion parameters, on a Raspberry Pi Zero 2, which is a microcomputer with 512MB of RAM, without adding more swap space and without offloading intermediate results on disk. The recommended minimum RAM/VRAM for Stable Diffusion 1.5 is typically 8GB. Generally, major machine learning frameworks and libraries are focused on minimizing inference latency and/or maximizing throughput, all of which... -
2
DeepSeek MoE
Towards Ultimate Expert Specialization in Mixture-of-Experts Language
DeepSeek-MoE (“DeepSeek MoE”) is the DeepSeek open implementation of a Mixture-of-Experts (MoE) model architecture meant to increase parameter efficiency by activating only a subset of “expert” submodules per input. The repository introduces fine-grained expert segmentation and shared expert isolation to improve specialization while controlling compute cost. For example, their MoE variant with 16.4B parameters claims comparable or better performance to standard dense models like DeepSeek 7B or LLaMA2 7B using about 40% of the total compute. The repo publishes both Base and Chat variants of the 16B MoE model (deepseek-moe-16b) and provides evaluation results across benchmarks. It also includes a quick start with inference instructions (using Hugging Face Transformers) and guidance on fine-tuning (DeepSpeed, hyperparameters, quantization). ... -
3
SSD in PyTorch 1.0
High quality, fast, modular reference implementation of SSD in PyTorch
...Add your own modules without pain. We abstract backbone, Detector, BoxHead, BoxPredictor, etc. You can replace every component with your own code without changing the code base. For example, You can add EfficientNet as the backbone, just add efficient_net.py (ALREADY ADDED) and register it, specific it in the config file, It's done! Smooth and enjoyable training procedure: we save the state of model, optimizer, scheduler, training iter, you can stop your training and resume training exactly from the save point without change your training CMD. -
4
YYeTsBot
Renren Film and Television bot, fully connected to Renren resources
...When searching for resources, it will be searched according to my predetermined priority (everyone video offline, subtitle man), of course, you can also use commands to force a subtitle group. Due to the difference in translations, it is recommended to enter a partial translation and then select from the list. For example, if you want to watch the fourth season of Game of Thrones, just search for "Game of Thrones". Want to keep a resource for yourself, but don't know how to program? It doesn't matter! There are currently two methods available, please choose according to your own situation. -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
5
Mixtral offloading
Run Mixtral-8x7B models in Colab or consumer desktops
Mixtral-Offloading is an open-source project designed to enable efficient inference of large Mixture-of-Experts language models such as Mixtral-8x7B on hardware with limited GPU memory. The project implements techniques that allow model components to be dynamically moved between CPU memory and GPU memory during inference, significantly reducing the amount of GPU VRAM required to run the model. This approach takes advantage of the sparse activation properties of mixture-of-experts... -
6
axflow
The TypeScript framework for AI development
...Its core SDK enables developers to integrate language model capabilities into web applications while maintaining strong modular design principles. Additional components support data ingestion, evaluation, and model interaction workflows that are commonly required when building production AI systems. For example, the framework includes modules for connecting application data to language models, evaluating the quality of model outputs, and building streaming user interfaces. Because each component can be used independently, developers can adopt Axflow incrementally rather than committing to a monolithic framework. This flexibility makes the system suitable for both experimentation and production environments. -
7
Alpaca-CoT
We unified the interfaces of instruction-tuning data
Alpaca-CoT is an open research project focused on improving reasoning capabilities in language models through chain-of-thought training data. The project builds upon the Alpaca instruction-tuning approach by introducing datasets and methods that encourage models to produce intermediate reasoning steps when solving problems. Instead of generating answers directly, the model learns to produce logical reasoning sequences that lead to the final solution. This chain-of-thought supervision helps... -
8
EvaDB
Database system for building simpler and faster AI-powered application
...This programming complexity prevents people who are experts in other domains from benefiting from these models. Running these deep learning models on large document or video datasets is costly and time-consuming. For example, the state-of-the-art object detection model takes multiple GPU years to process just a week’s videos from a single traffic monitoring camera. Besides the money spent on hardware, these models also increase the time that you spend waiting for the model inference to finish. -
9
Prem AI
Prem provides a unified environment to develop AI applications
...Abstracting away all technical complexities for AI deployment and ushering in a new era of privacy-centric AI applications - users can finally retain control and ownership of their models. The AI services expose an HTTP API interface, standardized for their interface type. For example, all models of type Chat expose the OpenAI API for easy of integration of existing tools and AI app ecosystem. Each service we support it's published on the Prem Registry. -
Atera - an All-in-one platform for IT managementYour IT essentials, integrated & elevated. Take your IT management from automated to autonomous, download Atera's agent to start your free trial!
-
10
ConsistencyDecoder
Consistency Distilled Diff VAE
ConsistencyDecoder is a Python package from OpenAI that introduces an improved decoding method for variational autoencoders (VAEs) used in Stable Diffusion pipelines. Instead of relying solely on the standard GAN or VAE decoder, this approach leverages a Consistency Distilled Diff VAE, designed to produce higher-quality and more stable outputs from encoded latents. The project provides a simple API for encoding with a Stable Diffusion VAE and decoding using the new consistency model,... -
11
Parallel WaveGAN
Unofficial Parallel WaveGAN
...It includes a large collection of “Kaldi-style” recipes for many datasets such as LJSpeech, LibriTTS, VCTK, JSUT, CMU Arctic, and multiple singing voice corpora in Japanese, Mandarin, Korean, and more. The project provides pre-trained models, Colab demos, and example configurations, allowing researchers to quickly evaluate vocoder quality or adapt models to new datasets. -
12
PyTorch Implementation of SDE Solvers
Differentiable SDE solvers with GPU support and efficient sensitivity
...The example trains an SDE as the generator of a GAN, whilst using a neural CDE [4] as the discriminator. -
13
ReplitLM
Inference code and configs for the ReplitLM model family
ReplitLM is a family of open-source language models developed by Replit for assisting with programming tasks such as code generation and completion. The project includes model checkpoints, configuration files, and example code that enable developers to run and experiment with the models locally or within machine learning frameworks. These models are designed specifically for coding workflows and are trained on large datasets of source code covering many programming languages and development environments. The repository also includes documentation and tutorials for integrating the models into development tools, APIs, or research pipelines. ... -
14
llama2-webui
Run any Llama 2 locally with gradio UI on GPU or CPU from anywhere
Running Llama 2 with gradio web UI on GPU or CPU from anywhere (Linux/Windows/Mac). -
15
RoomGPT
Upload a photo of your room to generate your dream room with AI
...The app is built on Next.js and exposes a simple web interface where users can upload images, choose styles, and view generated outputs. Under the hood, it calls a hosted ML model (for example on Replicate) via an API route and uses a service like Bytescale for image storage, keeping the front-end lightweight. The project is often described as an open-source clone or alternative to tools like InteriorAI, making AI-driven interior design experimentation accessible to developers. Because it is open source, developers can fork it, plug in different models, change the UI, or adapt the concept to other domains like garden layouts or product staging. -
16
LLM Applications
A comprehensive guide to building RAG-based LLM applications
LLM Applications is a practical reference repository that demonstrates how to build production-grade applications powered by large language models. The project focuses particularly on Retrieval-Augmented Generation architectures, which combine language models with external knowledge sources to improve accuracy and reliability. It provides step-by-step guidance for constructing systems that ingest documents, split them into chunks, generate embeddings, index them in vector databases, and... -
17
LLaMA
Inference code for Llama models
...It provides utilities to load pre-trained LLaMA model weights, run inference (text generation, chat, completions), and work with tokenizers. Tokenizer utilities, download scripts, shell helpers to fetch model weights with correct licensing/permissions. Includes example scripts for chat completions and text completions to show how to call the models in code. This repo is a core piece of the Llama model infrastructure, used by researchers and developers to run LLaMA models locally or in their infrastructure. It is meant for inference (not training from scratch) and connects with aspects like model cards, responsible use, licensing, etc. -
18
HyperCLIPS
CLIPS compatible application which allows a high performance execution
...You can use HyperCLIPS to run CLIPS programs with no modification. The original version of CLIPS Rule Based Programming Language is available from here. https://sourceforge.net/p/clipsrules/ The misclns4.tst is a good example for it because HyperCLIPS performs 200% - 400% faster than the original version of CLIPS. The CLIPS test suite(including misclns4.tst) are available from here. https://sourceforge.net/p/clipsrules/code/HEAD/tree/branches/63x/test_suite -
19
OpenNMT-tf
Neural machine translation and sequence learning using TensorFlow
...While neural machine translation is the main target task, it has been designed to more generally support sequence-to-sequence mapping, sequence tagging, sequence classification, language modeling. Models are described with code to allow training custom architectures and overriding default behavior. For example, the following instance defines a sequence-to-sequence model with 2 concatenated input features, a self-attentional encoder, and an attentional RNN decoder sharing its input and output embeddings. Sequence to sequence models can be trained with guided alignment and alignment information are returned as part of the translation API. -
20
GPT-Code UI
An open source implementation of OpenAI's ChatGPT Code interpreter
...You can put a .env in the working directory to load the OPENAI_API_KEY environment variable. For Azure OpenAI Services, there are also other configurable variables like deployment name. See .env.azure-example for more information. Note that model selection on the UI is currently not supported for Azure OpenAI Services. -
21
Language Models
Explore large language models in 512MB of RAM
...It is particularly useful for educational purposes, as it demonstrates the fundamental mechanics of language model inference and prompt-based applications. The repository includes multiple example applications such as chatbots, document question answering systems, and information retrieval tools. -
22
AI Explainability 360
Interpretability and explainability of data and machine learning model
...The AI Explainability 360 Python package includes a comprehensive set of algorithms that cover different dimensions of explanations along with proxy explainability metrics. The AI Explainability 360 interactive experience provides a gentle introduction to the concepts and capabilities by walking through an example use case for different consumer personas. The tutorials and example notebooks offer a deeper, data scientist-oriented introduction. The complete API is also available. There is no single approach to explainability that works best. There are many ways to explain: data vs. model, directly interpretable vs. post hoc explanation, local vs. global, etc. ... -
23
Lightning Flash
Flash enables you to easily configure and run complex AI recipes
...All data loading in Flash is performed via a from_* classmethod on a DataModule. Which DataModule to use and which from_* methods are available depends on the task you want to perform. For example, for image segmentation where your data is stored in folders, you would use the from_folders method of the SemanticSegmentationData class. Our tasks come loaded with pre-trained backbones and (where applicable) heads. You can view the available backbones to use with your task using available_backbones. With Flash, swapping among 40+ optimizers and 15 + schedulers recipes are simple. -
24
fastMRI
A large open dataset + tools to speed up MRI scans using ML
...The repository provides an open-source PyTorch framework with data loaders, subsampling utilities, reconstruction models, and evaluation metrics, supporting both research reproducibility and practical experimentation. It includes reference implementations for key MRI reconstruction architectures such as U-Net and Variational Networks (VarNet), along with example scripts for model training and evaluation using the PyTorch Lightning framework. The project also releases several fully anonymized public MRI datasets, including knee, brain, and prostate scans. -
25
TensorFlow Ranking
Learning to rank in TensorFlow
TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform. Commonly used loss functions including pointwise, pairwise, and listwise losses. Commonly used ranking metrics like Mean Reciprocal Rank (MRR) and Normalized Discounted Cumulative Gain (NDCG). Multi-item (also known as groupwise) scoring functions. LambdaLoss implementation for direct ranking metric optimization. Unbiased Learning-to-Rank from biased feedback data. We envision that this library...
