AIMET is a library that provides advanced model quantization and compression techniques for trained neural network models. It provides features that have been proven to improve run-time performance of deep learning neural network models with lower compute and memory requirements and minimal impact to task accuracy. AIMET is designed to work with PyTorch, TensorFlow and ONNX models. We also host the AIMET Model Zoo - a collection of popular neural network models optimized for 8-bit inference. We also provide recipes for users to quantize floating point models using AIMET.

PURE (Process-sUpervised Reinforcement lEarning) is a framework that trains a Process Reward Model (PRM) on a dataset and fine-tunes a language model to achieve state-of-the-art mathematical reasoning capabilities. It uses a novel credit assignment method to calculate return and supports multiple reward types. The final model outperforms existing methods with minimal RL data or compute resources, achieving high accuracy on various benchmarks. The tool addresses reward hacking issues and aims to enhance long-range decision-making and reasoning tasks using large language models.

MMLU-Pro is an enhanced benchmark designed to evaluate language understanding models across broader and more challenging tasks. It integrates more challenging, reasoning-focused questions and increases answer choices per question, significantly raising difficulty. The dataset comprises over 12,000 questions from academic exams and textbooks across 14 diverse domains. Experimental results show a significant drop in accuracy compared to the original MMLU, with greater stability under varying prompts. Models utilizing Chain of Thought reasoning achieved better performance on MMLU-Pro.

The Arthur Engine is a comprehensive tool for monitoring and governing AI/ML workloads. It provides evaluation and benchmarking of machine learning models, guardrails enforcement, and extensibility for fitting into various application architectures. With support for a wide range of evaluation metrics and customizable features, the tool aims to improve model understanding, optimize generative AI outputs, and prevent data-security and compliance risks. Key features include real-time guardrails, model performance monitoring, feature importance visualization, error breakdowns, and support for custom metrics and models integration.

Awesome-LLM-Quantization is a curated list of resources related to quantization techniques for Large Language Models (LLMs). Quantization is a crucial step in deploying LLMs on resource-constrained devices, such as mobile phones or edge devices, by reducing the model's size and computational requirements.

CIFAR-10 Airbench is a project offering fast and stable training baselines for CIFAR-10 dataset, facilitating machine learning research. It provides easily runnable PyTorch scripts for training neural networks with high accuracy levels. The methods used in this project aim to accelerate research on fundamental properties of deep learning. The project includes GPU-accelerated dataloader for custom experiments and trainings, and can be used for data selection and active learning experiments. The training methods provided are faster than standard ResNet training, offering improved performance for research projects.

MCP for Security is a repository that contains Model Context Protocol (MCP) server implementations for various security testing tools, making them accessible through a standardized interface. It aims to provide automated threat detection and reduce human latency in cybersecurity by combining artificial intelligence and security tools. Users can access a variety of tools for subdomain enumeration, reconnaissance, vulnerability scanning, web crawling, HTTP security analysis, mobile application security testing, network scanning, SSL/TLS configuration analysis, DNS brute-forcing, HTTP request smuggling detection, SQL injection testing, historical URL retrieval, and WordPress vulnerability scanning. The repository encourages collaboration and rapid evolution through open-source projects.

This repository contains a C++ application that demonstrates face recognition capabilities using computer vision techniques. The demo utilizes OpenCV and dlib libraries for efficient face detection and recognition with 3D passive face liveness detection (face anti-spoofing). Key Features: Face detection: The SDK utilizes advanced computer vision techniques to detect faces in images or video frames, enabling a wide range of applications. Face recognition: It can recognize known faces by comparing them with a pre-defined database of individuals. Age estimation: It can estimate the age of detected faces. Gender detection: It can determine the gender of detected faces. Liveness detection: It can detect whether a face is from a live person or a static image.

CuMo is a project focused on scaling multimodal Large Language Models (LLMs) with Co-Upcycled Mixture-of-Experts. It introduces CuMo, which incorporates Co-upcycled Top-K sparsely-gated Mixture-of-experts blocks into the vision encoder and the MLP connector, enhancing the capabilities of multimodal LLMs. The project adopts a three-stage training approach with auxiliary losses to stabilize the training process and maintain a balanced loading of experts. CuMo achieves comparable performance to other state-of-the-art multimodal LLMs on various Visual Question Answering (VQA) and visual-instruction-following benchmarks.

Defog's SQLCoder is a family of state-of-the-art large language models (LLMs) designed for converting natural language questions into SQL queries. It outperforms popular open-source models like gpt-4 and gpt-4-turbo on SQL generation tasks. SQLCoder has been trained on more than 20,000 human-curated questions based on 10 different schemas, and the model weights are licensed under CC BY-SA 4.0. Users can interact with SQLCoder through the 'transformers' library and run queries using the 'sqlcoder launch' command in the terminal. The tool has been tested on NVIDIA GPUs with more than 16GB VRAM and Apple Silicon devices with some limitations. SQLCoder offers a demo on their website and supports quantized versions of the model for consumer GPUs with sufficient memory.

Twelvet is a permission management system based on Spring Cloud Alibaba that serves as a framework for rapid development. It is a scaffolding framework based on microservices architecture, aiming to reduce duplication of business code and provide a common core business code for both microservices and monoliths. It is designed for learning microservices concepts and development, suitable for website management, CMS, CRM, OA, and other system development. The system is intended to quickly meet business needs, improve user experience, and save time by incubating practical functional points in lightweight, highly portable functional plugins.

Fishial.ai is a project focused on training and validating scripts for fish segmentation and classification models. It includes various scripts for automatic training with different loss functions, dataset manipulation, and model setup using Detectron2 API. The project also provides tools for converting classification models to TorchScript format and creating training datasets. The models available include MaskRCNN for fish segmentation and various versions of ResNet18 for fish classification with different class counts and features. The project aims to facilitate fish identification and analysis through machine learning techniques.

Pearl is a production-ready Reinforcement Learning AI agent library open-sourced by the Applied Reinforcement Learning team at Meta. It enables researchers and practitioners to develop Reinforcement Learning AI agents that prioritize cumulative long-term feedback over immediate feedback and can adapt to environments with limited observability, sparse feedback, and high stochasticity. Pearl offers a diverse set of unique features for production environments, including dynamic action spaces, offline learning, intelligent neural exploration, safe decision making, history summarization, and data augmentation.

MiniAiLive provides system integrators with fast, flexible and extremely precise facial recognition with 3D passive face liveness detection (face anti-spoofing) that can be deployed across a number of scenarios, including security, access control, public safety, fintech, smart retail and home protection.

Vim-airline is a lean and mean status/tabline plugin for Vim that provides a nice statusline at the bottom of each Vim window. It consists of several sections displaying information such as mode, environment status, filename, filetype, file encoding, and current position in the file. The plugin is highly customizable and integrates with various plugins, providing a tiny core with extensibility in mind. It is optimized for speed, supports multiple themes, and integrates seamlessly with other plugins. Vim-airline is written in 100% Vimscript, eliminating the need for Python. The plugin aims to be stable and includes a unit testing suite for reliability.

SeerAttention is a novel trainable sparse attention mechanism that learns intrinsic sparsity patterns directly from LLMs through self-distillation at post-training time. It achieves faster inference while maintaining accuracy for long-context prefilling. The tool offers features such as trainable sparse attention, block-level sparsity, self-distillation, efficient kernel, and easy integration with existing transformer architectures. Users can quickly start using SeerAttention for inference with AttnGate Adapter and training attention gates with self-distillation. The tool provides efficient evaluation methods and encourages contributions from the community.

AIMET is a library that provides advanced model quantization and compression techniques for trained neural network models. It provides features that have been proven to improve run-time performance of deep learning neural network models with lower compute and memory requirements and minimal impact to task accuracy. AIMET is designed to work with PyTorch, TensorFlow and ONNX models. We also host the AIMET Model Zoo - a collection of popular neural network models optimized for 8-bit inference. We also provide recipes for users to quantize floating point models using AIMET.

HQQ is a fast and accurate model quantizer that skips the need for calibration data. It's super simple to implement (just a few lines of code for the optimizer). It can crunch through quantizing the Llama2-70B model in only 4 minutes! 🚀

llm-resource is a comprehensive collection of high-quality resources for Large Language Models (LLM). It covers various aspects of LLM including algorithms, training, fine-tuning, alignment, inference, data engineering, compression, evaluation, prompt engineering, AI frameworks, AI basics, AI infrastructure, AI compilers, LLM application development, LLM operations, AI systems, and practical implementations. The repository aims to gather and share valuable resources related to LLM for the community to benefit from.

llmc is an off-the-shell tool designed for compressing LLM, leveraging state-of-the-art compression algorithms to enhance efficiency and reduce model size without compromising performance. It provides users with the ability to quantize LLMs, choose from various compression algorithms, export transformed models for further optimization, and directly infer compressed models with a shallow memory footprint. The tool supports a range of model types and quantization algorithms, with ongoing development to include pruning techniques. Users can design their configurations for quantization and evaluation, with documentation and examples planned for future updates. llmc is a valuable resource for researchers working on post-training quantization of large language models.

Awesome-Efficient-LLM is a curated list focusing on efficient large language models. It includes topics such as knowledge distillation, network pruning, quantization, inference acceleration, efficient MOE, efficient architecture of LLM, KV cache compression, text compression, low-rank decomposition, hardware/system, tuning, and survey. The repository provides a collection of papers and projects related to improving the efficiency of large language models through various techniques like sparsity, quantization, and compression.

The NVIDIA TensorRT Model Optimizer is a library designed to quantize and compress deep learning models for optimized inference on GPUs. It offers state-of-the-art model optimization techniques including quantization and sparsity to reduce inference costs for generative AI models. Users can easily stack different optimization techniques to produce quantized checkpoints from torch or ONNX models. The quantized checkpoints are ready for deployment in inference frameworks like TensorRT-LLM or TensorRT, with planned integrations for NVIDIA NeMo and Megatron-LM. The tool also supports 8-bit quantization with Stable Diffusion for enterprise users on NVIDIA NIM. Model Optimizer is available for free on NVIDIA PyPI, and this repository serves as a platform for sharing examples, GPU-optimized recipes, and collecting community feedback.

Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of papers on LLMs inference and serving.

llm-compressor is an easy-to-use library for optimizing models for deployment with vllm. It provides a comprehensive set of quantization algorithms, seamless integration with Hugging Face models and repositories, and supports mixed precision, activation quantization, and sparsity. Supported algorithms include PTQ, GPTQ, SmoothQuant, and SparseGPT. Installation can be done via git clone and local pip install. Compression can be easily applied by selecting an algorithm and calling the oneshot API. The library also offers end-to-end examples for model compression. Contributions to the code, examples, integrations, and documentation are appreciated.

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

AgentCloud is an open-source platform that enables companies to build and deploy private LLM chat apps, empowering teams to securely interact with their data. It comprises three main components: Agent Backend, Webapp, and Vector Proxy. To run this project locally, clone the repository, install Docker, and start the services. The project is licensed under the GNU Affero General Public License, version 3 only. Contributions and feedback are welcome from the community.

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

The Azure-Analytics-and-AI-Engagement repository provides packaged Industry Scenario DREAM Demos with ARM templates (Containing a demo web application, Power BI reports, Synapse resources, AML Notebooks etc.) that can be deployed in a customer’s subscription using the CAPE tool within a matter of few hours. Partners can also deploy DREAM Demos in their own subscriptions using DPoC.

ExecuTorch is an end-to-end solution for enabling on-device inference capabilities across mobile and edge devices including wearables, embedded devices and microcontrollers. It is part of the PyTorch Edge ecosystem and enables efficient deployment of PyTorch models to edge devices. Key value propositions of ExecuTorch are: * **Portability:** Compatibility with a wide variety of computing platforms, from high-end mobile phones to highly constrained embedded systems and microcontrollers. * **Productivity:** Enabling developers to use the same toolchains and SDK from PyTorch model authoring and conversion, to debugging and deployment to a wide variety of platforms. * **Performance:** Providing end users with a seamless and high-performance experience due to a lightweight runtime and utilizing full hardware capabilities such as CPUs, NPUs, and DSPs.

AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. AutoGen agents are customizable, conversable, and seamlessly allow human participation. They can operate in various modes that employ combinations of LLMs, human inputs, and tools.

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.