Search Results for "state-thread" - Page 12
Sort By:
Showing 549 open source projects for "state-thread"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
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
Curated Transformers
PyTorch library of curated Transformer models and their components
State-of-the-art transformers, brick by brick. Curated Transformers is a transformer library for PyTorch. It provides state-of-the-art models that are composed of a set of reusable components. Supports state-of-the-art transformer models, including LLMs such as Falcon, Llama, and Dolly v2. Implementing a feature or bugfix benefits all models. -
2
ipytest
Pytest in IPython notebooks
ipytest allows you to run Pytest in Jupyter notebooks. ipytest aims to give access to the full pytest experience and to make it easy to transfer tests out of notebooks into separate test files. -
3
django-ai-assistant
Integrate AI Assistants with Django to build intelligent applications
Combine the power of LLMs with Django's productivity to build intelligent applications. Let AI Assistants call methods from Django's side and do anything your users need! Use AI Tool Calling and RAG with Django to easily build state of the art AI Assistants. Please check the documentation: https://vintasoftware.github.io/django-ai-assistant/ -
4
Zeta
Build high-performance AI models with modular building blocks
zeta is a deep learning library focused on providing cutting-edge AI and neural network models with a strong emphasis on research-grade architectures. It includes state-of-the-art implementations for rapid experimentation and model building. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
5
Luna AI
Virtual AI anchor that combines state-of-the-art technology
Luna AI is a virtual AI streamer framework designed to power an interactive VTuber that can go live on major platforms and chat with viewers in real time. It is built around a core assistant persona called “Luna AI,” which can be driven by a wide range of large language models and platforms, including GPT-style APIs, Claude, LangChain-based backends, ChatGLM, Kimi, Ollama, and many others. The project supports multiple rendering backends for the avatar, such as Live2D, Unreal Engine (UE),... -
6
Postgres-WASM
A PostgresQL server running in your browser
Postgres-WASM is an experimental project that brings the PostgreSQL database engine into the browser by running it inside a WebAssembly-powered virtualized environment. Instead of reimplementing PostgreSQL, the project embeds a full Linux environment and runs a native PostgreSQL instance within it, all compiled to WebAssembly and executed in the browser. This allows developers to interact with a real PostgreSQL server locally in a sandboxed environment without installing any database... -
7
Qwen-Audio
Chat & pretrained large audio language model proposed by Alibaba Cloud
Qwen-Audio is a large audio-language model developed by Alibaba Cloud, built to accept various types of audio input (speech, natural sounds, music, singing) along with text input, and output text. There is also an instruction-tuned version called Qwen-Audio-Chat which supports conversational interaction (multi-round), audio + text input, creative tasks and reasoning over audio. It uses multi-task training over many different audio tasks (30+), and achieves strong multi-benchmarks performance... -
8
Foolbox
Python toolbox to create adversarial examples
Foolbox: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX. Foolbox 3 is built on top of EagerPy and runs natively in PyTorch, TensorFlow, and JAX. Foolbox provides a large collection of state-of-the-art gradient-based and decision-based adversarial attacks. Catch bugs before running your code thanks to extensive type annotations in Foolbox. Foolbox is a Python library that lets you easily run adversarial attacks against machine learning models like deep neural networks. It is built on top of EagerPy and works natively with models in PyTorch, TensorFlow, and JAX. -
9
SirTunnel
Minimal, self-hosted, 0-config alternative to ngrok
...A small Python script tells Caddy which public hostname should proxy to the temporary server-side tunnel port. Caddy handles reverse proxying and automatic HTTPS certificate management. Tunnel mappings are ephemeral and controlled by clients, keeping server-side state and configuration to a minimum. It is designed as a lightweight, near-zero-configuration alternative for developers who already operate an SSH-accessible server. -
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
10
Django Notebook
Django + shell_plus + Jupyter notebooks made easy
...A Jupyter notebook with access to objects from the Django ORM is a powerful tool to introspect data and run ad-hoc queries. Built-in integration with the imported objects from django-extensions shell_plus. Saves the state between sessions so you don't need to remember what you did. Inheritance diagrams on any object, including ORM models. -
11
StyleTTS 2
Towards Human-Level Text-to-Speech through Style Diffusion
StyleTTS2 is a state-of-the-art text-to-speech system that aims for human-level naturalness by combining style diffusion, adversarial training, and large speech language models. It extends the original StyleTTS idea by introducing a style diffusion model that can sample rich, realistic speaking styles conditioned on reference speech, allowing highly expressive and diverse prosody. -
12
Amphion
Toolkit for audio, music, and speech generation
Amphion is a toolkit from OpenMMLab dedicated to audio, music, and speech generation, aimed at both reproducible research and helping newcomers get started in generative audio. It provides standardized implementations and recipes for classic and state-of-the-art generative models in audio, including TTS, music generation, and voice conversion. A distinctive feature of Amphion is its emphasis on visualization: it offers interactive visualizations of model architectures and generation processes, making it easier to understand how complex generative audio models work. The toolkit is organized with example experiments (“egs”) and visualization demos that guide users through training, evaluation, and inspection of models. ... -
13
GPT Discord Bot
Example Discord bot written in Python that uses the completions API
...It is built on top of the discord.py framework and the OpenAI Python library, providing a simple, extensible template for building AI-powered Discord applications. The bot supports a /chat command that spawns a public thread, carries full conversation context across messages, and gracefully closes the thread when context or message limits are reached. Developers can customize system instructions through a config file and modify the model used for responses. While minimal, this project offers a clear example of how to set up authentication, permissions, and message handling for deploying a functional GPT-powered chatbot in Discord. -
14
Recurrent Interface Network (RIN)
Implementation of Recurrent Interface Network (RIN)
...Additionally, we will try adding an extra linear attention on the main branch as well as self-conditioning in the pixel space. The insight of being able to self-condition on any hidden state of the network as well as the newly proposed sigmoid noise schedule are the two main findings. -
15
FastChat
Open platform for training, serving, and evaluating language models
FastChat is an open platform for training, serving, and evaluating large language model-based chatbots. If you do not have enough memory, you can enable 8-bit compression by adding --load-8bit to the commands above. This can reduce memory usage by around half with slightly degraded model quality. It is compatible with the CPU, GPU, and Metal backend. Vicuna-13B with 8-bit compression can run on a single NVIDIA 3090/4080/T4/V100(16GB) GPU. In addition to that, you can add --cpu-offloading to... -
16
CAMPARI
Software for molecular simulations and trajectory analysis
We are proud to introduce version 5 of CAMPARI. We have added a number of new features, most notably a Python interface for interpreting user-supplied code (with the help of ForPy), a novel trajectory storage standard (with the help of libpqxx/PostgreSQL), and a module for performing transition path theory. Naturally, CAMPARI continues to provide the reference implementation of the ABSINTH force field paradigm and implicit solvation model. CAMPARI is a joint package for performing and... -
17
Arctic TimeSeries and Tick store
High performance datastore for time series and tick data
...Pandas DataFrames, Numpy arrays, Python objects via pickling etc. so you don't have to handle different datatypes manually. Uses LZ4 compression by default on the client side to get big savings on network / disk. Allows you to version different stages of an object and snapshot the state (In some ways similar to git), and allows you to freely experiment and then just revert back the snapshot. [VersionStore only] Does the chunking (breaking a Dataframe to smaller part for you. Has different types of Stores, each with it's own benefits. Eg. Versionstore allows you to version and snapshot stuff, TickStore is for storage and highly efficient retrieval of streaming data, ChunkStore allows you to chunk and efficiently retrieve ranges of chunks. -
18
BackgroundMattingV2
Real-Time High-Resolution Background Matting
Official repository for the paper Real-Time High-Resolution Background Matting. Our model requires capturing an additional background image and produces state-of-the-art matting results at 4K 30fps and HD 60fps on an Nvidia RTX 2080 TI GPU. -
19
MMEditing
MMEditing is a low-level vision toolbox based on PyTorch
...We decompose the editing framework into different components and one can easily construct a customized editor framework by combining different modules. The toolbox directly supports popular and contemporary inpainting, matting, super-resolution and generation tasks. The toolbox provides state-of-the-art methods in inpainting/matting/super-resolution/generation. Note that MMSR has been merged into this repo, as a part of MMEditing. With elaborate designs of the new framework and careful implementations, hope MMEditing could provide a better experience. When installing PyTorch in Step 2, you need to specify the version of CUDA. ... -
20
Transformers4Rec
Transformers4Rec is a flexible and efficient library
...The library works as a bridge between natural language processing (NLP) and recommender systems (RecSys) by integrating with one of the most popular NLP frameworks, Hugging Face Transformers (HF). Transformers4Rec makes state-of-the-art transformer architectures available for RecSys researchers and industry practitioners. Traditional recommendation algorithms usually ignore the temporal dynamics and the sequence of interactions when trying to model user behavior. Generally, the next user interaction is related to the sequence of the user's previous choices. ... -
21
SSD in PyTorch 1.0
High quality, fast, modular reference implementation of SSD in PyTorch
...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. -
22
State of Open Source AI
Clarity in the current fast-paced mess of Open Source innovation
This repository is the source for a book (or large written work) titled “The State of Open Source AI”. The goal of the project is to bring clarity to the rapidly evolving open-source AI ecosystem by documenting trends, models, tools, standards, deployment practices, and challenges. It acts as both a snapshot and a guide: readers can see what’s “hot now” in open AI infrastructure, what open licensing or governance issues are emerging, how deployment options compare, and what gaps remain. ... -
23
Filt8- v3.6 alerts for WSJT-X FT8
Alert and filter QSO for WSJT-X FT8 FT4
...CHECK OUT ft8mapper FOR BETTER GRAPHICS AND GRID TRACKING. Filt8 - v3.6 release - Requires Python 3.x (3.10 or higher on Mac) Scrollable maps for small screens State data as of Feb 25, 2024. Map saves settings. Map features: filter by band, click to Lookup. Offline Maps to show station grid locations as you decode them in real-time (Check out js8mapper project on https://sourceforge.net/projects/js8map/ for this same option for JS8Call) Map feature allows filtering by band, listings by callsigns or grids, and callsign lookups via QRZ or HamCall (this requires Internet). ... -
24
OpenAssistant
Chat-based assistant that understands tasks
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so. In the same way that Stable Diffusion helped the world make art and images in new ways, we want to improve the world by providing amazing conversational AI. We are in the early stages of development, working from established research in applying RLHF to large language models. Open Assistant is a project organized by LAION and individuals around... -
25
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.
