Repository History
138 repositories tagged with LLM
llama-cpp-python: Python Bindings for llama.cpp
llama-cpp-python provides robust Python bindings for the popular llama.cpp library, enabling efficient local inference with large language models. It offers a high-level API compatible with OpenAI's API, facilitating easy integration into existing applications. The project also includes a powerful web server for local deployment and supports various hardware acceleration backends.
FuncVul: Function-Level Vulnerability Detection with LLMs and Code Chunks
FuncVul is an innovative model designed to detect vulnerabilities at the function level in C/C++ and Python code, addressing a critical gap in software supply chain security. By leveraging large language models (LLMs) and a code chunk-based approach, FuncVul significantly improves the precision of vulnerability identification. The model demonstrates superior performance compared to existing state-of-the-art methods, achieving high accuracy and F1 scores across various datasets.
Marker: High-Accuracy Document Conversion to Markdown and JSON
Marker is an open-source Python tool designed for high-accuracy conversion of documents like PDFs, images, and office files into Markdown, JSON, and HTML. It excels at preserving complex formatting, extracting images, and can leverage LLMs for even greater precision. This makes Marker a powerful solution for structured document intelligence.
Text Generation Inference: High-Performance LLM Serving by Hugging Face
Text Generation Inference (TGI) is a robust toolkit from Hugging Face designed for deploying and serving Large Language Models (LLMs) with high performance. It powers Hugging Face's production services, including Hugging Chat and their Inference API. TGI offers optimized text generation, supporting popular open-source LLMs and implementing advanced features for efficient and scalable inference.
Weave by Weights & Biases: A Toolkit for AI-Powered Applications
Weave is an open-source toolkit developed by Weights & Biases designed for building and managing AI-powered applications. It provides robust features for logging, debugging, and evaluating language model inputs and outputs, streamlining the development workflow for generative AI. Weave aims to bring rigor and best practices to the experimental process of AI software development.
Data Prep Kit: Accelerating Data Preparation for GenAI and LLM Applications
Data Prep Kit is an open-source project designed to accelerate unstructured data preparation for GenAI and LLM applications. It provides a comprehensive set of modules and transforms to cleanse, transform, and enrich data for pre-training, fine-tuning, instruct-tuning LLMs, or building Retrieval Augmented Generation (RAG) applications. The kit is highly scalable, supporting processing from a laptop to data center scale using Python, Ray, and Spark runtimes.
Magic: The All-in-One Open-Source AI Productivity Platform
Magic is the first open-source all-in-one AI productivity platform, integrating a generalist AI agent, workflow engine, instant messaging, and collaborative office system. It aims to help enterprises build and deploy AI applications to achieve significant productivity increases, offering a comprehensive suite of tools for intelligent automation and collaboration.
Ditto: The Simplest Self-Building Coding Agent for Flask Apps
Ditto is a user-friendly Python tool that generates multi-file Flask applications from simple natural language descriptions. It leverages a straightforward LLM loop to automate the coding process, enabling users to transform ideas into functional web applications through a no-code interface. This agent simplifies development by automatically planning and constructing applications based on plain English input.
OLMoE.swift: Private, Offline AI Experience on iOS and macOS
OLMoE.swift provides a unique, privacy-focused AI experience by running large language models directly on your device. This Swift-based application ensures your queries and data remain private, operating entirely offline without an internet connection. It offers a robust solution for local AI inference on iOS and macOS, with integration options for Hugging Face.
Harmony: OpenAI's Renderer for GPT-OSS Response Format
Harmony is OpenAI's dedicated renderer for its `harmony` response format, specifically designed for use with `gpt-oss` open-weight models. This library provides a robust solution for defining conversation structures, generating reasoning output, and structuring function calls, ensuring consistent and efficient token-sequence handling for both rendering and parsing. It offers first-class support for both Python and Rust development.
claude-code-proxy: Use Anthropic Clients with OpenAI and Gemini Models
`claude-code-proxy` is a powerful proxy server that allows developers to use Anthropic clients, such as Claude Code, with various backend models including OpenAI, Gemini, or even Anthropic's own models. It provides seamless translation of API requests and responses, offering flexibility and control over your AI model choices. This tool is ideal for integrating different LLM providers without modifying existing Anthropic client code.
Rig: Build Modular and Scalable LLM Applications in Rust
Rig is a powerful Rust library designed for building modular, scalable, and ergonomic LLM-powered applications. It offers extensive features, including agentic workflows, compatibility with over 20 model providers, and seamless integration with more than 10 vector stores. Developers can leverage Rig to create robust generative AI solutions with minimal boilerplate.