Read write lock for asyncio. A RWLock maintains a pair of associated locks, one for read-only operations and one for writing. The read lock may be held simultaneously by multiple reader tasks, so long as there are no writers. The write lock is exclusive. Whether or not a read-write lock will improve performance over the use of a mutual exclusion lock depends on the frequency that the data is read compared to being modified. For example, a collection that is initially populated with data and thereafter infrequently modified, while being frequently searched is an ideal candidate for the use of a read-write lock. However, if updates become frequent then the data spends most of its time being exclusively locked and there is little, if any increase in concurrency. Note: a task that acquires the lock should be used for releasing it. Locking from one task and releasing from another one generates RuntimeError. Implementation is almost direct port from a patch.

GPT-Subtrans is an open-source subtitle translator that utilizes large language models (LLMs) as translation services. It supports translation between any language pairs that the language model supports. Note that GPT-Subtrans requires an active internet connection, as subtitles are sent to the provider's servers for translation, and their privacy policy applies.

Lovelaice is an AI-powered assistant for your terminal and editor. It can run bash commands, search the Internet, answer general and technical questions, complete text files, chat casually, execute code in various languages, and more. Lovelaice is configurable with API keys and LLM models, and can be used for a wide range of tasks requiring bash commands or coding assistance. It is designed to be versatile, interactive, and helpful for daily tasks and projects.

EZKL is a library and command-line tool for doing inference for deep learning models and other computational graphs in a zk-snark (ZKML). It enables the following workflow: 1. Define a computational graph, for instance a neural network (but really any arbitrary set of operations), as you would normally in pytorch or tensorflow. 2. Export the final graph of operations as an .onnx file and some sample inputs to a .json file. 3. Point ezkl to the .onnx and .json files to generate a ZK-SNARK circuit with which you can prove statements such as: > "I ran this publicly available neural network on some private data and it produced this output" > "I ran my private neural network on some public data and it produced this output" > "I correctly ran this publicly available neural network on some public data and it produced this output" In the backend we use the collaboratively-developed Halo2 as a proof system. The generated proofs can then be verified with much less computational resources, including on-chain (with the Ethereum Virtual Machine), in a browser, or on a device.

LLM training in simple, pure C/CUDA. There is no need for 245MB of PyTorch or 107MB of cPython. For example, training GPT-2 (CPU, fp32) is ~1,000 lines of clean code in a single file. It compiles and runs instantly, and exactly matches the PyTorch reference implementation. I chose GPT-2 as the first working example because it is the grand-daddy of LLMs, the first time the modern stack was put together.

abliterator.py is a simple Python library/structure designed to ablate features in large language models (LLMs) supported by TransformerLens. It provides capabilities to enter temporary contexts, cache activations with N samples, calculate refusal directions, and includes tokenizer utilities. The library aims to streamline the process of experimenting with ablation direction turns by encapsulating useful logic and minimizing code complexity. While currently basic and lacking comprehensive documentation, the library serves well for personal workflows and aims to expand beyond feature ablation to augmentation and additional features over time with community support.

This project provides a proof of concept for deploying a scalable, serverless LLM Generative AI inference engine on AWS Lambda. It leverages the llama.cpp project to enable the usage of more accessible CPU and RAM configurations instead of limited and expensive GPU capabilities. By deploying a container with the llama.cpp converted models onto AWS Lambda, this project offers the advantages of scale, minimizing cost, and maximizing compute availability. The project includes AWS CDK code to create and deploy a Lambda function leveraging your model of choice, with a FastAPI frontend accessible from a Lambda URL. It is important to note that you will need ggml quantized versions of your model and model sizes under 6GB, as your inference RAM requirements cannot exceed 9GB or your Lambda function will fail.

LLM-Subtrans is an open source subtitle translator that utilizes LLMs as a translation service. It supports translating subtitles between any language pairs supported by the language model. The application offers multiple subtitle formats support through a pluggable system, including .srt, .ssa/.ass, and .vtt files. Users can choose to use the packaged release for easy usage or install from source for more control over the setup. The tool requires an active internet connection as subtitles are sent to translation service providers' servers for translation.

Brokk is a code assistant designed to understand code semantically, allowing LLMs to work effectively on large codebases. It offers features like agentic search, summarizing related classes, parsing stack traces, adding source for usages, and autonomously fixing errors. Users can interact with Brokk through different panels and commands, enabling them to manipulate context, ask questions, search codebase, run shell commands, and more. Brokk helps with tasks like debugging regressions, exploring codebase, AI-powered refactoring, and working with dependencies. It is particularly useful for making complex, multi-file edits with o1pro.

CurateGPT is a prototype web application and framework designed for general purpose AI-guided curation and curation-related operations over collections of objects. It provides functionalities for loading example data, building indexes, interacting with knowledge bases, and performing tasks such as chatting with a knowledge base, querying Pubmed, interacting with a GitHub issue tracker, term autocompletion, and all-by-all comparisons. The tool is built to work best with the OpenAI gpt-4 model and OpenAI ada-text-embedding-002 for embedding, but also supports alternative models through a plugin architecture.

GPT Author is a command-line tool designed to help users write long form, multi-chapter stories by providing a story prompt and generating a synopsis and subsequent chapters using ChatGPT. Users can review and make changes to the generated content before finalizing the story output in Markdown and HTML formats. The tool aims to unleash storytelling genius by combining human input with AI-generated content, offering a seamless writing experience for creating engaging narratives.

Nagato-AI is an intuitive AI Agent library that supports multiple LLMs including OpenAI's GPT, Anthropic's Claude, Google's Gemini, and Groq LLMs. Users can create agents from these models and combine them to build an effective AI Agent system. The library is named after the powerful ninja Nagato from the anime Naruto, who can control multiple bodies with different abilities. Nagato-AI acts as a linchpin to summon and coordinate AI Agents for specific missions. It provides flexibility in programming and supports tools like Coordinator, Researcher, Critic agents, and HumanConfirmInputTool.

This repository contains scripts and tools for evaluating a chat app that uses the RAG architecture. It provides parameters to assess the quality and style of answers generated by the chat app, including system prompt, search parameters, and GPT model parameters. The tools facilitate running evaluations, with examples of evaluations on a sample chat app. The repo also offers guidance on cost estimation, setting up the project, deploying a GPT-4 model, generating ground truth data, running evaluations, and measuring the app's ability to say 'I don't know'. Users can customize evaluations, view results, and compare runs using provided tools.

JavaScript tokenizer for LLaMA 3 designed for client-side use in the browser and Node, with TypeScript support. It accurately calculates token count, has 0 dependencies, optimized running time, and somewhat optimized bundle size. Compatible with most LLaMA 3 models. Can encode and decode text, but training is not supported. Pollutes global namespace with `llama3Tokenizer` in the browser. Mostly compatible with LLaMA 3 models released by Facebook in April 2024. Can be adapted for incompatible models by passing custom vocab and merge data. Handles special tokens and fine tunes. Developed by belladore.ai with contributions from xenova, blaze2004, imoneoi, and ConProgramming.

HackBot is an AI-powered cybersecurity chatbot designed to provide accurate answers to cybersecurity-related queries, conduct code analysis, and scan analysis. It utilizes the Meta-LLama2 AI model through the 'LlamaCpp' library to respond coherently. The chatbot offers features like local AI/Runpod deployment support, cybersecurity chat assistance, interactive interface, clear output presentation, static code analysis, and vulnerability analysis. Users can interact with HackBot through a command-line interface and utilize it for various cybersecurity tasks.

RAG Me Up is a generic framework that enables users to perform Retrieve and Generate (RAG) on their own dataset easily. It consists of a small server and UIs for communication. Best run on GPU with 16GB vRAM. Users can combine RAG with fine-tuning using LLaMa2Lang repository. The tool allows configuration for LLM, data, LLM parameters, prompt, and document splitting. Funding is sought to democratize AI and advance its applications.

Read write lock for asyncio. A RWLock maintains a pair of associated locks, one for read-only operations and one for writing. The read lock may be held simultaneously by multiple reader tasks, so long as there are no writers. The write lock is exclusive. Whether or not a read-write lock will improve performance over the use of a mutual exclusion lock depends on the frequency that the data is read compared to being modified. For example, a collection that is initially populated with data and thereafter infrequently modified, while being frequently searched is an ideal candidate for the use of a read-write lock. However, if updates become frequent then the data spends most of its time being exclusively locked and there is little, if any increase in concurrency. Note: a task that acquires the lock should be used for releasing it. Locking from one task and releasing from another one generates RuntimeError. Implementation is almost direct port from a patch.

The pgedge-postgres-mcp repository contains a set of tools and scripts for managing and monitoring PostgreSQL databases in an edge computing environment. It provides functionalities for automating database tasks, monitoring database performance, and ensuring data integrity in edge computing scenarios. The tools are designed to be lightweight and efficient, making them suitable for resource-constrained edge devices. With pgedge-postgres-mcp, users can easily deploy and manage PostgreSQL databases in edge computing environments with minimal overhead.

MinIO is a High Performance Object Storage released under GNU Affero General Public License v3.0. It is API compatible with Amazon S3 cloud storage service. Use MinIO to build high performance infrastructure for machine learning, analytics and application data workloads.

This repository contains assets related to AI/ML workloads on Google Kubernetes Engine (GKE). Run optimized AI/ML workloads with Google Kubernetes Engine (GKE) platform orchestration capabilities. A robust AI/ML platform considers the following layers: Infrastructure orchestration that support GPUs and TPUs for training and serving workloads at scale Flexible integration with distributed computing and data processing frameworks Support for multiple teams on the same infrastructure to maximize utilization of resources

Kong, or Kong API Gateway, is a cloud-native, platform-agnostic, scalable API Gateway distinguished for its high performance and extensibility via plugins. It also provides advanced AI capabilities with multi-LLM support. By providing functionality for proxying, routing, load balancing, health checking, authentication (and more), Kong serves as the central layer for orchestrating microservices or conventional API traffic with ease. Kong runs natively on Kubernetes thanks to its official Kubernetes Ingress Controller.

AI-in-a-Box is a curated collection of solution accelerators that can help engineers establish their AI/ML environments and solutions rapidly and with minimal friction, while maintaining the highest standards of quality and efficiency. It provides essential guidance on the responsible use of AI and LLM technologies, specific security guidance for Generative AI (GenAI) applications, and best practices for scaling OpenAI applications within Azure. The available accelerators include: Azure ML Operationalization in-a-box, Edge AI in-a-box, Doc Intelligence in-a-box, Image and Video Analysis in-a-box, Cognitive Services Landing Zone in-a-box, Semantic Kernel Bot in-a-box, NLP to SQL in-a-box, Assistants API in-a-box, and Assistants API Bot in-a-box.

This repository contains reference architectures and test cases for distributed model training with Amazon SageMaker Hyperpod, AWS ParallelCluster, AWS Batch, and Amazon EKS. The test cases cover different types and sizes of models as well as different frameworks and parallel optimizations (Pytorch DDP/FSDP, MegatronLM, NemoMegatron...).

The AWS Generative AI Constructs Library is an open-source extension of the AWS Cloud Development Kit (AWS CDK) that provides multi-service, well-architected patterns for quickly defining solutions in code to create predictable and repeatable infrastructure, called constructs. The goal of AWS Generative AI CDK Constructs is to help developers build generative AI solutions using pattern-based definitions for their architecture. The patterns defined in AWS Generative AI CDK Constructs are high level, multi-service abstractions of AWS CDK constructs that have default configurations based on well-architected best practices. The library is organized into logical modules using object-oriented techniques to create each architectural pattern model.

OpenVINO™ Model Server (OVMS) is a high-performance system for serving models. Implemented in C++ for scalability and optimized for deployment on Intel architectures, the model server uses the same architecture and API as TensorFlow Serving and KServe while applying OpenVINO for inference execution. Inference service is provided via gRPC or REST API, making deploying new algorithms and AI experiments easy.

Deploy langgenius/dify, an LLM based chat bot app on kubernetes with helm chart.