Projects sharing features with Llama Dl

Pan-light is a tool for managing and downloading files from Baidu network storage. It provides high-speed file downloading and remote media streaming capabilities. The application uses concurrent segmented transfers to maximize network throughput and employs disk-persisted state tracking to resume interrupted downloads. It also includes a local proxy to bypass hotlinking protections, allowing remote videos to be streamed directly into a media player. The project features a cross-platform graphical user interface built with Go and Qt. Additionally, it supports remote software previews by runn

aria2 is a multi-protocol download manager and BitTorrent client. It functions as a command-line utility and a background daemon capable of retrieving files via HTTP, HTTPS, FTP, SFTP, BitTorrent, and Metalink. The project distinguishes itself by supporting multi-source downloading, which allows a single file to be retrieved from several different sources and protocols simultaneously. It operates as a download server by exposing JSON-RPC and XML-RPC interfaces over HTTP and WebSocket, enabling remote task management from external programs. The system optimizes throughput by splitting files i

FlagAI is a distributed deep learning framework and platform designed for the end-to-end lifecycle of large-scale foundation models. It provides a toolkit for training, fine-tuning, and deploying large language models and multi-modal systems across multi-node computing clusters. The project features hardware-agnostic compute abstractions to ensure consistent execution across different accelerators. It includes a dedicated library for parameter-efficient fine-tuning, allowing large neural networks to be adapted to specific tasks with minimal parameter updates and reduced computational overhead

Scoop is a command-line package manager and installer for Windows. It serves as a developer environment orchestrator designed to automate the installation, updating, and removal of software packages through a centralized repository of manifests. The project functions as a portable application distributor, deploying software using compressed archives rather than traditional Windows installers. This approach avoids graphical installation wizards and registry pollution by utilizing an isolated directory structure and shim-based execution to manage application binaries. The system includes capab

This project provides a foundational framework and reference implementation for executing causal language modeling and multimodal reasoning on local systems. It includes a set of core components for managing model assets, a fine-tuning framework, and structural definitions required to instantiate transformer-based architectures. The system is distinguished by its ability to process combined text and image inputs through multimodal transformer models for visual reasoning and document analysis. It also supports the deployment of quantized models, reducing memory footprints through low-precision

This project is a build artifact manager and file persistence tool designed to save files and directories from a workflow run as archived assets. It functions as a workflow asset archiver that compresses and uploads project files to a remote store. The system differentiates itself through a comprehensive metadata tracking system that generates unique identifiers, download URLs, and security digests for every uploaded asset. It manages the asset lifecycle using configurable retention policies to determine how long files remain available before automatic deletion and supports updating existing

Aria2 is a multi-protocol command-line download manager designed to maximize bandwidth utilization by retrieving files from multiple sources and protocols simultaneously. It functions as an asynchronous, event-driven engine that handles complex download lifecycles, including peer-to-peer transfers via BitTorrent, while ensuring data integrity through continuous chunk-based verification. The utility distinguishes itself through its ability to act as a background process that can be controlled programmatically via a remote procedure call interface. This allows external applications to manage, m

Gopeed is a cross-platform download manager that provides a unified interface for retrieving files across diverse protocols, including HTTP, BitTorrent, Magnet, and ED2K. It utilizes a multi-segment concurrent downloading engine to maximize network bandwidth utilization and accelerate transfer speeds. The application is designed for both desktop and mobile environments, offering a terminal-based command-line interface alongside a graphical user experience. The project distinguishes itself through a scriptable extension framework that allows users to execute custom JavaScript to automate compl

Ollama is a cross-platform runtime for managing, serving, and executing large language models on local hardware. It functions as a model manager and orchestrator that allows for the downloading, updating, and organization of model weights and configurations to ensure private and offline inference. The system provides a local inference API and a RESTful interface for programmatic model lifecycle management and text generation. It utilizes a compiled C++ backend to handle tensor operations and memory management. To support various hardware configurations, the runtime employs dynamic GPU offloa

Open Model Zoo is a curated collection of pre-trained and optimized deep learning models designed for high-performance inference using OpenVINO. It serves as a model repository and deployment framework that streamlines the integration of neural networks into production environments. The project utilizes a centralized manifest and a versioned registry to automate the downloading and organization of model weights and metadata. It includes tools for benchmarking inference performance and validating model accuracy by comparing outputs against ground-truth tensors to quantify precision loss. The

Fairseq is a PyTorch toolkit for sequence-to-sequence modeling, specializing in neural machine translation, automatic speech recognition, and large-scale language model training. It provides a framework for processing and aligning diverse data sources, including text, audio, and video, to support tasks such as speech-to-text conversion and multimodal sequence learning. The project is distinguished by its distributed training capabilities, which utilize parameter sharding, mixed-precision training, and CPU offloading to handle models that exceed single-device memory. It also includes specializ

Persepolis is a Python-based download manager and graphical user interface for the aria2 engine. It functions as a concurrent file downloader that splits files into multiple chunks to be retrieved simultaneously, maximizing available network bandwidth. The application integrates a media extraction engine to resolve direct URLs, enabling the retrieval of video and audio content from various online streaming platforms and hosting services. It provides tools for download queue management and automation, including the ability to schedule specific start times or define time windows for downloads

Cog is a machine learning packaging tool and containerized model wrapper that bundles models and their dependencies into standardized Docker containers. It functions as an environment manager and inference server, ensuring consistent model execution across different hardware systems by resolving GPU drivers, system libraries, and Python dependencies. The project distinguishes itself by automatically generating RESTful HTTP servers and OpenAPI schemas based on defined model input and output types. It manages large model weights as external fixtures to optimize image size and utilizes a slot-ba

DiffusionBee is a Stable Diffusion desktop client for macOS that functions as an AI image generator and editor. It allows for the local generation of images from text prompts and the management of diffusion models without requiring external cloud services or technical setup. The application includes a local diffusion model manager for importing and switching between custom trained model files to achieve specific artistic styles. It also features a system for tracking generation history and uploading assets to a public gallery. The software covers several image synthesis and manipulation work

Annie is a command-line video downloader and web video extraction library written in Go. It functions as a concurrent media downloader designed to fetch video files and playlists from websites via URLs. The tool distinguishes itself through a proxy-aware network layer that supports SOCKS5 and HTTP proxies to bypass regional content restrictions. It also incorporates session cookie integration and referrer spoofing to facilitate the download of authenticated or age-gated content. The project provides capabilities for bulk media acquisition, including batch downloading from text files and extr

picoGPT is a lightweight, low-level runtime environment and inference engine designed to load pre-trained checkpoints and execute generative transformer model inference. It provides a minimal implementation of the generative pre-trained transformer architecture to facilitate local language model execution. The project includes a C++ machine learning library for converting model parameters and executing greedy token generation without heavy external dependencies. It handles remote asset synchronization by downloading pre-trained weights, hyperparameters, and vocabulary files from remote server

Villain is a command and control framework and distributed orchestrator designed for managing reverse TCP and HoaxShell connections. It serves as a reverse shell manager and payload generation tool, allowing for the coordination of remote access across multiple target systems. The project distinguishes itself through a distributed architecture that synchronizes active remote sessions and broadcasts messages across connected server instances for collaborative operations. It includes a fileless execution engine that runs scripts directly in remote memory over HTTP to avoid writing files to the

lmdeploy is a high-performance inference engine and deployment framework for large language models and vision models. It functions as a multi-modal model server and compression toolkit designed to serve models with high throughput and low latency. The system enables the distribution of model services across multiple machines using request-based load balancing and tensor parallelism. It includes specialized tools for model quantization and compression to reduce the memory footprint of weights and caches. The framework covers broad capability areas including production deployment, distributed

BaiduYunVIP is a speed bypass guide and optimization toolkit designed to remove download bandwidth throttling on Baidu Netdisk cloud storage. It functions as a resource for achieving maximum download speeds from cloud platforms through a combination of shared credentials and configuration steps. The project provides a curated collection of shared login details and subscription access for premium cloud storage and streaming service memberships. It further assists users by directing them toward third-party software and external tools specifically designed to override native download speed limit

vLLM is a high-throughput inference engine designed for the efficient serving and execution of large language models. It functions as a production-ready distributed model server, providing standard API protocols for online serving while also supporting offline batch processing. The system is built to maximize token generation speed and memory efficiency, enabling both large-scale cloud deployments and local execution on personal hardware. The project distinguishes itself through advanced memory management and request scheduling techniques, most notably its use of non-contiguous key-value cach

Accelerate is a PyTorch distributed training library that abstracts the boilerplate required to run models across multiple GPUs, TPUs, and CPUs. It functions as a deep learning model scaler and distributed hardware orchestrator, allowing the same training script to run on different hardware backends without modifying the core logic. The project provides a distributed training command line interface for configuring compute environments and launching jobs across single or multi-node clusters. It includes a mixed precision training framework to implement FP16 and BF16 precision, reducing memory

The simplest way to run LLaMA on your local machine

Rag-stack is an enterprise knowledge retrieval system designed to deploy private generative artificial intelligence environments. It functions as a retrieval-augmented generation stack, orchestrating the connection between internal document repositories and open-source language models to enable natural language querying of private organizational data. The platform distinguishes itself by providing a complete infrastructure for private large language model hosting and vector database management. By utilizing infrastructure-as-code provisioning and containerized microservices, it allows organiz

Langchain-Chatchat is a system for building retrieval-augmented generation applications and autonomous AI agents. It integrates a knowledge base management system and an agent framework to enable language models to interact with private documents and execute multi-step tasks through external tools. The platform supports local deployment of language models on private infrastructure to operate without an internet connection. It includes a multimodal AI platform that combines vision models for image analysis with text-to-image generation capabilities. The system provides a web-based conversatio

ytDownloader is a video downloader and media extraction tool that uses the yt-dlp engine to retrieve video and audio files from various social media and video sharing platforms. It functions as a utility for capturing full media files, specific segments or ranges of tracks, and entire video playlists. The project includes a hardware-accelerated video compressor to reduce file sizes while maintaining visual quality. It also features a subtitle downloader capable of retrieving both text captions and embedded subtitle tracks for accessibility and translation. The system handles broad media task

BaiduNetdiskPlugin-macOS is a suite of macOS system extensions and tools designed to remove download speed limits and unlock premium features for the Baidu Netdisk client. It functions as a download speed unblocker and premium feature unlocker to enable maximum data transfer rates and activate SVIP status. The project includes a software update blocker that prevents the client from performing automatic updates to preserve the applied modifications. It achieves these results by removing local data transfer rate restrictions and eliminating trial duration limits.

Fauxpilot is a self-hosted AI coding assistant and local inference server. It functions as a proxy and API gateway that redirects traffic from IDE plugins to a local large language model, allowing for AI-assisted programming without external cloud dependencies. The project provides a specialized API emulation layer that mimics coding assistant protocols and a standardized OpenAI-compatible interface. This enables supported code editors to use local models for completions and suggestions by overriding default proxy URLs. The system includes capabilities for downloading and deploying local mod