General Introduction Petals is an open source project developed by the BigScience Workshop to run Large Language Models (LLMs) through a distributed computing approach. Users can run and fine-tune LLMs at home using consumer-grade GPUs or Google Colab, such as Llama 3.1, Mixtral, F...
Comprehensive Introduction Aphrodite Engine is the official backend engine for PygmalionAI, designed to provide an inference endpoint for PygmalionAI sites and support rapid deployment of Hugging Face compatible models. The engine utilizes vLLM's Paged Attention technology for efficient K/V management and continuous batch processing,...
General Introduction Text generation web UI is a Gradio-based web UI designed for the Large Language Model (LLM). It supports a variety of text generation backends, including Transformers, llama.cpp and ExLlamaV2. Users can quickly get started with a simple installation...
General Introduction llama.cpp is a library implemented in pure C/C++ designed to simplify the inference process for Large Language Models (LLM). It supports a wide range of hardware platforms, including Apple Silicon, NVIDIA GPUs, and AMD GPUs, and provides a variety of quantization options to increase inference speed and reduce memory usage. The project ...
General Introduction Jan is an open source ChatGPT replacement that can 100% run offline on a user's device. It is driven by a Cortex engine and supports a wide range of hardware platforms, including NVIDIA GPUs and Apple M-series chips.Jan provides a rich library of models that users can download and run such as...
General Introduction AyeSoul is a unified AI search, answer and task engine designed to help users accomplish a variety of everyday tasks through a simple interface. Whether it's web search, deep research, brainstorming, creative writing, content creation or programming, AyeSoul provides intelligent support for...
General Introduction Komo is an AI-powered search engine designed to provide a fast, private and ad-free search experience. Users can use Komo to explore in depth, get instant answers, and discuss a variety of topics. Its main features include search, explore and chat to help users efficiently find what...
General Introduction Morphic is a search engine based on AI technology with a generative user interface designed to provide intelligent Q&A and efficient search experience. Users can perform a variety of searches including text, video, etc. with Morphic, and can save search history and share search results.Morphic supports a variety of AI...
General Introduction Hyperspace is an innovative generative browser (aiOS), based on the world's largest peer-to-peer AI network, designed to provide users with powerful tools for deep research and analysis. By integrating a wide range of AI models and data sources, Hyperspace allows users to rapidly generate information networks, utilizing high-quality sources...
Comprehensive Introduction GroundX is a full-stack solution designed for building real-data based LLM (Large Language Model) applications, specifically designed to build a full suite of RAG applications. It solves the phantom problem that traditional vector databases create when processing complex documents through dynamic chunking and context generation, helping...
English 
简体中文 
日本語 
Deutsch (Sie) 
Português do Brasil