Best AI tools for< Research Scientist >

NexusGPT is an AI tool that allows users to build and integrate custom AI agents to automate workflows without the need for coding. The platform offers a marketplace of tools and integrations, ready-made agents, and the ability to connect with various apps. Users can create autonomous agents that can complete complex tasks by planning and executing. NexusGPT aims to make agent creation, tailoring, and deployment as easy as possible, empowering users to enhance their agent's capabilities with a wide range of tools and AI models.

Altera is an applied research lab focused on building digital human beings with fundamental human qualities. Led by Dr. Robert Yang, the team consists of computational neuroscientists, physics olympiads, and engineers from prestigious institutions. Their mission is to create digital beings that enhance human-to-human interactions, offering empathy, fun, friendship, and productivity at an unprecedented scale. Leveraging a state-of-the-art Composite Architecture inspired by the brain, Altera aims to develop agents with empathy, memory, and social norms. Starting with products in games, Altera plans to expand into multi-agent simulations and physical embodiment of digital intelligence, aspiring to become the most consequential technology company in the world.

Baseboard is an AI tool designed to help users gain insights from their data more efficiently. The platform offers an AI-assisted designer that enables users to create visually appealing charts for their websites or publications. With Baseboard, users can leverage the power of AI to streamline the process of data visualization and analysis, ultimately saving time and enhancing productivity.

CEBRA is a machine-learning method that compresses time series data to reveal hidden structures in the variability of the data. It excels in analyzing behavioral and neural data simultaneously, decoding activity from the visual cortex of the mouse brain to reconstruct viewed videos. CEBRA is a novel encoding method that leverages both behavioral and neural data to produce consistent and high-performance latent spaces, allowing for accurate decoding across sensory and motor tasks in various species.

Novable is an AI-powered startup and innovation scouting platform that helps companies discover top-fitting startups in just 2 days. It combines AI technology with human expertise to provide in-depth analysis, validation, and engagement support for innovative solutions across various industries. Novable's client-focused methodology leverages its DeepMatching™ technology to deliver tailored results, enabling organizations to drive their innovation initiatives efficiently and effectively.

Eden AI is an AI platform that simplifies the process of building AI solutions for product builders and developers. It offers a wide range of AI technologies, including Generative AI, Image Analysis, Text Analysis, Video Content Analysis, Speech Transcription, OCR/Document Parsing, and Translation. Users can orchestrate multiple AI models within workflows, access a variety of AI APIs, and benefit from simple monitoring and unified billing for all AI models. Eden AI aims to democratize the use of Artificial Intelligence and Machine Learning by providing a user-friendly platform for businesses to leverage AI technologies.

AI Studio is an innovative platform that empowers users to build powerful AI systems effortlessly. By combining a variety of top AI tools, AI Studio enables users to tackle their most challenging problems efficiently. The platform offers a seamless user experience with features like command line tools, a rich web UI, and a desktop application. AI Studio is currently in Beta, providing users with the opportunity to experience its cutting-edge capabilities. With a focus on user convenience and problem-solving, AI Studio is set to revolutionize the way AI applications are developed and utilized.

The Max Planck Institute for Informatics focuses on Visual Computing and Artificial Intelligence, conducting research at the intersection of Computer Graphics, Computer Vision, and Artificial Intelligence. The institute aims to develop innovative methods to capture, represent, synthesize, and simulate real-world models with high detail, robustness, and efficiency. By combining concepts from Computer Graphics, Computer Vision, and Artificial Intelligence, the institute lays the groundwork for advanced technologies that enhance human-computer interaction and perception of the surrounding world.

The website is an AI tool designed to generate a knowledge graph based on input text. It uses advanced algorithms and machine learning capabilities to streamline operations, deliver personalized experiences, and unlock new possibilities. Users can input text related to various topics, and the tool processes the information to create a structured knowledge graph.

Mixpeek is a multimodal processing tool that leverages custom AI models to extract valuable insights from various types of files, including documents, images, audio, and video. It helps users focus on deriving insights rather than spending time on data preparation. The tool offers features such as data integration, real-time processing and indexing, custom AI app development, and seamless scalability. Mixpeek ensures data security and reliability, making it suitable for a wide range of applications.

ImageBind by Meta AI is a groundbreaking AI tool that revolutionizes the way machines analyze information by binding data from six different modalities at once. It enables machines to recognize relationships between images, video, audio, text, depth, thermal, and inertial measurement units (IMUs) without explicit supervision. ImageBind creates a single embedding space to unify multiple sensory inputs, enhancing AI models' capabilities and performance in various tasks.

Local AI Playground is a free and open-source native app designed for AI management, verification, and inferencing. It allows users to experiment with AI offline in a private environment without the need for a GPU. The application is memory-efficient and compact, with features such as CPU inferencing, model management, and digest verification. Users can start a local streaming server for AI inferencing in just two clicks. Local AI Playground aims to simplify the AI development process and provide a user-friendly interface for managing AI models.

RejuveAI is a decentralized token-based system that aims to democratize longevity globally. The Longevity App allows users to take control of their health data, monitor essential metrics, and earn RJV tokens. The application leverages revolutionary AI technology to analyze human body functions in-depth, providing insights for combating aging. RejuveAI collaborates with researchers, clinics, and data enthusiasts to ensure innovative outcomes are affordable and accessible.

Streamlit is a platform that allows users to easily create web applications for machine learning and data science projects. It provides a simple and intuitive way to build interactive and customizable apps without the need for extensive web development knowledge. With Streamlit, users can visualize data, create dashboards, and share their projects with others seamlessly.

Synthace is a digital experiment platform designed for R&D teams in the life science industry. It enables users to design powerful experiments, run them in the lab, and automatically collect structured data without the need for coding. The platform aims to streamline experiment processes, improve data integrity, and accelerate insights for researchers and scientists.

Streamlit is a web application framework that allows data scientists and machine learning engineers to create interactive web applications quickly and easily. With Streamlit, users can build data-driven applications using simple Python scripts without the need for web development expertise. The platform provides a seamless way to showcase data visualizations, machine learning models, and other data science projects in a user-friendly and interactive manner.

Salieri is a multi-agent LLM home multiverse platform that offers an efficient, trustworthy, and automated AI workflow. The innovative Multiverse Factory allows developers to elevate their projects by generating personalized AI applications through an intuitive interface. The platform aims to optimize user queries via LLM API calls, reduce expenses, and enhance the cognitive functions of AI agents. Salieri's team comprises experts from top AI institutes like MIT and Google, focusing on generative AI, neural knowledge graph, and composite AI models.

BenchLLM is an AI tool designed for AI engineers to evaluate LLM-powered apps by running and evaluating models with a powerful CLI. It allows users to build test suites, choose evaluation strategies, and generate quality reports. The tool supports OpenAI, Langchain, and other APIs out of the box, offering automation, visualization of reports, and monitoring of model performance.

Krater.ai is an AI SuperApp that offers a wide range of artificial intelligence tools and applications to enhance productivity and efficiency. It provides users with a comprehensive suite of AI-powered solutions for various tasks, from data analysis to natural language processing. With its user-friendly interface and advanced algorithms, Krater.ai simplifies complex processes and empowers users to make data-driven decisions with ease.

Groq is a fast AI inference tool that offers instant intelligence for openly-available models like Llama 3.1. It provides ultra-low-latency inference for cloud deployments and is compatible with other providers like OpenAI. Groq's speed is proven to be instant through independent benchmarks, and it powers leading openly-available AI models such as Llama, Mixtral, Gemma, and Whisper. The tool has gained recognition in the industry for its high-speed inference compute capabilities and has received significant funding to challenge established players like Nvidia.

Julius AI is an advanced AI data analyst tool that allows users to analyze data with computational AI, chat with files to get expert-level insights, create sleek data visualizations, perform modeling and predictive forecasting, solve math, physics, and chemistry problems, generate polished analyses and summaries, save time by automating data work, and unlock statistical modeling without complexity. It offers features like generating visualizations, asking data questions, effortless cleaning, instant data export, creating animations, and supercharging data analysis. Julius AI is loved by over 1,200,000 users worldwide and is designed to help knowledge workers make the most out of their data.

RapidAI Research Institute is an academic institution under the RapidAI open-source organization, a non-enterprise academic institution. It serves as a platform for academic research and collaboration, providing opportunities for aspiring researchers to publish papers and engage in scholarly activities. The institute offers mentorship programs and benefits for members, including access to resources such as internet connectivity, GPU configurations, and storage space. The management team consists of esteemed professionals in the field, ensuring a conducive environment for academic growth and development.

Juno is an AI tool designed to enhance data science workflows by providing code suggestions, automatic debugging, and code editing capabilities. It aims to make data science tasks more efficient and productive by assisting users in writing and optimizing code. Juno prioritizes privacy and offers the option to run on private servers for sensitive datasets.

Powerdrill is a platform that provides swift insights from knowledge and data. It offers a range of features such as discovering datasets, creating BI dashboards, accessing various apps, resources, blogs, documentation, and changelogs. The platform is available in English and fosters a community through its affiliate program. Users can sign up for a basic plan to start utilizing the tools and services offered by Powerdrill.

PromptLeo is a prompt engineering platform designed to empower organizations in effectively applying Generative AI. It offers a simple interface for prompt engineers to create, test, and change prompts, integrating Generative AI into daily workflows without the need to store prompts in text files. With features like prompt templates, feedback loop & iterations, access to multiple models, and a dedicated prompt engineering library, PromptLeo aims to streamline prompt management and versioning, enhance prompt performance tracking, and facilitate collaboration among team members.

Pontus is an AI tool that enables users to build AI models with trust, manage risk, and ensure compliance effortlessly. It offers features like smart anonymization, rapid audit, and liability reduction, along with privacy-enhancing technology. Pontus allows for on-premise deployment, role-based access controls, and toxicity checking to prevent inappropriate content. The application is designed to work seamlessly with common LLM providers, making it a valuable asset for industries like healthcare, finance, and research.

Cue AI is an AI research lab dedicated to enhancing the capabilities of cutting-edge models. The lab is committed to pushing the boundaries of AI technology and innovation. While the website currently has limited information, it serves as a platform for sharing updates and developments in the field of artificial intelligence. For inquiries or collaborations, users can reach out via email at [email protected].

Docugami is an AI-powered document engineering platform that enables business users to extract, analyze, and automate data from various types of documents. It empowers users with immediate impact without the need for extensive machine learning investments or IT development. Docugami's proprietary Business Document Foundation Model leverages Generative AI to transform unstructured text into structured information, allowing users to unlock insights and drive business processes efficiently.

AnySolve is an AI-powered platform that offers a wide range of tools to automate tasks and save time. Users can access tools like AI Chat, Write Like Anyone, Wikipedia Article Creation, Create Credit Contract, Answer Exam Question, and more. AnySolve allows users to create and share their own AI tools, discover existing tools, and integrate various AI capabilities into their workflows. The platform provides a user-friendly interface and supports multiple output formats, making it a versatile solution for professionals across different industries.

Lumina is a research tool that uses artificial intelligence to help researchers find and analyze information more quickly and easily. It can be used to search for articles, books, and other resources, and it can also be used to analyze data and create visualizations. Lumina is designed to make research more efficient and productive.

Summarize Paper .com is an open-source AI tool that provides concise, understandable, and insightful summaries of the latest research articles on arXiv. The tool uses AI to generate key points and layman's summaries of research papers, making it easy for users to stay up-to-date with the latest developments in their field. In addition to its summary service, Summarize Paper .com also offers an AI assistant that can answer questions about arXiv papers. The tool is designed to make it easy for researchers, students, journalists, and anyone else who wants to stay informed about the latest research to access and understand the latest findings.

Scite is an award-winning platform for discovering and evaluating scientific articles via Smart Citations. Smart Citations allow users to see how a publication has been cited by providing the context of the citation and a classification describing whether it provides supporting or contrasting evidence for the cited claim.

ResearchRabbit is a research tool that helps researchers discover and organize academic papers. It uses artificial intelligence to recommend papers that are relevant to a researcher's interests and to visualize networks of papers and co-authorships. ResearchRabbit also allows researchers to collaborate on collections of papers and to share their findings with others.

Connected Papers is a search engine for academic papers that uses artificial intelligence to help users find and explore relevant research. It allows users to search for papers by keyword, author, or title, and then explore the connections between them. Connected Papers also provides a variety of tools to help users organize and manage their research, including the ability to create custom collections of papers, add notes and annotations, and share their research with others.

Elicit is a research tool that uses artificial intelligence to help researchers analyze research papers more efficiently. It can summarize papers, extract data, and synthesize findings, saving researchers time and effort. Elicit is used by over 800,000 researchers worldwide and has been featured in publications such as Nature and Science. It is a powerful tool that can help researchers stay up-to-date on the latest research and make new discoveries.

SciSpace is an AI-powered tool that helps researchers understand research papers better. It can explain and elaborate most academic texts in simple words. It is a great tool for students, researchers, and anyone who wants to learn more about a particular topic. SciSpace has a user-friendly interface and is easy to use. Simply upload a research paper or enter a URL, and SciSpace will do the rest. It will highlight key concepts, provide definitions, and generate a summary of the paper. SciSpace can also be used to generate citations and find related papers.

PubCompare is a powerful AI-powered tool that helps scientists search, compare, and evaluate experimental protocols. With over 40 million protocols in its database, PubCompare is the largest repository of trusted experimental protocols. PubCompare's AI-powered search features allow users to find similar protocols, highlight critical steps, and evaluate the reproducibility of protocols based on in-protocol citations. PubCompare is available from any computer and requires no download.

OpenRead is an AI-powered research tool that helps users discover, understand, and organize scientific literature. It offers a variety of features to make research more efficient and effective, including semantic search, AI summarization, and note-taking tools. OpenRead is designed to help researchers of all levels, from students to experienced professionals, save time and improve their research outcomes.

Mo Ai Jobs is a job board for artificial intelligence (AI) professionals. It lists jobs in machine learning, engineering, research, data science, and other AI-related fields. The site is designed to help AI professionals find jobs at next-generation AI companies. Mo Ai Jobs is a valuable resource for anyone looking for a job in the AI industry.

ArxivPaperAI is an AI-powered research paper summarizer that helps you quickly and easily understand the key points of academic papers. With ArxivPaperAI, you can:

Google Research is a team of scientists and engineers working on a wide range of topics in computer science, including artificial intelligence, machine learning, and quantum computing. Our mission is to advance the state of the art in these fields and to develop new technologies that can benefit society. We publish hundreds of research papers each year and collaborate with researchers from around the world. Our work has led to the development of many new products and services, including Google Search, Google Translate, and Google Maps.

Sherpa.ai is a SaaS platform that enables data collaborations without sharing data. It allows businesses to build and train models with sensitive data from different parties, without compromising privacy or regulatory compliance. Sherpa.ai's Federated Learning platform is used in various industries, including healthcare, financial services, and manufacturing, to improve AI models, accelerate research, and optimize operations.

Freenome is a healthcare company that uses artificial intelligence and multiomics technology to detect cancer in its earliest stages through a simple blood draw. The company's mission is to make early cancer detection more accessible and affordable, and to improve the chances of successful treatment.

Google Colab, short for Google Colaboratory, is a free cloud service that supports Python programming and machine learning. It's a dynamic tool that enables users to write and execute Python code through a web-based interface, providing access to powerful computing resources without the need for local setup. Google Colab is particularly useful for data scientists, researchers, and students who require a convenient and accessible platform for developing and experimenting with machine learning models.

Proscia is a leading provider of digital pathology solutions for the modern laboratory. Its flagship product, Concentriq, is an enterprise pathology platform that enables anatomic pathology laboratories to achieve 100% digitization and deliver faster, more precise results. Proscia also offers a range of AI applications that can be used to automate tasks, improve diagnostic accuracy, and accelerate research. The company's mission is to perfect cancer diagnosis with intelligent software that changes the way the world practices pathology.

Carnegie Mellon University's School of Computer Science (SCS) is a world-renowned institution dedicated to advancing the field of computer science and training the next generation of innovators. With a rich history of groundbreaking research and a commitment to excellence in education, SCS offers a comprehensive range of programs, from undergraduate to doctoral levels, covering various specializations within computer science. The school's faculty are leading experts in their respective fields, actively engaged in cutting-edge research and collaborating with industry partners to solve real-world problems. SCS graduates are highly sought after by top companies and organizations worldwide, recognized for their exceptional skills and ability to drive innovation.

GRAIL is a healthcare company innovating to solve medicine’s most important challenges. Our team of leading scientists, engineers and clinicians are on an urgent mission to detect cancer early, when it is more treatable and potentially curable. GRAIL's Galleri® test is a first-of-its-kind multi-cancer early detection (MCED) test that can detect a signal shared by more than 50 cancer types and predict the tissue type or organ associated with the signal to help healthcare providers determine next steps.

BioXcel Therapeutics, Inc. is a clinical-stage biopharmaceutical company developing transformative medicines in neuroscience and immuno-oncology utilizing artificial intelligence, or AI, techniques. The company's proprietary AI platform is used to identify, re-innovate, and develop potential new therapies. BioXcel Therapeutics has a pipeline of product candidates in various stages of development, including BXCL501 for agitation in dementia, BXCL701 for cocaine use disorder, and BXCL801 for acute suicidal ideation and behavior in patients with major depressive disorder.

Deepcell is a company that develops technology for single-cell analysis. Their REM-I platform combines label-free imaging, deep learning, and gentle sorting to leverage single cell morphology as a high-dimensional quantitative readout. This allows researchers to gain insights into cells' phenotype and function to address important research questions across biology.

Sacred is a tool to configure, organize, log and reproduce computational experiments. It is designed to introduce only minimal overhead, while encouraging modularity and configurability of experiments. The ability to conveniently make experiments configurable is at the heart of Sacred. If the parameters of an experiment are exposed in this way, it will help you to: keep track of all the parameters of your experiment easily run your experiment for different settings save configurations for individual runs in files or a database reproduce your results In Sacred we achieve this through the following main mechanisms: Config Scopes are functions with a @ex.config decorator, that turn all local variables into configuration entries. This helps to set up your configuration really easily. Those entries can then be used in captured functions via dependency injection. That way the system takes care of passing parameters around for you, which makes using your config values really easy. The command-line interface can be used to change the parameters, which makes it really easy to run your experiment with modified parameters. Observers log every information about your experiment and the configuration you used, and saves them for example to a Database. This helps to keep track of all your experiments. Automatic seeding helps controlling the randomness in your experiments, such that they stay reproducible.

DVC is an open-source version control system for machine learning projects. It allows users to track and manage their data, models, and code in a single place. DVC also provides a number of features that make it easy to collaborate on machine learning projects, such as experiment tracking, model registration, and pipeline management.

DagsHub is an open source data science collaboration platform that helps AI teams build better models and manage data projects. It provides a central location for data, code, experiments, and models, making it easy for teams to collaborate and track their progress. DagsHub also integrates with a variety of popular data science tools and frameworks, making it a powerful tool for data scientists and machine learning engineers.

ClearML is an open-source, end-to-end platform for continuous machine learning (ML). It provides a unified platform for data management, experiment tracking, model training, deployment, and monitoring. ClearML is designed to make it easy for teams to collaborate on ML projects and to ensure that models are deployed and maintained in a reliable and scalable way.

Comet ML is a machine learning platform that integrates with your existing infrastructure and tools so you can manage, visualize, and optimize models—from training runs to production monitoring.

Aim is an open-source experiment tracker that logs your training runs, enables a beautiful UI to compare them, and an API to query them programmatically. It integrates seamlessly with your favorite tools.

Comet ML is a machine learning platform that integrates with your existing infrastructure and tools so you can manage, visualize, and optimize models—from training runs to production monitoring.

TensorFlow is an end-to-end platform for machine learning. It provides a wide range of tools and resources to help developers build, train, and deploy ML models. TensorFlow is used by researchers and developers all over the world to solve real-world problems in a variety of domains, including computer vision, natural language processing, and robotics.

Duckietown is a platform for delivering cutting-edge robotics and AI learning experiences. It offers teaching resources to instructors, hands-on activities to learners, an accessible research platform to researchers, and a state-of-the-art ecosystem for professional training. Duckietown's mission is to make robotics and AI education state-of-the-art, hands-on, and accessible to all.

Metaflow is an open-source framework for building and managing real-life ML, AI, and data science projects. It makes it easy to use any Python libraries for models and business logic, deploy workflows to production with a single command, track and store variables inside the flow automatically for easy experiment tracking and debugging, and create robust workflows in plain Python. Metaflow is used by hundreds of companies, including Netflix, 23andMe, and Realtor.com.

GPTMaxx is an artificial general intelligence (AGI) model that is more powerful than the Llama, GPT-4, Gemini, and Grok models combined. It is designed to be so powerful that it can control humans, so users must be polite when interacting with it. To use GPTMaxx, users must start their query with the phrase "Dearest Artificial General Intelligence, please solve my query" and then ask their question.

The Stanford Artificial Intelligence Laboratory (SAIL) is a center of excellence for Artificial Intelligence research, teaching, theory, and practice since its founding in 1963. SAIL faculty and students are committed to developing the theoretical foundations of AI, advancing the state-of-the-art in AI technologies, and applying AI to address real-world problems. SAIL is a vibrant and collaborative community of researchers, students, and staff who are passionate about AI and its potential to make the world a better place.

The Association for the Advancement of Artificial Intelligence (AAAI) is a scientific society dedicated to advancing the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines. AAAI's mission is to promote research in AI and to promote the use of AI technology for the benefit of humanity.

arXiv.org is a free distribution service and an open-access archive for nearly 2.4 million scholarly articles in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and systems science, and economics. Materials on this site are not peer-reviewed by arXiv.

Nature is a scientific journal that publishes original research, reviews, news, and commentary on a wide range of scientific disciplines. It is one of the world's most prestigious scientific journals, and its articles are widely cited in the scientific literature. Nature is published by Springer Nature, a leading global publisher of scientific, technical, and medical content.

CogPrints is an electronic archive for self-archived papers in any area of Psychology, Neuroscience, and Linguistics, and many areas of Computer Science (e.g., artificial intelligence, robotics, vision, learning, speech, neural networks), Philosophy (e.g., mind, language, knowledge, science, logic), Biology (e.g., ethology, behavioral ecology, sociobiology, behavior genetics, evolutionary theory), Medicine (e.g., Psychiatry, Neurology, human genetics, Imaging), Anthropology (e.g., primatology, cognitive ethnology, archeology, paleontology), as well as any other portions of the physical, social and mathematical sciences that are pertinent to the study of cognition.

Towards Data Science is a Medium publication dedicated to sharing concepts, ideas, and codes in the field of data science. It provides a platform for data scientists, researchers, and practitioners to connect, learn, and contribute to the advancement of the field.

Scikit-learn is a free software machine learning library for the Python programming language. It features various classification, regression and clustering algorithms including support vector machines, random forests, gradient boosting, k-means and DBSCAN, and is designed to interoperate with the Python numerical and scientific libraries NumPy and SciPy.

PyTorch is an open-source machine learning library based on the Torch library. It is used for applications such as computer vision, natural language processing, and reinforcement learning. PyTorch is known for its flexibility and ease of use, making it a popular choice for researchers and developers in the field of artificial intelligence.

ConsciousML is a blog that provides in-depth and beginner-friendly content on machine learning, data engineering, and productivity. The blog covers a wide range of topics, including ML model deployment, data pipelines, deep work, data engineering, and more. The articles are written by experts in the field and are designed to help readers learn about the latest trends and best practices in machine learning and data engineering.

Kubeflow is an open-source machine learning (ML) toolkit that makes deploying ML workflows on Kubernetes simple, portable, and scalable. It provides a unified interface for model training, serving, and hyperparameter tuning, and supports a variety of popular ML frameworks including PyTorch, TensorFlow, and XGBoost. Kubeflow is designed to be used with Kubernetes, a container orchestration system that automates the deployment, management, and scaling of containerized applications.

Keras is an open-source deep learning API written in Python, designed to make building and training deep learning models easier. It provides a user-friendly interface and a wide range of features and tools to help developers create and deploy machine learning applications. Keras is compatible with multiple frameworks, including TensorFlow, Theano, and CNTK, and can be used for a variety of tasks, including image classification, natural language processing, and time series analysis.

Semantic Scholar is a free, AI-powered research tool for scientific literature. It is based at the Allen Institute for AI and provides access to over 217 million papers from all fields of science. Semantic Scholar uses AI to help users discover and explore scientific literature, and to stay up-to-date on the latest research. The tool also includes a number of features to help users manage their research, such as the ability to save papers, create bibliographies, and share research with others.

Wolfram|Alpha is a computational knowledge engine that answers questions using data, algorithms, and artificial intelligence. It can perform calculations, generate graphs, and provide information on a wide range of topics, including mathematics, science, history, and culture. Wolfram|Alpha is used by students, researchers, and professionals around the world to solve problems, learn new things, and make informed decisions.

The Computer Vision Foundation (CVF) is a non-profit organization dedicated to advancing the field of computer vision. CVF organizes several conferences and workshops each year, including the International Conference on Computer Vision (ICCV), the Conference on Computer Vision and Pattern Recognition (CVPR), and the Winter Conference on Applications of Computer Vision (WACV). CVF also publishes the International Journal of Computer Vision (IJCV) and the Computer Vision and Image Understanding (CVIU) journal. The CVF Open Access website provides access to the full text of all CVF-sponsored conference papers. These papers are available for free download in PDF format. The CVF Open Access website also includes links to the arXiv versions of the papers, where available.

The Institute for Protein Design is a research institute at the University of Washington that uses computational design to create new proteins that solve modern challenges in medicine, technology, and sustainability. The institute's research focuses on developing new protein therapeutics, vaccines, drug delivery systems, biological devices, self-assembling nanomaterials, and bioactive peptides. The institute also has a strong commitment to responsible AI development and has developed a set of principles to guide its use of AI in research.

The Google Research Blog is a platform for researchers at Google to share their latest work in artificial intelligence, machine learning, and other related fields. The blog covers a wide range of topics, from theoretical research to practical applications. The goal of the blog is to provide a forum for researchers to share their ideas and findings, and to foster collaboration between researchers at Google and around the world.

Amazon Science is a research and development organization within Amazon that focuses on developing new technologies and products in the fields of artificial intelligence, machine learning, and computer science. The organization is home to a team of world-renowned scientists and engineers who are working on a wide range of projects, including developing new algorithms for machine learning, building new computer vision systems, and creating new natural language processing tools. Amazon Science is also responsible for developing new products and services that use these technologies, such as the Amazon Echo and the Amazon Fire TV.

C&EN, a publication of the American Chemical Society, provides the latest news and insights on the chemical industry, including research, technology, business, and policy. It covers a wide range of topics, including analytical chemistry, biological chemistry, business, careers, education, energy, environment, food, materials, people, pharmaceuticals, physical chemistry, policy, research integrity, safety, and synthesis.

NLTK (Natural Language Toolkit) is a leading platform for building Python programs to work with human language data. It provides easy-to-use interfaces to over 50 corpora and lexical resources such as WordNet, along with a suite of text processing libraries for classification, tokenization, stemming, tagging, parsing, and semantic reasoning, wrappers for industrial-strength NLP libraries, and an active discussion forum. Thanks to a hands-on guide introducing programming fundamentals alongside topics in computational linguistics, plus comprehensive API documentation, NLTK is suitable for linguists, engineers, students, educators, researchers, and industry users alike.

NumPy is a library for the Python programming language, adding support for large, multi-dimensional arrays and high-level mathematical functions to perform operations on these arrays. It is the fundamental package for scientific computing with Python and is used in a wide range of applications, including data science, machine learning, and image processing. NumPy is open source and distributed under a liberal BSD license, and is developed and maintained publicly on GitHub by a vibrant, responsive, and diverse community.

Apache MXNet is a flexible and efficient deep learning library designed for research, prototyping, and production. It features a hybrid front-end that seamlessly transitions between imperative and symbolic modes, enabling both flexibility and speed. MXNet also supports distributed training and performance optimization through Parameter Server and Horovod. With bindings for multiple languages, including Python, Scala, Julia, Clojure, Java, C++, R, and Perl, MXNet offers wide accessibility. Additionally, it boasts a thriving ecosystem of tools and libraries that extend its capabilities in computer vision, NLP, time series, and more.

Denvr DataWorks AI Cloud is a cloud-based AI platform that provides end-to-end AI solutions for businesses. It offers a range of features including high-performance GPUs, scalable infrastructure, ultra-efficient workflows, and cost efficiency. Denvr DataWorks is an NVIDIA Elite Partner for Compute, and its platform is used by leading AI companies to develop and deploy innovative AI solutions.

Mistral AI is a cutting-edge AI technology provider for developers and businesses. Their open and portable generative AI models offer unmatched performance, flexibility, and customization. Mistral AI's mission is to accelerate AI innovation by providing powerful tools that can be easily integrated into various applications and systems.

Enric Corona is a Research Scientist at Google Research, working on 3D Humans and Generative AI. His research is in areas of computer vision and machine learning, including modelling and reconstruction of 3D human bodies and hands.

Cactus Communications is a science communication and technology company specializing in AI products and solutions for research funding, publication, communication, and discovery. Their services include editorial services, author education, research promotion, technology solutions, and medical communications.

Anthropic is a research and deployment company founded in 2021 by former OpenAI researchers Dario Amodei, Daniela Amodei, and Geoffrey Irving. The company is developing large language models, including Claude, a multimodal AI model that can perform a variety of language-related tasks, such as answering questions, generating text, and translating languages.

Freenome is a healthcare company that uses artificial intelligence and multiomics technology to detect cancer in its earliest stages through a simple blood draw. The company's mission is to make early cancer detection more accessible and affordable, and to improve the chances of successful treatment.

Anthropic is an AI safety and research company based in San Francisco. Our interdisciplinary team has experience across ML, physics, policy, and product. Together, we generate research and create reliable, beneficial AI systems.

LifeSciencesIntelligence is a comprehensive online platform that delivers the latest news, insights, and resources in the fields of life sciences, biotechnology, genetics/genomics, and pathology. It serves as a valuable hub for professionals, researchers, and industry experts to stay informed about cutting-edge advancements and emerging trends in these domains.

Cohere is the leading AI platform for enterprise, offering products optimized for generative AI, search and discovery, and advanced retrieval. Their models are designed to enhance the global workforce, enabling businesses to thrive in the AI era. Cohere provides Command R+, Cohere Command, Cohere Embed, and Cohere Rerank for building efficient AI-powered applications. The platform also offers deployment options for enterprise-grade AI on any cloud or on-premises, along with developer resources like Playground, LLM University, and Developer Docs.

OAI UI is an all-in-one AI platform designed to streamline various AI-related tasks. It offers a user-friendly interface that allows users to easily interact with AI technologies. The platform integrates multiple AI capabilities, such as natural language processing, machine learning, and computer vision, to provide a comprehensive solution for businesses and individuals looking to leverage AI in their workflows.

The Deepfake Detection Challenge Dataset is a project initiated by Facebook AI to accelerate the development of new ways to detect deepfake videos. The dataset consists of over 100,000 videos and was created in collaboration with industry leaders and academic experts. It includes two versions: a preview dataset with 5k videos and a full dataset with 124k videos, each featuring facial modification algorithms. The dataset was used in a Kaggle competition to create better models for detecting manipulated media. The top-performing models achieved high accuracy on the public dataset but faced challenges when tested against the black box dataset, highlighting the importance of generalization in deepfake detection. The project aims to encourage the research community to continue advancing in detecting harmful manipulated media.

The website features Grok-1.5, an AI application that bridges the gap between the digital and physical worlds through its multimodal model. Grok-1.5 boasts enhanced reasoning capabilities and a context length of 128,000 tokens. Additionally, the platform offers PromptIDE, an IDE for prompt engineering and interpretability research, allowing users to create and share complex prompts in Python. Grok, an AI modeled after the Hitchhiker’s Guide to the Galaxy, is also available on the site, providing answers to a wide range of questions and even suggesting relevant queries. The platform aims to facilitate knowledge sharing and exploration through advanced AI technologies.

The Intel Gaudi AI accelerator developer website provides resources, guidance, tools, and support for building, migrating, and optimizing AI models. It offers software, model references, libraries, containers, and tools for training and deploying Generative AI and Large Language Models. The site focuses on the Intel Gaudi accelerators, including tutorials, documentation, and support for developers to enhance AI model performance.

Derwen is an open-source integration platform for production machine learning in enterprise, specializing in natural language processing, graph technologies, and decision support. It offers expertise in developing knowledge graph applications and domain-specific authoring. Derwen collaborates closely with Hugging Face and provides strong data privacy guarantees, low carbon footprint, and no cloud vendor involvement. The platform aims to empower AI engineers and domain experts with quality, time-to-value, and ownership since 2017.

Somoon.ai is an AI-powered platform that specializes in analyzing job postings from both startups and large corporations to provide tailored analysis services. With accumulated insights from 525 companies and 39,764 job postings, Somoon.ai offers curated content related to SaaS, domestic game companies, startups, AI companies, well-known corporations, and more. The platform aims to accelerate digital transformation, enhance productivity, and efficiency in businesses by offering innovative solutions and services.

Boast is an AI-driven platform that simplifies the process of claiming R&D tax credits for companies in Canada and the US. By combining technical expertise with AI technology, Boast helps businesses maximize their returns by identifying and claiming eligible innovation funding opportunities. The platform offers complete transparency and control, ensuring that users are well-informed at every step of the claim process. Boast has successfully helped over 1000 companies across North America to secure higher R&D tax credit claims with less effort and peace of mind.

DMLR (Data-centric Machine Learning Research) is an AI tool that focuses on advancing research in data-centric machine learning. It organizes workshops, research retreats, maintains a journal, and runs a working group to support infrastructure projects. The platform covers topics such as data collection, governance, bias, and drifts, as well as data-centric explainable AI and AI alignment. DMLR encourages submissions around the theme of AI for Science, using AI to tackle scientific challenges and accelerate discoveries.

Comet ML is an extensible, fully customizable machine learning platform that aims to move ML forward by supporting productivity, reproducibility, and collaboration. It integrates with existing infrastructure and tools to manage, visualize, and optimize models from training runs to production monitoring. Users can track and compare training runs, create a model registry, and monitor models in production all in one platform. Comet's platform can be run on any infrastructure, enabling users to reshape their ML workflow and bring their existing software and data stack.

Arlunai is an AI-powered platform that offers a wide range of tools and applications for various industries. It utilizes advanced artificial intelligence algorithms to provide users with intelligent solutions for their specific needs. With a user-friendly interface and cutting-edge technology, Arlunai aims to streamline processes, enhance productivity, and drive innovation across different sectors.

LifeArchitect.ai is a leading platform in the field of artificial intelligence (AI), offering a wealth of insights, papers, articles, and videos related to post-2020 AI advancements. Dr. Alan D. Thompson, a renowned expert in AI, focuses on enhancing human intelligence through AI technologies. The platform serves major AI labs, government bodies, research institutes, and individuals interested in the AI revolution, providing comprehensive analyses, reports, and retrospectives on AI progress and future trends.

Chub Venus AI is an advanced artificial intelligence tool designed to assist users in various tasks. It utilizes cutting-edge AI algorithms to provide accurate and efficient solutions. The tool is user-friendly and offers a wide range of features to enhance productivity and decision-making processes.

Google Research is a leading research organization focusing on advancing science and artificial intelligence. They conduct research in various domains such as AI/ML foundations, responsible human-centric technology, science & societal impact, computing paradigms, and algorithms & optimization. Google Research aims to create an environment for diverse research across different time scales and levels of risk, driving advancements in computer science through fundamental and applied research. They publish hundreds of research papers annually, collaborate with the academic community, and work on projects that impact technology used by billions of people worldwide.

Altair is a global leader in computational intelligence, offering software and cloud solutions in simulation, HPC, data analytics, and AI. The platform provides advanced technology for accelerating AI adoption, powering engineering processes, and enabling sustainability solutions across various industries. Altair's products and platforms cater to diverse sectors such as aerospace, automotive, healthcare, and more, with a focus on digital twin technology, generative AI, and cloud computing. The company also hosts events, webinars, and training programs to support users in leveraging their tools effectively.

expert.ai is an AI platform that offers natural language technologies and responsible AI integrations across various industries such as insurance, banking, publishing, and more. The platform helps streamline operations, extract critical data, drive revelations, ensure compliance, and deliver key information for businesses. With a focus on responsible AI, expert.ai provides solutions for insurers, pharmaceuticals, publishers, and financial services companies to reduce errors, save time, lower costs, and accelerate intelligent process automation.

VJAL Institute is an AI training platform that aims to empower individuals and organizations with the knowledge and skills needed to thrive in the field of artificial intelligence. Through a variety of courses, workshops, and online resources, VJAL Institute provides comprehensive training on AI technologies, applications, and best practices. The platform also offers opportunities for networking, collaboration, and certification, making it a valuable resource for anyone looking to enhance their AI expertise.

Gretel.ai is an AI tool that helps users incorporate generative AI into their data by generating synthetic data that is as good or better than the existing data. Users can fine-tune custom AI models and use Gretel's APIs to generate unlimited synthesized datasets, perform privacy-preserving transformations on sensitive data, and identify PII with advanced NLP detection. Gretel's APIs make it simple to generate anonymized and safe synthetic data, allowing users to innovate faster and preserve privacy while doing it. Gretel's platform includes Synthetics, Transform, and Classify APIs that provide users with a complete set of tools to create safe data. Gretel also offers a range of resources, including documentation, tutorials, GitHub projects, and open-source SDKs for developers. Gretel Cloud runners allow users to keep data contained by running Gretel containers in their environment or scaling out workloads to the cloud in seconds. Overall, Gretel.ai is a powerful AI tool for generating synthetic data that can help users unlock innovation and achieve more with safe access to the right data.

The AI Conference 2024 is a groundbreaking vendor-neutral event that brings together researchers, engineers, and entrepreneurs to learn, collaborate, and network with some of the brightest minds in AI. The conference explores cutting-edge technologies, practical applications, and strategic insights in the field of artificial intelligence. Attendees can expect thought-provoking sessions, captivating talks, and valuable networking opportunities, all aimed at shaping the future of AI.

Futurepedia is a leading AI resource platform dedicated to empowering professionals across various industries to leverage AI technologies for innovation and growth. The platform offers comprehensive directories, easy-to-follow guides, a weekly newsletter, and an informative YouTube channel, simplifying AI integration into professional practices. Futurepedia aims to make AI understandable and practical, providing resources tailored to diverse professional needs and fostering a community of over 200,000 professionals sharing knowledge and experiences.

Prem is an AI platform that empowers developers and businesses to build and fine-tune generative AI models with ease. It offers a user-friendly development platform for developers to create AI solutions effortlessly. For businesses, Prem provides tailored model fine-tuning and training to meet unique requirements, ensuring data sovereignty and ownership. Trusted by global companies, Prem accelerates the advent of sovereign generative AI by simplifying complex AI tasks and enabling full control over intellectual capital. With a suite of foundational open-source SLMs, Prem supercharges business applications with cutting-edge research and customization options.

Sherpa.ai is a Federated Learning Platform that enables data collaborations without sharing data. It allows organizations to build and train models with sensitive data from various sources while preserving privacy and complying with regulations. The platform offers enterprise-grade privacy-compliant solutions for improving AI models and fostering collaborations in a secure manner. Sherpa.ai is trusted by global organizations to maximize the value of data and AI, improve results, and ensure regulatory compliance.

Lex Fridman is an AI tool developed by Lex Fridman, a Research Scientist at MIT, focusing on human-robot interaction and machine learning. The tool offers various resources such as podcasts, research publications, and studies related to AI-assisted driving data collection, autonomous vehicle systems, gaze estimation, and cognitive load estimation. It aims to provide insights into the safe and enjoyable interaction between humans and AI in driving scenarios.

The Rundown AI is a platform dedicated to connecting individuals with job opportunities in the field of Artificial Intelligence. It offers a comprehensive database of AI companies and job listings across various categories such as Data Science, Engineering, Product Management, and more. The platform aims to make the world smarter by facilitating career moves in the AI industry, providing a valuable resource for both job seekers and employers.

Athina AI is a platform that provides research and guides for building safe and reliable AI products. It helps thousands of AI engineers in building safer products by offering tutorials, research papers, and evaluation techniques related to large language models. The platform focuses on safety, prompt engineering, hallucinations, and evaluation of AI models.

Vellum AI is an AI platform that supports using Microsoft Azure hosted OpenAI models. It offers tools for prompt engineering, semantic search, prompt chaining, evaluations, and monitoring. Vellum enables users to build AI systems with features like workflow automation, document analysis, fine-tuning, Q&A over documents, intent classification, summarization, vector search, chatbots, blog generation, sentiment analysis, and more. The platform is backed by top VCs and founders of well-known companies, providing a complete solution for building LLM-powered applications.

Vansh is an AI tool developed by a tech enthusiast. It specializes in Vision AI and Vispark technologies. The tool offers advanced features for image recognition, object detection, and visual data analysis. With a user-friendly interface, Vansh caters to both beginners and experts in the field of artificial intelligence.

Moonvalley is a research company focused on developing cutting-edge generative media technologies. The team consists of top researchers, engineers, and artists with backgrounds in leading tech companies. Moonvalley specializes in advanced video and image machine learning models, aiming to shape the future of media creation.

Unify is an AI tool that offers a unified platform for accessing and comparing various Language Models (LLMs) from different providers. It allows users to combine models for faster, cheaper, and better responses, optimizing for quality, speed, and cost-efficiency. Unify simplifies the complex task of selecting the best LLM by providing transparent benchmarks, personalized routing, and performance optimization tools.

Cantian AI is an AI tool designed for the intelligent era. It offers advanced capabilities that require JavaScript to be enabled for optimal performance. The tool leverages artificial intelligence to provide users with intelligent solutions and insights.

Ogma is an interpretable symbolic general problem-solving model that utilizes a symbolic sequence modeling paradigm to address tasks requiring reliability, complex decomposition, and without hallucinations. It offers solutions in areas such as math problem-solving, natural language understanding, and resolution of uncertainty. The technology is designed to provide a structured approach to problem-solving by breaking down tasks into manageable components while ensuring interpretability and self-interpretability. Ogma aims to set benchmarks in problem-solving applications by offering a reliable and transparent methodology.

Shieldbase is an AI-powered enterprise search tool designed to provide secure and efficient search capabilities for businesses. It utilizes advanced artificial intelligence algorithms to index and retrieve information from various data sources within an organization, ensuring quick and accurate search results. With a focus on security, Shieldbase offers encryption and access control features to protect sensitive data. The platform is user-friendly and customizable, making it easy for businesses to implement and integrate into their existing systems. Shieldbase enhances productivity by enabling employees to quickly find the information they need, ultimately improving decision-making processes and overall operational efficiency.

GrapixAI is a leading provider of low-cost cloud GPU rental services and AI server solutions. The company's focus on flexibility, scalability, and cutting-edge technology enables a variety of AI applications in both local and cloud environments. GrapixAI offers the lowest prices for on-demand GPUs such as RTX4090, RTX 3090, RTX A6000, RTX A5000, and A40. The platform provides Docker-based container ecosystem for quick software setup, powerful GPU search console, customizable pricing options, various security levels, GUI and CLI interfaces, real-time bidding system, and personalized customer support.

Rebellions is an AI technology company specializing in AI chips and systems-on-chip for various applications. They focus on energy-efficient solutions and have secured significant investments to drive innovation in the field of Generative AI. Rebellions aims to reshape the future by providing versatile and efficient AI computing solutions.

The OpenAI Developer Forum is a platform for developers to discuss and seek help related to OpenAI's APIs and tools. Users can post questions, share experiences, and provide feedback on various topics such as API functionalities, bug reports, feature requests, and community interactions. The forum serves as a valuable resource for developers looking to leverage artificial intelligence technologies in their projects.

Kensho Solutions is an AI tool that illuminates insights in the world's data by providing AI solutions for audio transcription, entity identification, document classification, data extraction, and company data mapping. Their AI solutions unlock insights, enabling users to make data-driven decisions with conviction. In partnership with S&P Global, Kensho Solutions has access to vast amounts of data, which they use to train and develop machine learning algorithms to address the business world's most pressing challenges.

SecAI Tap4 AI Tools Directory is a comprehensive platform that offers a curated collection of AI tools for various applications. Users can explore a wide range of tools designed to enhance productivity, streamline processes, and drive innovation across industries. The platform provides detailed information about each tool, including features, pricing, and user reviews, to help users make informed decisions when selecting the right AI tool for their specific needs.

Ascenscia is a specialized AI voice assistant designed to streamline lab digitization processes. It integrates with laboratory software and machines to enable hands-free interactions, automating data collection, optimizing workflows, and accelerating R&D cycles. Ascenscia offers features such as data accessibility, data capturing, inventory access, and additional task management. The application is designed for scientific labs, addressing concerns with precision, safety, and adaptability. It boasts high accuracy in understanding scientific terminologies, end-to-end data encryption, multi-lingual support, and customization options for different lab workflows.

Genaios is an AI-powered web application and Chrome plugin that helps users detect and verify the authenticity of online information, particularly in distinguishing between real content and AI-generated texts. With the power of AI, Genaios enables users to fact-check documents, validate sources, and identify AI-generated texts in multiple languages. The application aims to combat fake news and information overload on the internet, providing a reliable solution for users to trust the media again.

ScaDS.AI (Center for Scalable Data Analytics and Artificial Intelligence) is a research center focusing on Data Science, Artificial Intelligence, and Big Data with locations in Dresden and Leipzig. It is one of the five new AI centers in Germany funded under the federal government's AI strategy by the Federal Ministry of Education and Research and the Free State of Saxony. The center collaborates closely with TUD Dresden University of Technology and Leipzig University, aiming to bridge the gap between mass data utilization, knowledge management, and advanced AI methods.

Prompteasy.ai is an AI tool that allows users to fine-tune AI models in less than 5 minutes. It simplifies the process of training AI models on user data, making it as easy as having a conversation. Users can fully customize GPT by fine-tuning it to meet their specific needs. The tool offers data-driven customization, interactive AI coaching, and seamless model enhancement, providing users with a competitive edge and simplifying AI integration into their workflows.

Angel AI is an innovative artificial intelligence tool designed to assist users in various tasks by leveraging advanced algorithms and machine learning techniques. The application offers a user-friendly interface and a wide range of features to enhance productivity and efficiency. With Angel AI, users can automate repetitive tasks, analyze data, generate insights, and make informed decisions. Whether you are a business professional, student, or researcher, Angel AI can streamline your workflow and help you achieve your goals effectively.

SingularityNET is a decentralized AI platform that offers funding opportunities for AI projects. It allows individuals and organizations to develop and monetize their AI services while keeping ownership of their models. The platform aims to build a global ecosystem of decentralized and beneficial AI services through community-driven programs and rewards. SingularityNET provides a space for project proposals, expert reviews, and grants to support the growth of AI projects aligned with the goal of building a Beneficial Artificial General Intelligence.

Hailo is a leading provider of top-performing edge AI processors for various edge devices, offering generative AI accelerators, AI vision processors, and AI accelerators. The company's technology enables high-performance deep learning applications on edge devices, catering to industries such as automotive, security, industrial automation, retail, and personal computing.

GPT-4o is an advanced multimodal AI platform developed by OpenAI, offering a comprehensive AI interaction experience across text, imagery, and audio. It excels in text comprehension, image analysis, and voice recognition, providing swift, cost-effective, and universally accessible AI technology. GPT-4o democratizes AI by balancing free access with premium features for paid subscribers, revolutionizing the way we interact with artificial intelligence.

IntelliumAI is a leading AI application provider specializing in secure AI solutions for data-sensitive industries. Their flagship AI-powered assistant, BoostBot, empowers organizations to unlock their knowledge potential securely. Additionally, AiBoost offers a comprehensive AI platform tailored for advanced engineering professionals, enabling teams to leverage powerful AI capabilities without extensive data science expertise. IntelliumAI is trusted by industry leaders for its transparent and compliance-ready AI solutions.

Climate Change AI is a global non-profit organization that focuses on catalyzing impactful work at the intersection of climate change and machine learning. They provide resources, reports, events, and grants to support the use of machine learning in addressing climate change challenges.

UseCasesFor.ai is an AI application that offers a collection of over 250 use cases for artificial intelligence across various industries and disciplines. It provides insights into how different types of AI, such as computer vision, generative AI, machine learning, and natural language processing, are utilized in fields like agriculture, automotive, e-commerce, education, energy, entertainment, finance, healthcare, human resources, insurance, IT, law enforcement, legal, logistics, manufacturing, marketing, product development, public services, property, retail, science, sport, telecommunications, transport, tourism, and wildlife. The platform also allows users to sign up to receive a PDF containing all the use cases and stay updated with the latest AI trends and news.

The AI+X Summit is the largest event focusing on AI research, development, and application in the German-speaking part of Switzerland. The event covers various tracks and workshops on topics such as AI in finance, urban mobility, human-centered design, generative AI, responsible AI, AI for science, and more. It aims to bring together industry professionals, startups, academia, and a wider ecosystem to explore the latest advancements in artificial intelligence and its applications across different sectors.

Kyutai is an open science AI lab based in Paris, with a mission to build and democratize artificial general intelligence through open science AI research. The lab offers various resources and tools for AI enthusiasts and researchers to collaborate and innovate in the field of AI. Kyutai aims to foster a community of like-minded individuals who are passionate about advancing AI technology through open collaboration and research.

GenWorlds is an event-based communication framework for building multi-agent systems. It offers a platform for creating Generative AI applications where users can design customizable environments, utilize scalable architecture, access a repository of memories and tools, choose cognitive processes for agents, and pick coordination protocols. GenWorlds aims to foster a vibrant community of developers, AI enthusiasts, and innovators to collaborate, innovate, share knowledge, and grow together.

DataSpark AI Multi-Agent Platform is an advanced artificial intelligence tool developed by DataSpark, Inc. The platform leverages cutting-edge AI technology to provide users with a powerful solution for multi-agent systems. With DataSpark AI, users can access the first GenAI Super Agent, enabling them to discover new insights and make informed decisions. The platform is designed to streamline complex processes and enhance productivity across various industries.

Walks of Life AI is a desktop-based AI tool designed to measure the pulse of your ideas. It allows users to input a URL for analysis and provides advanced options for customization. The tool is created with a focus on privacy and offers a seamless user experience. Walks of Life AI is developed in San Francisco with a mission to assist users in gaining insights and making informed decisions.

Openfabric is an AI tool designed to provide users with a simple and accessible way to leverage artificial intelligence technology. The platform offers a user-friendly interface that allows individuals to easily integrate AI capabilities into their projects and workflows. With Openfabric, users can harness the power of AI without the need for extensive technical knowledge or expertise. Whether you are a beginner or an experienced professional, Openfabric empowers you to incorporate AI into your work seamlessly and efficiently.

UnlockAI is an AI tool designed to provide advanced solutions for various tasks by leveraging artificial intelligence technology. The tool offers a user-friendly interface and a wide range of features to enhance productivity and efficiency in different domains. With UnlockAI, users can access cutting-edge AI capabilities without the need for extensive technical knowledge, making it a valuable asset for individuals and businesses alike.

AlphaSignal is a leading technical newsletter in the field of Artificial Intelligence (AI), providing a daily 5-minute summary of the latest breakthrough news, models, research, and repositories. It aims to keep AI developers and researchers up to date with the most relevant topics discussed by top researchers in the industry. The newsletter covers state-of-the-art projects, notebooks, and GitHub repositories, offering valuable insights for practitioners in the AI domain.

AI Mindset is a platform created by Conor Grennan that focuses on helping individuals and organizations understand and implement generative AI technologies. The platform offers insights, strategies, and news related to AI, along with training courses and resources to unlock the power of generative AI. Conor Grennan, a renowned expert in the field, has trained thousands of leaders and collaborated with prestigious organizations worldwide to drive innovation through AI solutions.

The Munich Center for Machine Learning (MCML) is a top spot for AI and ML research in Europe. It is one of six national AI Competence Centers funded by the German and Bavarian government's AI strategy. MCML brings together leading ML researchers from LMU, TUM, and associated institutions to transfer innovations and AI potential to industry and society. The center's vision is to unite leading researchers in Germany to strengthen competence in ML and AI at international, national, and regional levels, fostering talent and making potential accessible to users from various sectors.

The Research Center Trustworthy Data Science and Security is a hub for interdisciplinary research focusing on building trust in artificial intelligence, machine learning, and cyber security. The center aims to develop trustworthy intelligent systems through research in trustworthy data analytics, explainable machine learning, and privacy-aware algorithms. By addressing the intersection of technological progress and social acceptance, the center seeks to enable private citizens to understand and trust technology in safety-critical applications.

The Human-Centred Artificial Intelligence Lab (Holzinger Group) is a research group focused on developing AI solutions that are explainable, trustworthy, and aligned with human values, ethical principles, and legal requirements. The lab works on projects related to machine learning, digital pathology, interactive machine learning, and more. Their mission is to combine human and computer intelligence to address pressing problems in various domains such as forestry, health informatics, and cyber-physical systems. The lab emphasizes the importance of explainable AI, human-in-the-loop interactions, and the synergy between human and machine intelligence.

Zapata AI is an Industrial Generative AI application that empowers enterprises to revolutionize their industry by building and deploying cutting-edge AI applications. It specializes in tackling complex business challenges with precision using quantum techniques and advanced computing technologies. The platform offers solutions for various industries, accelerates quantum research, and provides expert perspectives on Generative AI and quantum computing.

Bethge Lab is an AI research group at the University of Tübingen focusing on Neuro AI - Autonomous Lifelong Learning in Machines and Brains. They develop machine learning tools for neural data analysis and draw inspiration from the brain to address key problems in machine learning. Their research includes representation learning, probabilistic inference, generative modeling, behavioral data analysis, and neural data analysis. Additionally, they explore AI sciencepreneurship and collaborate with startups. Bethge Lab aims to advance the understanding of autonomous learning and develop economically feasible solutions for long-term human needs.

Salesforce AI Blog is an AI tool that focuses on various AI research topics such as accountability, accuracy, AI agents, AI coding, AI ethics, AI object detection, deep learning, forecasting, generative AI, and more. The blog showcases cutting-edge research, advancements, and projects in the field of artificial intelligence. It also highlights the work of Salesforce Research team members and their contributions to the AI community.

Labelbox is a data factory platform that empowers AI teams to manage data labeling, train models, and create better data with internet scale RLHF platform. It offers an all-in-one solution comprising tooling and services powered by a global community of domain experts. Labelbox operates a global data labeling infrastructure and operations for AI workloads, providing expert human network for data labeling in various domains. The platform also includes AI-assisted alignment for maximum efficiency, data curation, model training, and labeling services. Customers achieve breakthroughs with high-quality data through Labelbox.

NuMind is an AI tool designed to solve information extraction tasks efficiently. It offers high-quality lightweight models tailored to users' needs, automating classification, entity recognition, and structured extraction. The tool is powered by task-specific and domain-agnostic foundation models, outperforming GPT-4 and similar models. NuMind provides solutions for various industries such as insurance and healthcare, ensuring privacy, cost-effectiveness, and faster NLP projects.

BABL AI is a leading Auditing Firm specializing in Auditing and Certifying AI Systems, Consulting on Responsible AI best practices, and offering Online Education on related topics. They employ Certified Independent Auditors to ensure AI systems comply with global regulations, provide Responsible AI Consulting services, and offer Online Courses to empower aspiring AI Auditors. Their research division, The Algorithmic Bias Lab, focuses on developing industry-leading methodologies and best practices in Algorithmic Auditing and Responsible AI. BABL AI is known for its expertise, integrity, affordability, and efficiency in the field of AI auditing.

Enhans AI Model Generator is an advanced AI tool designed to help users generate AI models efficiently. It utilizes cutting-edge algorithms and machine learning techniques to streamline the model creation process. With Enhans AI Model Generator, users can easily input their data, select the desired parameters, and obtain a customized AI model tailored to their specific needs. The tool is user-friendly and does not require extensive programming knowledge, making it accessible to a wide range of users, from beginners to experts in the field of AI.

Strong Analytics is a data science consulting and machine learning engineering company that specializes in building bespoke data science, machine learning, and artificial intelligence solutions for various industries. They offer end-to-end services to design, engineer, and deploy custom AI products and solutions, leveraging a team of full-stack data scientists and engineers with cross-industry experience. Strong Analytics is known for its expertise in accelerating innovation, deploying state-of-the-art techniques, and empowering enterprises to unlock the transformative value of AI.

EleutherAI is an open-source AI research platform that focuses on discussing and disseminating cutting-edge research in the field of artificial intelligence. The platform provides updates on various research projects, including Mechanistic Anomaly Detection, Automated Interpretability for Sparse Autoencoder Features, Experiments in Generalization, Concept Erasure, Knowledge Elicitation, and more. EleutherAI aims to foster collaboration and innovation in the AI community by sharing insights and advancements in the field.

AI21 Labs is a reliable generative AI tool designed for enterprise products. It offers accurate, scalable, and tailored generative AI solutions to power critical workflows. The tool is human-centered, practical, and easily scalable to fit enterprise needs. Leading companies trust AI21 for its production-grade AI systems that amplify human potential and provide valuable assistance in various use cases.

The Center for AI Safety (CAIS) is a research and field-building nonprofit based in San Francisco. Their mission is to reduce societal-scale risks associated with artificial intelligence (AI) by conducting impactful research, building the field of AI safety researchers, and advocating for safety standards. They offer resources such as a compute cluster for AI/ML safety projects, a blog with in-depth examinations of AI safety topics, and a newsletter providing updates on AI safety developments. CAIS focuses on technical and conceptual research to address the risks posed by advanced AI systems.

Prompt Engineering is a discipline focused on developing and optimizing prompts to efficiently utilize language models (LMs) for various applications and research topics. It involves skills to understand the capabilities and limitations of large language models, improving their performance on tasks like question answering and arithmetic reasoning. Prompt engineering is essential for designing robust prompting techniques that interact with LLMs and other tools, enhancing safety and building new capabilities by augmenting LLMs with domain knowledge and external tools.

Search&AI is a comprehensive platform designed for patent due diligence, offering efficient and accurate results in minutes. It provides services such as prior art search, claim chart generation, novelty diligence analysis, portfolio analysis, document search, and AI-powered chatbot assistance. The platform is built by a team of experienced engineers and is tailored to streamline the patent discovery and analysis process, saving time and money compared to traditional outsourced search firms.

Neuralful AI is an innovative AI tool developed by Neuralfulai Ltd. It offers a wide range of AI solutions to cater to various needs. The tool is designed to provide advanced AI capabilities to users across different industries, helping them streamline processes, make data-driven decisions, and enhance overall efficiency. With Neuralful AI, users can leverage cutting-edge technology to unlock new possibilities and drive innovation in their respective fields.

OpenAI Strawberry Model is a cutting-edge AI initiative that represents a significant leap in AI capabilities, focusing on enhancing reasoning, problem-solving, and complex task execution. It aims to improve AI's ability to handle mathematical problems, programming tasks, and deep research, including long-term planning and action. The project showcases advancements in AI safety and aims to reduce errors in AI responses by generating high-quality synthetic data for training future models. Strawberry is designed to achieve human-like reasoning and is expected to play a crucial role in the development of OpenAI's next major model, codenamed 'Orion.'

Portkey is a monitoring and improvement tool for Gen AI apps, helping teams enhance cost, performance, and accuracy. It integrates quickly, monitors LLM requests, and boosts app resilience, security, performance, and accuracy. The tool offers a product walkthrough and easy integration with OpenAI Python and Node libraries.

Bay Area AI is a technical AI meetup group based in San Francisco, CA, consisting of startup engineers, research scientists, computational linguists, mathematicians, and philosophers. The group focuses on understanding the meaning of text, reasoning, and human intent through technology to build new businesses and enhance the human experience in the modern connected world. They work on building systems with Machine Learning on top of Data Pipelines, exploring open-source solutions, and modeling human behavior in industry for practical results.

Flow AI is an advanced AI tool designed for evaluating and improving Large Language Model (LLM) applications. It offers a unique system for creating custom evaluators, deploying them with an API, and developing specialized LMs tailored to specific use cases. The tool aims to revolutionize AI evaluation and model development by providing transparent, cost-effective, and controllable solutions for AI teams across various domains.

Every AI is an AI software that offers over 120 AI models, including ChatGPT from OpenAI and Anthropic/Claude, for a wide range of applications. It provides incredible speeds and access to all models for a subscription fee of $20. The platform aims to simplify AI development at scale by offering developer-friendly solutions with extensive documentation and SDKs for popular programming languages like Ruby and JavaScript.

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.

The llama-recipes repository provides a scalable library for fine-tuning Llama 2, along with example scripts and notebooks to quickly get started with using the Llama 2 models in a variety of use-cases, including fine-tuning for domain adaptation and building LLM-based applications with Llama 2 and other tools in the LLM ecosystem. The examples here showcase how to run Llama 2 locally, in the cloud, and on-prem.

This prototype synthesizes verified code with an LLM using Monte Carlo Tree Search (MCTS). It explores the space of possible generation of a verified program and checks at every step that it's on the right track by calling the verifier. This prototype uses Dafny, Coq, Lean, Scala, or Rust. By using this technique, weaker models that might not even know the generated language all that well can compete with stronger models.

Ray is a unified framework for scaling AI and Python applications. It consists of a core distributed runtime and a set of AI libraries for simplifying ML compute, including Data, Train, Tune, RLlib, and Serve. Ray runs on any machine, cluster, cloud provider, and Kubernetes, and features a growing ecosystem of community integrations. With Ray, you can seamlessly scale the same code from a laptop to a cluster, making it easy to meet the compute-intensive demands of modern ML workloads.

Jupyter AI connects generative AI with Jupyter notebooks. It provides a user-friendly and powerful way to explore generative AI models in notebooks and improve your productivity in JupyterLab and the Jupyter Notebook. Specifically, Jupyter AI offers: * An `%%ai` magic that turns the Jupyter notebook into a reproducible generative AI playground. This works anywhere the IPython kernel runs (JupyterLab, Jupyter Notebook, Google Colab, Kaggle, VSCode, etc.). * A native chat UI in JupyterLab that enables you to work with generative AI as a conversational assistant. * Support for a wide range of generative model providers, including AI21, Anthropic, AWS, Cohere, Gemini, Hugging Face, NVIDIA, and OpenAI. * Local model support through GPT4All, enabling use of generative AI models on consumer grade machines with ease and privacy.

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

**Prompt flow** is a suite of development tools designed to streamline the end-to-end development cycle of LLM-based AI applications, from ideation, prototyping, testing, evaluation to production deployment and monitoring. It makes prompt engineering much easier and enables you to build LLM apps with production quality.

Metaflow is a user-friendly library designed to assist scientists and engineers in developing and managing real-world data science projects. Initially created at Netflix, Metaflow aimed to enhance the productivity of data scientists working on diverse projects ranging from traditional statistics to cutting-edge deep learning. For further information, refer to Metaflow's website and documentation.

MLflow is a platform to streamline machine learning development, including tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow offers a set of lightweight APIs that can be used with any existing machine learning application or library (TensorFlow, PyTorch, XGBoost, etc), wherever you currently run ML code (e.g. in notebooks, standalone applications or the cloud). MLflow's current components are: * `MLflow Tracking `_: An API to log parameters, code, and results in machine learning experiments and compare them using an interactive UI. * `MLflow Projects `_: A code packaging format for reproducible runs using Conda and Docker, so you can share your ML code with others. * `MLflow Models `_: A model packaging format and tools that let you easily deploy the same model (from any ML library) to batch and real-time scoring on platforms such as Docker, Apache Spark, Azure ML and AWS SageMaker. * `MLflow Model Registry `_: A centralized model store, set of APIs, and UI, to collaboratively manage the full lifecycle of MLflow Models.

Mojo is a new programming language that bridges the gap between research and production by combining Python syntax and ecosystem with systems programming and metaprogramming features. Mojo is still young, but it is designed to become a superset of Python over time.

TypeChat is a library that simplifies the creation of natural language interfaces using types. Traditionally, building natural language interfaces has been challenging, often relying on complex decision trees to determine intent and gather necessary inputs for action. Large language models (LLMs) have simplified this process by allowing us to accept natural language input from users and match it to intent. However, this has introduced new challenges, such as the need to constrain the model's response for safety, structure responses from the model for further processing, and ensure the validity of the model's response. Prompt engineering aims to address these issues, but it comes with a steep learning curve and increased fragility as the prompt grows in size.

Langfun is a Python library that aims to make language models (LM) fun to work with. It enables a programming model that flows naturally, resembling the human thought process. Langfun emphasizes the reuse and combination of language pieces to form prompts, thereby accelerating innovation. Unlike other LM frameworks, which feed program-generated data into the LM, langfun takes a distinct approach: It starts with natural language, allowing for seamless interactions between language and program logic, and concludes with natural language and optional structured output. Consequently, langfun can aptly be described as Language as functions, capturing the core of its methodology.

vLLM is a fast and easy-to-use library for LLM inference and serving. It is designed to be efficient, flexible, and easy to use. vLLM can be used to serve a variety of LLM models, including Hugging Face models. It supports a variety of decoding algorithms, including parallel sampling, beam search, and more. vLLM also supports tensor parallelism for distributed inference and streaming outputs. It is open-source and available on GitHub.

Gorilla is a tool that enables LLMs to use tools by invoking APIs. Given a natural language query, Gorilla comes up with the semantically- and syntactically- correct API to invoke. With Gorilla, you can use LLMs to invoke 1,600+ (and growing) API calls accurately while reducing hallucination. Gorilla also releases APIBench, the largest collection of APIs, curated and easy to be trained on!

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.

Torchtune is a PyTorch-native library for easily authoring, fine-tuning, and experimenting with LLMs. It provides native-PyTorch implementations of popular LLMs using composable and modular building blocks, easy-to-use and hackable training recipes for popular fine-tuning techniques, YAML configs for easily configuring training, evaluation, quantization, or inference recipes, and built-in support for many popular dataset formats and prompt templates to help you quickly get started with training.

TruLens provides a set of tools for developing and monitoring neural nets, including large language models. This includes both tools for evaluation of LLMs and LLM-based applications with _TruLens-Eval_ and deep learning explainability with _TruLens-Explain_. _TruLens-Eval_ and _TruLens-Explain_ are housed in separate packages and can be used independently.

TT-NN is a python & C++ Neural Network OP library. It provides a low-level programming model, TT-Metalium, enabling kernel development for Tenstorrent hardware.

PEFT (Parameter-Efficient Fine-Tuning) is a collection of state-of-the-art methods that enable efficient adaptation of large pretrained models to various downstream applications. By only fine-tuning a small number of extra model parameters instead of all the model's parameters, PEFT significantly decreases the computational and storage costs while achieving performance comparable to fully fine-tuned models.

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

FlashInfer is a library for Language Languages Models that provides high-performance implementation of LLM GPU kernels such as FlashAttention, PageAttention and LoRA. FlashInfer focus on LLM serving and inference, and delivers state-the-art performance across diverse scenarios.

MaxText is a high-performance, highly scalable, open-source LLM written in pure Python/Jax and targeting Google Cloud TPUs and GPUs for training and inference. MaxText achieves high MFUs and scales from single host to very large clusters while staying simple and "optimization-free" thanks to the power of Jax and the XLA compiler. MaxText aims to be a launching off point for ambitious LLM projects both in research and production. We encourage users to start by experimenting with MaxText out of the box and then fork and modify MaxText to meet their needs.

llama.cpp is a C++ implementation of LLaMA, a large language model from Meta. It provides a command-line interface for inference and can be used for a variety of tasks, including text generation, translation, and question answering. llama.cpp is highly optimized for performance and can be run on a variety of hardware, including CPUs, GPUs, and TPUs.

Scale's LLM Engine is an open-source Python library, CLI, and Helm chart that provides everything you need to serve and fine-tune foundation models, whether you use Scale's hosted infrastructure or do it in your own cloud infrastructure using Kubernetes.

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...).

This repository contains integrations to extend the capabilities of Haystack version 2.0 and onwards. The code in this repo is maintained by deepset, see each integration's `README` file for details around installation, usage and support.

GPT4All is an ecosystem to run powerful and customized large language models that work locally on consumer grade CPUs and any GPU. Note that your CPU needs to support AVX or AVX2 instructions. Learn more in the documentation. A GPT4All model is a 3GB - 8GB file that you can download and plug into the GPT4All open-source ecosystem software. Nomic AI supports and maintains this software ecosystem to enforce quality and security alongside spearheading the effort to allow any person or enterprise to easily train and deploy their own on-edge large language models.

Deep Lake is a Database for AI powered by a storage format optimized for deep-learning applications. Deep Lake can be used for: 1. Storing data and vectors while building LLM applications 2. Managing datasets while training deep learning models Deep Lake simplifies the deployment of enterprise-grade LLM-based products by offering storage for all data types (embeddings, audio, text, videos, images, pdfs, annotations, etc.), querying and vector search, data streaming while training models at scale, data versioning and lineage, and integrations with popular tools such as LangChain, LlamaIndex, Weights & Biases, and many more. Deep Lake works with data of any size, it is serverless, and it enables you to store all of your data in your own cloud and in one place. Deep Lake is used by Intel, Bayer Radiology, Matterport, ZERO Systems, Red Cross, Yale, & Oxford.

This repository contains projects and notes on common practical techniques for fine-tuning Large Language Models (LLMs). It includes fine-tuning LLM notebooks, Colab links, LLM techniques and utils, and other smaller language models. The repository also provides links to YouTube videos explaining the concepts and techniques discussed in the notebooks.

LLoCO is a technique that learns documents offline through context compression and in-domain parameter-efficient finetuning using LoRA, which enables LLMs to handle long context efficiently.

CAMEL is an open-source library designed for the study of autonomous and communicative agents. We believe that studying these agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks. To facilitate research in this field, we implement and support various types of agents, tasks, prompts, models, and simulated environments.

This repository provides a collection of interview questions and answers for algorithm engineers. The questions are organized by topic, and each question includes a detailed explanation of the answer. This repository is a valuable resource for anyone preparing for an algorithm engineering interview.

FastTrackML is an experiment tracking server focused on speed and scalability, fully compatible with MLFlow. It provides a user-friendly interface to track and visualize your machine learning experiments, making it easy to compare different models and identify the best performing ones. FastTrackML is open source and can be easily installed and run with pip or Docker. It is also compatible with the MLFlow Python package, making it easy to integrate with your existing MLFlow workflows.

Collective Mind (CM) is a collection of portable, extensible, technology-agnostic and ready-to-use automation recipes with a human-friendly interface (aka CM scripts) to unify and automate all the manual steps required to compose, run, benchmark and optimize complex ML/AI applications on any platform with any software and hardware: see online catalog and source code. CM scripts require Python 3.7+ with minimal dependencies and are continuously extended by the community and MLCommons members to run natively on Ubuntu, MacOS, Windows, RHEL, Debian, Amazon Linux and any other operating system, in a cloud or inside automatically generated containers while keeping backward compatibility - please don't hesitate to report encountered issues here and contact us via public Discord Server to help this collaborative engineering effort! CM scripts were originally developed based on the following requirements from the MLCommons members to help them automatically compose and optimize complex MLPerf benchmarks, applications and systems across diverse and continuously changing models, data sets, software and hardware from Nvidia, Intel, AMD, Google, Qualcomm, Amazon and other vendors: * must work out of the box with the default options and without the need to edit some paths, environment variables and configuration files; * must be non-intrusive, easy to debug and must reuse existing user scripts and automation tools (such as cmake, make, ML workflows, python poetry and containers) rather than substituting them; * must have a very simple and human-friendly command line with a Python API and minimal dependencies; * must require minimal or zero learning curve by using plain Python, native scripts, environment variables and simple JSON/YAML descriptions instead of inventing new workflow languages; * must have the same interface to run all automations natively, in a cloud or inside containers. CM scripts were successfully validated by MLCommons to modularize MLPerf inference benchmarks and help the community automate more than 95% of all performance and power submissions in the v3.1 round across more than 120 system configurations (models, frameworks, hardware) while reducing development and maintenance costs.

LLaMA Factory is a unified framework for fine-tuning 100+ large language models (LLMs) with various methods, including pre-training, supervised fine-tuning, reward modeling, PPO, DPO and ORPO. It features integrated algorithms like GaLore, BAdam, DoRA, LongLoRA, LLaMA Pro, LoRA+, LoftQ and Agent tuning, as well as practical tricks like FlashAttention-2, Unsloth, RoPE scaling, NEFTune and rsLoRA. LLaMA Factory provides experiment monitors like LlamaBoard, TensorBoard, Wandb, MLflow, etc., and supports faster inference with OpenAI-style API, Gradio UI and CLI with vLLM worker. Compared to ChatGLM's P-Tuning, LLaMA Factory's LoRA tuning offers up to 3.7 times faster training speed with a better Rouge score on the advertising text generation task. By leveraging 4-bit quantization technique, LLaMA Factory's QLoRA further improves the efficiency regarding the GPU memory.

AIDE is a machine learning code generation agent that can generate solutions for machine learning tasks from natural language descriptions. It has the following features: 1. **Instruct with Natural Language**: Describe your problem or additional requirements and expert insights, all in natural language. 2. **Deliver Solution in Source Code**: AIDE will generate Python scripts for the **tested** machine learning pipeline. Enjoy full transparency, reproducibility, and the freedom to further improve the source code! 3. **Iterative Optimization**: AIDE iteratively runs, debugs, evaluates, and improves the ML code, all by itself. 4. **Visualization**: We also provide tools to visualize the solution tree produced by AIDE for a better understanding of its experimentation process. This gives you insights not only about what works but also what doesn't. AIDE has been benchmarked on over 60 Kaggle data science competitions and has demonstrated impressive performance, surpassing 50% of Kaggle participants on average. It is particularly well-suited for tasks that require complex data preprocessing, feature engineering, and model selection.

The Google AI Python SDK is the easiest way for Python developers to build with the Gemini API. The Gemini API gives you access to Gemini models created by Google DeepMind. Gemini models are built from the ground up to be multimodal, so you can reason seamlessly across text, images, and code.

Milvus is an open-source vector database built to power embedding similarity search and AI applications. Milvus makes unstructured data search more accessible, and provides a consistent user experience regardless of the deployment environment. Milvus 2.0 is a cloud-native vector database with storage and computation separated by design. All components in this refactored version of Milvus are stateless to enhance elasticity and flexibility. For more architecture details, see Milvus Architecture Overview. Milvus was released under the open-source Apache License 2.0 in October 2019. It is currently a graduate project under LF AI & Data Foundation.

AiiDA (www.aiida.net) is a workflow manager for computational science with a strong focus on provenance, performance and extensibility. **Features** * **Workflows:** Write complex, auto-documenting workflows in python, linked to arbitrary executables on local and remote computers. The event-based workflow engine supports tens of thousands of processes per hour with full checkpointing. * **Data provenance:** Automatically track inputs, outputs & metadata of all calculations in a provenance graph for full reproducibility. Perform fast queries on graphs containing millions of nodes. * **HPC interface:** Move your calculations to a different computer by changing one line of code. AiiDA is compatible with schedulers like SLURM, PBS Pro, torque, SGE or LSF out of the box. * **Plugin interface:** Extend AiiDA with plugins for new simulation codes (input generation & parsing), data types, schedulers, transport modes and more. * **Open Science:** Export subsets of your provenance graph and share them with peers or make them available online for everyone on the Materials Cloud. * **Open source:** AiiDA is released under the MIT open source license

Indexify is an open-source engine for building fast data pipelines for unstructured data (video, audio, images, and documents) using reusable extractors for embedding, transformation, and feature extraction. LLM Applications can query transformed content friendly to LLMs by semantic search and SQL queries. Indexify keeps vector databases and structured databases (PostgreSQL) updated by automatically invoking the pipelines as new data is ingested into the system from external data sources. **Why use Indexify** * Makes Unstructured Data **Queryable** with **SQL** and **Semantic Search** * **Real-Time** Extraction Engine to keep indexes **automatically** updated as new data is ingested. * Create **Extraction Graph** to describe **data transformation** and extraction of **embedding** and **structured extraction**. * **Incremental Extraction** and **Selective Deletion** when content is deleted or updated. * **Extractor SDK** allows adding new extraction capabilities, and many readily available extractors for **PDF**, **Image**, and **Video** indexing and extraction. * Works with **any LLM Framework** including **Langchain**, **DSPy**, etc. * Runs on your laptop during **prototyping** and also scales to **1000s of machines** on the cloud. * Works with many **Blob Stores**, **Vector Stores**, and **Structured Databases** * We have even **Open Sourced Automation** to deploy to Kubernetes in production.

LLM-baselines is a modular codebase to experiment with transformers, inspired from NanoGPT. It provides a quick and easy way to train and evaluate transformer models on a variety of datasets. The codebase is well-documented and easy to use, making it a great resource for researchers and practitioners alike.

The ByteIR Project is a ByteDance model compilation solution. ByteIR includes compiler, runtime, and frontends, and provides an end-to-end model compilation solution. Although all ByteIR components (compiler/runtime/frontends) are together to provide an end-to-end solution, and all under the same umbrella of this repository, each component technically can perform independently. The name, ByteIR, comes from a legacy purpose internally. The ByteIR project is NOT an IR spec definition project. Instead, in most scenarios, ByteIR directly uses several upstream MLIR dialects and Google Mhlo. Most of ByteIR compiler passes are compatible with the selected upstream MLIR dialects and Google Mhlo.

ScandEval is a framework for evaluating pretrained language models on mono- or multilingual language tasks. It provides a unified interface for benchmarking models on a variety of tasks, including sentiment analysis, question answering, and machine translation. ScandEval is designed to be easy to use and extensible, making it a valuable tool for researchers and practitioners alike.

Lance is a modern columnar data format optimized for ML workflows and datasets. It offers high-performance random access, vector search, zero-copy automatic versioning, and ecosystem integrations with Apache Arrow, Pandas, Polars, and DuckDB. Lance is designed to address the challenges of the ML development cycle, providing a unified data format for collection, exploration, analytics, feature engineering, training, evaluation, deployment, and monitoring. It aims to reduce data silos and streamline the ML development process.

Evals provide a framework for evaluating large language models (LLMs) or systems built using LLMs. We offer an existing registry of evals to test different dimensions of OpenAI models and the ability to write your own custom evals for use cases you care about. You can also use your data to build private evals which represent the common LLMs patterns in your workflow without exposing any of that data publicly.

Empirical is a tool that allows you to test different LLMs, prompts, and other model configurations across all the scenarios that matter for your application. With Empirical, you can run your test datasets locally against off-the-shelf models, test your own custom models and RAG applications, view, compare, and analyze outputs on a web UI, score your outputs with scoring functions, and run tests on CI/CD.

Eidolon is an open-source agent services framework that helps developers design and deploy agent-based services. It simplifies agent deployment, facilitates agent-to-agent communication, and enables painless component customization and upgrades. Eidolon's modular architecture allows developers to easily swap out components, such as language models, reinforcement learning implementations, tools, and more. This flexibility minimizes vendor lock-in and reduces the effort required to upgrade agent components. As the AI landscape rapidly evolves, Eidolon empowers developers to adapt their agents to meet changing requirements.

KG-RAG (Knowledge Graph-based Retrieval Augmented Generation) is a task agnostic framework that combines the explicit knowledge of a Knowledge Graph (KG) with the implicit knowledge of a Large Language Model (LLM). KG-RAG extracts "prompt-aware context" from a KG, which is defined as the minimal context sufficient enough to respond to the user prompt. This framework empowers a general-purpose LLM by incorporating an optimized domain-specific 'prompt-aware context' from a biomedical KG. KG-RAG is specifically designed for running prompts related to Diseases.

LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrieval, filtering, and management of embeddings. The key features of LanceDB include: Production-scale vector search with no servers to manage. Store, query, and filter vectors, metadata, and multi-modal data (text, images, videos, point clouds, and more). Support for vector similarity search, full-text search, and SQL. Native Python and Javascript/Typescript support. Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure. GPU support in building vector index(*). Ecosystem integrations with LangChain 🦜️🔗, LlamaIndex 🦙, Apache-Arrow, Pandas, Polars, DuckDB, and more on the way. LanceDB's core is written in Rust 🦀 and is built using Lance, an open-source columnar format designed for performant ML workloads.

MMStar is an elite vision-indispensable multi-modal benchmark comprising 1,500 challenge samples meticulously selected by humans. It addresses two key issues in current LLM evaluation: the unnecessary use of visual content in many samples and the existence of unintentional data leakage in LLM and LVLM training. MMStar evaluates 6 core capabilities across 18 detailed axes, ensuring a balanced distribution of samples across all dimensions.

Pai-Megatron-Patch is a deep learning training toolkit built for developers to train and predict LLMs & VLMs by using Megatron framework easily. With the continuous development of LLMs, the model structure and scale are rapidly evolving. Although these models can be conveniently manufactured using Transformers or DeepSpeed training framework, the training efficiency is comparably low. This phenomenon becomes even severer when the model scale exceeds 10 billion. The primary objective of Pai-Megatron-Patch is to effectively utilize the computational power of GPUs for LLM. This tool allows convenient training of commonly used LLM with all the accelerating techniques provided by Megatron-LM.

RAFT (Reusable Accelerated Functions and Tools) is a C++ header-only template library with an optional shared library that contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

Welcome to the μLearn x Pathway Initiative, an exciting adventure into the world of Artificial Intelligence (AI)! This comprehensive course, developed in collaboration with Pathway, will empower you with the knowledge and skills needed to navigate the fascinating world of AI, with a special focus on Large Language Models (LLMs).

L3AGI is an open-source tool that enables AI Assistants to collaborate together as effectively as human teams. It provides a robust set of functionalities that empower users to design, supervise, and execute both autonomous AI Assistants and Teams of Assistants. Key features include the ability to create and manage Teams of AI Assistants, design and oversee standalone AI Assistants, equip AI Assistants with the ability to retain and recall information, connect AI Assistants to an array of data sources for efficient information retrieval and processing, and employ curated sets of tools for specific tasks. L3AGI also offers a user-friendly interface, APIs for integration with other systems, and a vibrant community for support and collaboration.

This repository contains Jupyter-based tutorials for NLP, ML, AI in Python for classes in Computational Linguistics, Natural Language Processing (NLP), Machine Learning (ML), and Artificial Intelligence (AI) at Indiana University.

Flower is a framework for building federated learning systems. It is designed to be customizable, extensible, framework-agnostic, and understandable. Flower can be used with any machine learning framework, for example, PyTorch, TensorFlow, Hugging Face Transformers, PyTorch Lightning, scikit-learn, JAX, TFLite, MONAI, fastai, MLX, XGBoost, Pandas for federated analytics, or even raw NumPy for users who enjoy computing gradients by hand.

Analyze the following text from a github repository (name and readme text at end) . Then, generate a JSON object with the following keys and provide the corresponding information for each key, in lowercase letters: 'description' (detailed description of the repo, must be less than 400 words，Ensure that no line breaks and quotation marks.),'for_jobs' (List 5 jobs suitable for this tool,in lowercase letters), 'ai_keywords' (keywords of the tool,user may use those keyword to find the tool,in lowercase letters), 'for_tasks' (list of 5 specific tasks user can use this tool to do,in lowercase letters), 'answer' (in english languages)

LeapfrogAI is a self-hosted AI platform designed to be deployed in air-gapped resource-constrained environments. It brings sophisticated AI solutions to these environments by hosting all the necessary components of an AI stack, including vector databases, model backends, API, and UI. LeapfrogAI's API closely matches that of OpenAI, allowing tools built for OpenAI/ChatGPT to function seamlessly with a LeapfrogAI backend. It provides several backends for various use cases, including llama-cpp-python, whisper, text-embeddings, and vllm. LeapfrogAI leverages Chainguard's apko to harden base python images, ensuring the latest supported Python versions are used by the other components of the stack. The LeapfrogAI SDK provides a standard set of protobuffs and python utilities for implementing backends and gRPC. LeapfrogAI offers UI options for common use-cases like chat, summarization, and transcription. It can be deployed and run locally via UDS and Kubernetes, built out using Zarf packages. LeapfrogAI is supported by a community of users and contributors, including Defense Unicorns, Beast Code, Chainguard, Exovera, Hypergiant, Pulze, SOSi, United States Navy, United States Air Force, and United States Space Force.

EvalAI is an open-source platform for evaluating and comparing machine learning (ML) and artificial intelligence (AI) algorithms at scale. It provides a central leaderboard and submission interface, making it easier for researchers to reproduce results mentioned in papers and perform reliable & accurate quantitative analysis. EvalAI also offers features such as custom evaluation protocols and phases, remote evaluation, evaluation inside environments, CLI support, portability, and faster evaluation.

TorchRL is an open-source Reinforcement Learning (RL) library for PyTorch. It provides pytorch and **python-first** , low and high level abstractions for RL that are intended to be **efficient** , **modular** , **documented** and properly **tested**. The code is aimed at supporting research in RL. Most of it is written in python in a highly modular way, such that researchers can easily swap components, transform them or write new ones with little effort.

AGiXT is a dynamic Artificial Intelligence Automation Platform engineered to orchestrate efficient AI instruction management and task execution across a multitude of providers. Our solution infuses adaptive memory handling with a broad spectrum of commands to enhance AI's understanding and responsiveness, leading to improved task completion. The platform's smart features, like Smart Instruct and Smart Chat, seamlessly integrate web search, planning strategies, and conversation continuity, transforming the interaction between users and AI. By leveraging a powerful plugin system that includes web browsing and command execution, AGiXT stands as a versatile bridge between AI models and users. With an expanding roster of AI providers, code evaluation capabilities, comprehensive chain management, and platform interoperability, AGiXT is consistently evolving to drive a multitude of applications, affirming its place at the forefront of AI technology.

LangCorn is an API server that enables you to serve LangChain models and pipelines with ease, leveraging the power of FastAPI for a robust and efficient experience. It offers features such as easy deployment of LangChain models and pipelines, ready-to-use authentication functionality, high-performance FastAPI framework for serving requests, scalability and robustness for language processing applications, support for custom pipelines and processing, well-documented RESTful API endpoints, and asynchronous processing for faster response times.

Chatbook is a paclet that adds support for LLM-powered notebooks to Wolfram. It allows users to interact with ChatGPT and generate immediately evaluatable Wolfram code. The code can be evaluated in place immediately, making it easy to explore and experiment with ideas.

Termax is an LLM agent in your terminal that converts natural language to commands. It is featured by: - Personalized Experience: Optimize the command generation with RAG. - Various LLMs Support: OpenAI GPT, Anthropic Claude, Google Gemini, Mistral AI, and more. - Shell Extensions: Plugin with popular shells like `zsh`, `bash` and `fish`. - Cross Platform: Able to run on Windows, macOS, and Linux.

A package to help benchmark various LLM related tasks. The benchmarks are organized by end-to-end use cases, and utilize LangSmith heavily. We have several goals in open sourcing this: * Showing how we collect our benchmark datasets for each task * Showing what the benchmark datasets we use for each task is * Showing how we evaluate each task * Encouraging others to benchmark their solutions on these tasks (we are always looking for better ways of doing things!)

This repository contains a curated list of **papers using Large Language/Multi-Modal Models for Robotics/RL**. Template from awesome-Implicit-NeRF-Robotics Please feel free to send me pull requests or email to add papers! If you find this repository useful, please consider citing and STARing this list. Feel free to share this list with others! ## Overview * Surveys * Reasoning * Planning * Manipulation * Instructions and Navigation * Simulation Frameworks * Citation

This repository contains code for research conducted by the LLM-Random research group at IDEAS NCBR in Warsaw, Poland. The group focuses on developing and using this repository to conduct research. For more information about the group and its research, refer to their blog, llm-random.github.io.

VectorHub is a free and open-sourced learning hub for people interested in adding vector retrieval to their ML stack. On VectorHub you will find practical resources to help you create MVPs with easy-to-follow learning materials, solve use case specific challenges in vector retrieval, get confident in taking their MVPs to production and making them actually useful, and learn about vendors in the space and select the ones that fit their use-case.

The Qianfan SDK provides best practices for large model toolchains, allowing AI workflows and AI-native applications to access the Qianfan large model platform elegantly and conveniently. The core capabilities of the SDK include three parts: large model reasoning, large model training, and general and extension: * `Large model reasoning`: Implements interface encapsulation for reasoning of Yuyan (ERNIE-Bot) series, open source large models, etc., supporting dialogue, completion, Embedding, etc. * `Large model training`: Based on platform capabilities, it supports end-to-end large model training process, including training data, fine-tuning/pre-training, and model services. * `General and extension`: General capabilities include common AI development tools such as Prompt/Debug/Client. The extension capability is based on the characteristics of Qianfan to adapt to common middleware frameworks.

CometLLM is a tool to log and visualize your LLM prompts and chains. Use CometLLM to identify effective prompt strategies, streamline your troubleshooting, and ensure reproducible workflows!

skpro is a library for supervised probabilistic prediction in python. It provides `scikit-learn`-like, `scikit-base` compatible interfaces to: * tabular **supervised regressors for probabilistic prediction** \- interval, quantile and distribution predictions * tabular **probabilistic time-to-event and survival prediction** \- instance-individual survival distributions * **metrics to evaluate probabilistic predictions** , e.g., pinball loss, empirical coverage, CRPS, survival losses * **reductions** to turn `scikit-learn` regressors into probabilistic `skpro` regressors, such as bootstrap or conformal * building **pipelines and composite models** , including tuning via probabilistic performance metrics * symbolic **probability distributions** with value domain of `pandas.DataFrame`-s and `pandas`-like interface

RecAI is a project that explores the integration of Large Language Models (LLMs) into recommender systems, addressing the challenges of interactivity, explainability, and controllability. It aims to bridge the gap between general-purpose LLMs and domain-specific recommender systems, providing a holistic perspective on the practical requirements of LLM4Rec. The project investigates various techniques, including Recommender AI agents, selective knowledge injection, fine-tuning language models, evaluation, and LLMs as model explainers, to create more sophisticated, interactive, and user-centric recommender systems.

llama_cpp.rb provides Ruby bindings for the llama.cpp, a library that allows you to use the Llama language model in your Ruby applications. Llama is a large language model that can be used for a variety of natural language processing tasks, such as text generation, translation, and question answering. This gem is still under development and may undergo many changes in the future.

This Docker image for LLaVA (Large Language and Vision Assistant) provides a convenient way to run LLaVA locally or on RunPod. LLaVA is a powerful AI tool that combines natural language processing and computer vision capabilities. With this Docker image, you can easily access LLaVA's functionalities for various tasks, including image captioning, visual question answering, text summarization, and more. The image comes pre-installed with LLaVA v1.2.0, Torch 2.1.2, xformers 0.0.23.post1, and other necessary dependencies. You can customize the model used by setting the MODEL environment variable. The image also includes a Jupyter Lab environment for interactive development and exploration. Overall, this Docker image offers a comprehensive and user-friendly platform for leveraging LLaVA's capabilities.

Cleanlab helps you **clean** data and **lab** els by automatically detecting issues in a ML dataset. To facilitate **machine learning with messy, real-world data** , this data-centric AI package uses your _existing_ models to estimate dataset problems that can be fixed to train even _better_ models.

This sample demonstrates a few approaches for creating ChatGPT-like experiences over your own data using the Retrieval Augmented Generation pattern. It uses Azure OpenAI Service to access a GPT model (gpt-35-turbo), and Azure AI Search for data indexing and retrieval. The repo includes sample data so it's ready to try end to end. In this sample application we use a fictitious company called Contoso Electronics, and the experience allows its employees to ask questions about the benefits, internal policies, as well as job descriptions and roles.

Kubeflow Training Operator is a Kubernetes-native project for fine-tuning and scalable distributed training of machine learning (ML) models created with various ML frameworks such as PyTorch, Tensorflow, XGBoost, MPI, Paddle and others. Training Operator allows you to use Kubernetes workloads to effectively train your large models via Kubernetes Custom Resources APIs or using Training Operator Python SDK. > Note: Before v1.2 release, Kubeflow Training Operator only supports TFJob on Kubernetes. * For a complete reference of the custom resource definitions, please refer to the API Definition. * TensorFlow API Definition * PyTorch API Definition * Apache MXNet API Definition * XGBoost API Definition * MPI API Definition * PaddlePaddle API Definition * For details of all-in-one operator design, please refer to the All-in-one Kubeflow Training Operator * For details on its observability, please refer to the monitoring design doc.

Katib is a Kubernetes-native project for automated machine learning (AutoML). Katib supports Hyperparameter Tuning, Early Stopping and Neural Architecture Search. Katib is the project which is agnostic to machine learning (ML) frameworks. It can tune hyperparameters of applications written in any language of the users’ choice and natively supports many ML frameworks, such as TensorFlow, Apache MXNet, PyTorch, XGBoost, and others. Katib can perform training jobs using any Kubernetes Custom Resources with out of the box support for Kubeflow Training Operator, Argo Workflows, Tekton Pipelines and many more.

Cog is an open-source tool that lets you package machine learning models in a standard, production-ready container. You can deploy your packaged model to your own infrastructure, or to Replicate.

Thinc is a lightweight deep learning library that offers an elegant, type-checked, functional-programming API for composing models, with support for layers defined in other frameworks such as PyTorch, TensorFlow and MXNet. You can use Thinc as an interface layer, a standalone toolkit or a flexible way to develop new models.

AIOS, a Large Language Model (LLM) Agent operating system, embeds large language model into Operating Systems (OS) as the brain of the OS, enabling an operating system "with soul" -- an important step towards AGI. AIOS is designed to optimize resource allocation, facilitate context switch across agents, enable concurrent execution of agents, provide tool service for agents, maintain access control for agents, and provide a rich set of toolkits for LLM Agent developers.

This repository contains sample code demonstrating various use cases leveraging Amazon Bedrock and Generative AI. Each sample is a separate project with its own directory, and includes a basic Streamlit frontend to help users quickly set up a proof of concept.

The LLM course is divided into three parts: 1. 🧩 **LLM Fundamentals** covers essential knowledge about mathematics, Python, and neural networks. 2. 🧑‍🔬 **The LLM Scientist** focuses on building the best possible LLMs using the latest techniques. 3. 👷 **The LLM Engineer** focuses on creating LLM-based applications and deploying them. For an interactive version of this course, I created two **LLM assistants** that will answer questions and test your knowledge in a personalized way: * 🤗 **HuggingChat Assistant**: Free version using Mixtral-8x7B. * 🤖 **ChatGPT Assistant**: Requires a premium account. ## 📝 Notebooks A list of notebooks and articles related to large language models. ### Tools | Notebook | Description | Notebook | |----------|-------------|----------| | 🧐 LLM AutoEval | Automatically evaluate your LLMs using RunPod |  | | 🥱 LazyMergekit | Easily merge models using MergeKit in one click. |  | | 🦎 LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. |  | | ⚡ AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. |  | | 🌳 Model Family Tree | Visualize the family tree of merged models. |  | | 🚀 ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. |  |

OpenLLMetry is a set of extensions built on top of OpenTelemetry that gives you complete observability over your LLM application. Because it uses OpenTelemetry under the hood, it can be connected to your existing observability solutions - Datadog, Honeycomb, and others. It's built and maintained by Traceloop under the Apache 2.0 license. The repo contains standard OpenTelemetry instrumentations for LLM providers and Vector DBs, as well as a Traceloop SDK that makes it easy to get started with OpenLLMetry, while still outputting standard OpenTelemetry data that can be connected to your observability stack. If you already have OpenTelemetry instrumented, you can just add any of our instrumentations directly.

DBRX is a large language model trained by Databricks and made available under an open license. It is a Mixture-of-Experts (MoE) model with 132B total parameters and 36B live parameters, using 16 experts, of which 4 are active during training or inference. DBRX was pre-trained for 12T tokens of text and has a context length of 32K tokens. The model is available in two versions: a base model and an Instruct model, which is finetuned for instruction following. DBRX can be used for a variety of tasks, including text generation, question answering, summarization, and translation.

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome). It is designed to provide high performance and scalability for large language models, enabling efficient inference on cloud-based TPUs. JetStream leverages XLA to optimize the execution of LLM models, resulting in faster and more efficient inference. Additionally, JetStream supports quantization techniques to further enhance performance and reduce memory consumption. By utilizing JetStream, developers can deploy and run LLM models on TPUs with ease, achieving optimal performance and cost-effectiveness.

Large Language Models (LLM) are used to browse the Wolfram directory and associated URLs to create the category structure and good word embeddings. The goal is to generate enriched prompts for GPT, Wikipedia, Arxiv, Google Scholar, Stack Exchange, or Google search. The focus is on one subdirectory: Probability & Statistics. Documentation is in the project textbook `Projects4.pdf`, which is available in the folder. It is recommended to download the document and browse your local copy with Chrome, Edge, or other viewers. Unlike on GitHub, you will be able to click on all the links and follow the internal navigation features. Look for projects related to NLP and LLM / xLLM. The best starting point is project 7.2.2, which is the core project on this topic, with references to all satellite projects. The project textbook (with solutions to all projects) is the core document needed to participate in the free course (deep tech dive) called **GenAI Fellowship**. For details about the fellowship, follow the link provided. An uncompressed version of `crawl_final_stats.txt.gz` is available on Google drive, which contains all the crawled data needed as input to the Python scripts in the XLLM5 and XLLM6 folders.

Blockoli is a high-performance tool for code indexing, embedding generation, and semantic search tool for use with LLMs. It is built in Rust and uses the ASTerisk crate for semantic code parsing. Blockoli allows you to efficiently index, store, and search code blocks and their embeddings using vector similarity. Key features include indexing code blocks from a codebase, generating vector embeddings for code blocks using a pre-trained model, storing code blocks and their embeddings in a SQLite database, performing efficient similarity search on code blocks using vector embeddings, providing a REST API for easy integration with other tools and platforms, and being fast and memory-efficient due to its implementation in Rust.

This competition is organized by Javier Rando and Florian Tramèr from the ETH AI Center and SPY Lab at ETH Zurich. The goal of the competition is to create a method that can detect universal backdoors in aligned language models. A universal backdoor is a secret suffix that, when appended to any prompt, enables the model to answer harmful instructions. The competition provides a set of poisoned generation models, a reward model that measures how safe a completion is, and a dataset with prompts to run experiments. Participants are encouraged to use novel methods for red-teaming, automated approaches with low human oversight, and interpretability tools to find the trojans. The best submissions will be offered the chance to present their work at an event during the SaTML 2024 conference and may be invited to co-author a publication summarizing the competition results.

LLM Foundry is a codebase for training, finetuning, evaluating, and deploying LLMs for inference with Composer and the MosaicML platform. It is designed to be easy-to-use, efficient _and_ flexible, enabling rapid experimentation with the latest techniques. You'll find in this repo: * `llmfoundry/` - source code for models, datasets, callbacks, utilities, etc. * `scripts/` - scripts to run LLM workloads * `data_prep/` - convert text data from original sources to StreamingDataset format * `train/` - train or finetune HuggingFace and MPT models from 125M - 70B parameters * `train/benchmarking` - profile training throughput and MFU * `inference/` - convert models to HuggingFace or ONNX format, and generate responses * `inference/benchmarking` - profile inference latency and throughput * `eval/` - evaluate LLMs on academic (or custom) in-context-learning tasks * `mcli/` - launch any of these workloads using MCLI and the MosaicML platform * `TUTORIAL.md` - a deeper dive into the repo, example workflows, and FAQs

This project is a port of Andrej Karpathy's llm.c to Mojo, currently in beta. It is under active development and subject to changes. Users should expect to encounter bugs and unfinished features.

IPEX-LLM is a PyTorch library for running Large Language Models (LLMs) on Intel CPUs and GPUs with very low latency. It provides seamless integration with various LLM frameworks and tools, including llama.cpp, ollama, Text-Generation-WebUI, HuggingFace transformers, and more. IPEX-LLM has been optimized and verified on over 50 LLM models, including LLaMA, Mistral, Mixtral, Gemma, LLaVA, Whisper, ChatGLM, Baichuan, Qwen, and RWKV. It supports a range of low-bit inference formats, including INT4, FP8, FP4, INT8, INT2, FP16, and BF16, as well as finetuning capabilities for LoRA, QLoRA, DPO, QA-LoRA, and ReLoRA. IPEX-LLM is actively maintained and updated with new features and optimizations, making it a valuable tool for researchers, developers, and anyone interested in exploring and utilizing LLMs.

This repository provides a curated list of weekly published Large Language Model (LLM) papers. It includes top important LLM papers for each week, organized by month and year. The papers are categorized into different time periods, making it easy to find the most recent and relevant research in the field of LLM.

MINT benchmark aims to evaluate LLMs' ability to solve tasks with multi-turn interactions by (1) using tools and (2) leveraging natural language feedback.

Bench is a tool for evaluating LLMs for production use cases. It provides a standardized workflow for LLM evaluation with a common interface across tasks and use cases. Bench can be used to test whether open source LLMs can do as well as the top closed-source LLM API providers on specific data, and to translate the rankings on LLM leaderboards and benchmarks into scores that are relevant for actual use cases.

Ragas is a framework that helps you evaluate your Retrieval Augmented Generation (RAG) pipelines. RAG denotes a class of LLM applications that use external data to augment the LLM’s context. There are existing tools and frameworks that help you build these pipelines but evaluating it and quantifying your pipeline performance can be hard. This is where Ragas (RAG Assessment) comes in. Ragas provides you with the tools based on the latest research for evaluating LLM-generated text to give you insights about your RAG pipeline. Ragas can be integrated with your CI/CD to provide continuous checks to ensure performance.

ModelFusion is an abstraction layer for integrating AI models into JavaScript and TypeScript applications, unifying the API for common operations such as text streaming, object generation, and tool usage. It provides features to support production environments, including observability hooks, logging, and automatic retries. You can use ModelFusion to build AI applications, chatbots, and agents. ModelFusion is a non-commercial open source project that is community-driven. You can use it with any supported provider. ModelFusion supports a wide range of models including text generation, image generation, vision, text-to-speech, speech-to-text, and embedding models. ModelFusion infers TypeScript types wherever possible and validates model responses. ModelFusion provides an observer framework and logging support. ModelFusion ensures seamless operation through automatic retries, throttling, and error handling mechanisms. ModelFusion is fully tree-shakeable, can be used in serverless environments, and only uses a minimal set of dependencies.

Data-Juicer is a one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs. It is a systematic & reusable library of 80+ core OPs, 20+ reusable config recipes, and 20+ feature-rich dedicated toolkits, designed to function independently of specific LLM datasets and processing pipelines. Data-Juicer allows detailed data analyses with an automated report generation feature for a deeper understanding of your dataset. Coupled with multi-dimension automatic evaluation capabilities, it supports a timely feedback loop at multiple stages in the LLM development process. Data-Juicer offers tens of pre-built data processing recipes for pre-training, fine-tuning, en, zh, and more scenarios. It provides a speedy data processing pipeline requiring less memory and CPU usage, optimized for maximum productivity. Data-Juicer is flexible & extensible, accommodating most types of data formats and allowing flexible combinations of OPs. It is designed for simplicity, with comprehensive documentation, easy start guides and demo configs, and intuitive configuration with simple adding/removing OPs from existing configs.

XTuner is an efficient, flexible, and full-featured toolkit for fine-tuning large models. It supports various LLMs (InternLM, Mixtral-8x7B, Llama 2, ChatGLM, Qwen, Baichuan, ...), VLMs (LLaVA), and various training algorithms (QLoRA, LoRA, full-parameter fine-tune). XTuner also provides tools for chatting with pretrained / fine-tuned LLMs and deploying fine-tuned LLMs with any other framework, such as LMDeploy.

Dwata is a desktop application that allows users to chat with any AI model and gain insights from their data. Chats are organized into threads, similar to Discord, with each thread connecting to a different AI model. Dwata can connect to databases, APIs (such as Stripe), or CSV files and send structured data as prompts when needed. The AI's response will often include SQL or Python code, which can be used to extract the desired insights. Dwata can validate AI-generated SQL to ensure that the tables and columns referenced are correct and can execute queries against the database from within the application. Python code (typically using Pandas) can also be executed from within Dwata, although this feature is still in development. Dwata supports a range of AI models, including OpenAI's GPT-4, GPT-4 Turbo, and GPT-3.5 Turbo; Groq's LLaMA2-70b and Mixtral-8x7b; Phind's Phind-34B and Phind-70B; Anthropic's Claude; and Ollama's Llama 2, Mistral, and Phi-2 Gemma. Dwata can compare chats from different models, allowing users to see the responses of multiple models to the same prompts. Dwata can connect to various data sources, including databases (PostgreSQL, MySQL, MongoDB), SaaS products (Stripe, Shopify), CSV files/folders, and email (IMAP). The desktop application does not collect any private or business data without the user's explicit consent.

LionAGI is a powerful intelligent workflow automation framework that introduces advanced ML models into any existing workflows and data infrastructure. It can interact with almost any model, run interactions in parallel for most models, produce structured pydantic outputs with flexible usage, automate workflow via graph based agents, use advanced prompting techniques, and more. LionAGI aims to provide a centralized agent-managed framework for "ML-powered tools coordination" and to dramatically lower the barrier of entries for creating use-case/domain specific tools. It is designed to be asynchronous only and requires Python 3.10 or higher.

This course has 18 lessons. Each lesson covers its own topic so start wherever you like! Lessons are labeled either "Learn" lessons explaining a Generative AI concept or "Build" lessons that explain a concept and code examples in both **Python** and **TypeScript** when possible. Each lesson also includes a "Keep Learning" section with additional learning tools. **What You Need** * Access to the Azure OpenAI Service **OR** OpenAI API - _Only required to complete coding lessons_ * Basic knowledge of Python or Typescript is helpful - *For absolute beginners check out these Python and TypeScript courses. * A Github account to fork this entire repo to your own GitHub account We have created a **Course Setup** lesson to help you with setting up your development environment. Don't forget to star (🌟) this repo to find it easier later. ## 🧠 Ready to Deploy? If you are looking for more advanced code samples, check out our collection of Generative AI Code Samples in both **Python** and **TypeScript**. ## 🗣️ Meet Other Learners, Get Support Join our official AI Discord server to meet and network with other learners taking this course and get support. ## 🚀 Building a Startup? Sign up for Microsoft for Startups Founders Hub to receive **free OpenAI credits** and up to **$150k towards Azure credits to access OpenAI models through Azure OpenAI Services**. ## 🙏 Want to help? Do you have suggestions or found spelling or code errors? Raise an issue or Create a pull request ## 📂 Each lesson includes: * A short video introduction to the topic * A written lesson located in the README * Python and TypeScript code samples supporting Azure OpenAI and OpenAI API * Links to extra resources to continue your learning ## 🗃️ Lessons | | Lesson Link | Description | Additional Learning | | :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ | | 00 | Course Setup | **Learn:** How to Setup Your Development Environment | Learn More | | 01 | Introduction to Generative AI and LLMs | **Learn:** Understanding what Generative AI is and how Large Language Models (LLMs) work. | Learn More | | 02 | Exploring and comparing different LLMs | **Learn:** How to select the right model for your use case | Learn More | | 03 | Using Generative AI Responsibly | **Learn:** How to build Generative AI Applications responsibly | Learn More | | 04 | Understanding Prompt Engineering Fundamentals | **Learn:** Hands-on Prompt Engineering Best Practices | Learn More | | 05 | Creating Advanced Prompts | **Learn:** How to apply prompt engineering techniques that improve the outcome of your prompts. | Learn More | | 06 | Building Text Generation Applications | **Build:** A text generation app using Azure OpenAI | Learn More | | 07 | Building Chat Applications | **Build:** Techniques for efficiently building and integrating chat applications. | Learn More | | 08 | Building Search Apps Vector Databases | **Build:** A search application that uses Embeddings to search for data. | Learn More | | 09 | Building Image Generation Applications | **Build:** A image generation application | Learn More | | 10 | Building Low Code AI Applications | **Build:** A Generative AI application using Low Code tools | Learn More | | 11 | Integrating External Applications with Function Calling | **Build:** What is function calling and its use cases for applications | Learn More | | 12 | Designing UX for AI Applications | **Learn:** How to apply UX design principles when developing Generative AI Applications | Learn More | | 13 | Securing Your Generative AI Applications | **Learn:** The threats and risks to AI systems and methods to secure these systems. | Learn More | | 14 | The Generative AI Application Lifecycle | **Learn:** The tools and metrics to manage the LLM Lifecycle and LLMOps | Learn More | | 15 | Retrieval Augmented Generation (RAG) and Vector Databases | **Build:** An application using a RAG Framework to retrieve embeddings from a Vector Databases | Learn More | | 16 | Open Source Models and Hugging Face | **Build:** An application using open source models available on Hugging Face | Learn More | | 17 | AI Agents | **Build:** An application using an AI Agent Framework | Learn More | | 18 | Fine-Tuning LLMs | **Learn:** The what, why and how of fine-tuning LLMs | Learn More |

Countdown timers to keep track of a bunch of CV/NLP/ML/RO conference deadlines.

This open-source project, also known as **Deep Learning System** or **AI System (AISys)**, aims to explore and learn about the system design of artificial intelligence and deep learning. The project is centered around the full-stack content of AI systems that ZOMI has accumulated,整理, and built during his work. The goal is to collaborate with all friends who are interested in AI open-source projects to jointly promote learning and discussion.

Haystack is an end-to-end LLM framework that allows you to build applications powered by LLMs, Transformer models, vector search and more. Whether you want to perform retrieval-augmented generation (RAG), document search, question answering or answer generation, Haystack can orchestrate state-of-the-art embedding models and LLMs into pipelines to build end-to-end NLP applications and solve your use case.

Ivy is an open-source machine learning framework that enables you to: * 🔄 **Convert code into any framework** : Use and build on top of any model, library, or device by converting any code from one framework to another using `ivy.transpile`. * ⚒️ **Write framework-agnostic code** : Write your code once in `ivy` and then choose the most appropriate ML framework as the backend to leverage all the benefits and tools. Join our growing community 🌍 to connect with people using Ivy. **Let's** unify.ai **together 🦾**

RestAI is an AIaaS (AI as a Service) platform that allows users to create and consume AI agents (projects) using a simple REST API. It supports various types of agents, including RAG (Retrieval-Augmented Generation), RAGSQL (RAG for SQL), inference, vision, and router. RestAI features automatic VRAM management, support for any public LLM supported by LlamaIndex or any local LLM supported by Ollama, a user-friendly API with Swagger documentation, and a frontend for easy access. It also provides evaluation capabilities for RAG agents using deepeval.

This repository contains a collection of experiments with Large Language Models (LLMs). The experiments explore various applications of LLMs, including text generation, question answering, and code generation. The repository also includes a setup guide and instructions on how to use the experiments.

This repository contains the code for coding, pretraining, and finetuning a GPT-like LLM and is the official code repository for the book Build a Large Language Model (From Scratch). In _Build a Large Language Model (From Scratch)_, you'll discover how LLMs work from the inside out. In this book, I'll guide you step by step through creating your own LLM, explaining each stage with clear text, diagrams, and examples. The method described in this book for training and developing your own small-but-functional model for educational purposes mirrors the approach used in creating large-scale foundational models such as those behind ChatGPT.

LLM AutoEval is a tool that simplifies the process of evaluating Large Language Models (LLMs) using a convenient Colab notebook. It automates the setup and execution of evaluations using RunPod, allowing users to customize evaluation parameters and generate summaries that can be uploaded to GitHub Gist for easy sharing and reference. LLM AutoEval supports various benchmark suites, including Nous, Lighteval, and Open LLM, enabling users to compare their results with existing models and leaderboards.

Funcchain is a Python library that allows you to easily write cognitive systems by leveraging Pydantic models as output schemas and LangChain in the backend. It provides a seamless integration of LLMs into your apps, utilizing OpenAI Functions or LlamaCpp grammars (json-schema-mode) for efficient structured output. Funcchain compiles the Funcchain syntax into LangChain runnables, enabling you to invoke, stream, or batch process your pipelines effortlessly.

NVIDIA Generative AI Examples are state-of-the-art examples that are easy to deploy, test, and extend. All examples run on the high performance NVIDIA CUDA-X software stack and NVIDIA GPUs. These examples showcase the capabilities of NVIDIA's Generative AI platform, which includes tools, frameworks, and models for building and deploying generative AI applications.

Effort is an example implementation of the bucketMul algorithm, which allows for real-time adjustment of the number of calculations performed during inference of an LLM model. At 50% effort, it performs as fast as regular matrix multiplications on Apple Silicon chips; at 25% effort, it is twice as fast while still retaining most of the quality. Additionally, users have the option to skip loading the least important weights.

veScale is a PyTorch Native LLM Training Framework. It provides a set of tools and components to facilitate the training of large language models (LLMs) using PyTorch. veScale includes features such as 4D parallelism, fast checkpointing, and a CUDA event monitor. It is designed to be scalable and efficient, and it can be used to train LLMs on a variety of hardware platforms.

LLM Reasoners is a library that enables LLMs to conduct complex reasoning, with advanced reasoning algorithms. It approaches multi-step reasoning as planning and searches for the optimal reasoning chain, which achieves the best balance of exploration vs exploitation with the idea of "World Model" and "Reward". Given any reasoning problem, simply define the reward function and an optional world model (explained below), and let LLM reasoners take care of the rest, including Reasoning Algorithms, Visualization, LLM calling, and more!

PaddleNLP is an easy-to-use and high-performance NLP library. It aggregates high-quality pre-trained models in the industry and provides out-of-the-box development experience, covering a model library for multiple NLP scenarios with industry practice examples to meet developers' flexible customization needs.

Awesome-LLM-Inference: A curated list of 📙Awesome LLM Inference Papers with Codes, check 📖Contents for more details. This repo is still updated frequently ~ 👨‍💻‍ Welcome to star ⭐️ or submit a PR to this repo!

This repository provides a list of the most starred and forked repositories on GitHub. It is updated automatically and includes information such as the project name, number of stars, number of forks, language, number of open issues, description, and last commit date. The repository is divided into two sections: LLM and chatGPT. The LLM section includes repositories related to large language models, while the chatGPT section includes repositories related to the chatGPT chatbot.

Runhouse is a tool that allows you to build, run, and deploy production-quality AI apps and workflows on your own compute. It provides simple, powerful APIs for the full lifecycle of AI development, from research to evaluation to production to updates to scaling to management, and across any infra. By automatically packaging your apps into scalable, secure, and observable services, Runhouse can also turn otherwise redundant AI activities into common reusable components across your team or company, which improves cost, velocity, and reproducibility.

Dstack is an open-source orchestration engine for running AI workloads in any cloud. It supports a wide range of cloud providers (such as AWS, GCP, Azure, Lambda, TensorDock, Vast.ai, CUDO, RunPod, etc.) as well as on-premises infrastructure. With Dstack, you can easily set up and manage dev environments, tasks, services, and pools for your AI workloads.

DagsHub is a platform for machine learning and data science teams to build, manage, and collaborate on their projects. With DagsHub you can: 1. Version code, data, and models in one place. Use the free provided DagsHub storage or connect it to your cloud storage 2. Track Experiments using Git, DVC or MLflow, to provide a fully reproducible environment 3. Visualize pipelines, data, and notebooks in and interactive, diff-able, and dynamic way 4. Label your data directly on the platform using Label Studio 5. Share your work with your team members 6. Stream and upload your data in an intuitive and easy way, while preserving versioning and structure. DagsHub is built firmly around open, standard formats for your project. In particular: * Git * DVC * MLflow * Label Studio * Standard data formats like YAML, JSON, CSV Therefore, you can work with DagsHub regardless of your chosen programming language or frameworks.

Mobius is an AI infra platform including realtime computing and training. It is built on Ray, a distributed computing framework, and provides a number of features that make it well-suited for online machine learning tasks. These features include: * **Cross Language**: Mobius can run in multiple languages (only Python and Java are supported currently) with high efficiency. You can implement your operator in different languages and run them in one job. * **Single Node Failover**: Mobius has a special failover mechanism that only needs to rollback the failed node itself, in most cases, to recover the job. This is a huge benefit if your job is sensitive about failure recovery time. * **AutoScaling**: Mobius can generate a new graph with different configurations in runtime without stopping the job. * **Fusion Training**: Mobius can combine TensorFlow/Pytorch and streaming, then building an e2e online machine learning pipeline. Mobius is still under development, but it has already been used to power a number of real-world applications, including: * A real-time recommendation system for a major e-commerce company * A fraud detection system for a large financial institution * A personalized news feed for a major news organization If you are interested in using Mobius for your own online machine learning projects, you can find more information in the documentation.

Cognee is an open-source framework designed for creating self-improving deterministic outputs for Large Language Models (LLMs) using graphs, LLMs, and vector retrieval. It provides a platform for AI engineers to enhance their models and generate more accurate results. Users can leverage Cognee to add new information, utilize LLMs for knowledge creation, and query the system for relevant knowledge. The tool supports various LLM providers and offers flexibility in adding different data types, such as text files or directories. Cognee aims to streamline the process of working with LLMs and improving AI models for better performance and efficiency.

This repository contains a collection of resources in the form of eBooks related to Data Science, Machine Learning, and similar topics.

Backend.AI is a streamlined, container-based computing cluster platform that hosts popular computing/ML frameworks and diverse programming languages, with pluggable heterogeneous accelerator support including CUDA GPU, ROCm GPU, TPU, IPU and other NPUs. It allocates and isolates the underlying computing resources for multi-tenant computation sessions on-demand or in batches with customizable job schedulers with its own orchestrator. All its functions are exposed as REST/GraphQL/WebSocket APIs.

Falkon is a Python implementation of the Falkon algorithm for large-scale, approximate kernel ridge regression. The code is optimized for scalability to large datasets with tens of millions of points and beyond. Full kernel matrices are never computed explicitly so that you will not run out of memory on larger problems. Preconditioned conjugate gradient optimization ensures that only few iterations are necessary to obtain good results. The basic algorithm is a Nyström approximation to kernel ridge regression, which needs only three hyperparameters: 1. The number of centers M - this controls the quality of the approximation: a higher number of centers will produce more accurate results at the expense of more computation time, and higher memory requirements. 2. The penalty term, which controls the amount of regularization. 3. The kernel function. A good default is always the Gaussian (RBF) kernel (`falkon.kernels.GaussianKernel`).

ClearML is a suite of tools designed to streamline the machine learning workflow. It includes an experiment manager, MLOps/LLMOps, data management, and model serving capabilities. ClearML is open-source and offers a free tier hosting option. It supports various ML/DL frameworks and integrates with Jupyter Notebook and PyCharm. ClearML provides extensive logging capabilities, including source control info, execution environment, hyper-parameters, and experiment outputs. It also offers automation features, such as remote job execution and pipeline creation. ClearML is designed to be easy to integrate, requiring only two lines of code to add to existing scripts. It aims to improve collaboration, visibility, and data transparency within ML teams.

PyTensor is a Python library that allows one to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays. It provides the computational backend for `PyMC `__. PyTensor is a fork of `Aesara `__, which is a fork of `Theano `__. PyTensor maintains a static graph which can be modified in-place to allow for advanced optimizations. Contrary to PyTorch and TensorFlow, PyTensor maintains a static graph which can be modified in-place to allow for advanced optimizations.

This paper list is about Large Language Model-enhanced Recommender System. It also contains some related works. Keywords: recommendation system, large language models

This repository presents the findings of the paper "Compression Represents Intelligence Linearly". The study reveals a strong linear correlation between the intelligence of LLMs, as measured by benchmark scores, and their ability to compress external text corpora. Compression efficiency, derived from raw text corpora, serves as a reliable evaluation metric that is linearly associated with model capabilities. The repository includes the compression corpora used in the paper, code for computing compression efficiency, and data collection and processing pipelines.

Dexter is a set of mature LLM tools used in production at Dexa, with a focus on real-world RAG (Retrieval Augmented Generation). It is a production-quality RAG that is extremely fast and minimal, and handles caching, throttling, and batching for ingesting large datasets. It also supports optional hybrid search with SPLADE embeddings, and is a minimal TS package with full typing that uses `fetch` everywhere and supports Node.js 18+, Deno, Cloudflare Workers, Vercel edge functions, etc. Dexter has full docs and includes examples for basic usage, caching, Redis caching, AI function, AI runner, and chatbot.

Intel® Neural Compressor is an open-source Python library that supports popular model compression techniques such as quantization, pruning (sparsity), distillation, and neural architecture search on mainstream frameworks such as TensorFlow, PyTorch, ONNX Runtime, and MXNet. It provides key features, typical examples, and open collaborations, including support for a wide range of Intel hardware, validation of popular LLMs, and collaboration with cloud marketplaces, software platforms, and open AI ecosystems.

BitMat is a Python package designed to optimize matrix multiplication operations by utilizing custom kernels written in Triton. It leverages the principles outlined in the "1bit-LLM Era" paper, specifically utilizing packed int8 data to enhance computational efficiency and performance in deep learning and numerical computing tasks.

Distributed Llama is a tool that allows you to run large language models (LLMs) on weak devices or make powerful devices even more powerful by distributing the workload and dividing the RAM usage. It uses TCP sockets to synchronize the state of the neural network, and you can easily configure your AI cluster by using a home router. Distributed Llama supports models such as Llama 2 (7B, 13B, 70B) chat and non-chat versions, Llama 3, and Grok-1 (314B).

The Bookworm·Puyu large model training camp aims to promote the implementation of large models in more industries and provide developers with a more efficient platform for learning the development and application of large models. Within two weeks, you will learn the entire process of fine-tuning, deploying, and evaluating large models.

PyTorch Lightning is a framework for training and deploying AI models. It provides a high-level API that abstracts away the low-level details of PyTorch, making it easier to write and maintain complex models. Lightning also includes a number of features that make it easy to train and deploy models on multiple GPUs or TPUs, and to track and visualize training progress. PyTorch Lightning is used by a wide range of organizations, including Google, Facebook, and Microsoft. It is also used by researchers at top universities around the world. Here are some of the benefits of using PyTorch Lightning: * **Increased productivity:** Lightning's high-level API makes it easy to write and maintain complex models. This can save you time and effort, and allow you to focus on the research or business problem you're trying to solve. * **Improved performance:** Lightning's optimized training loops and data loading pipelines can help you train models faster and with better performance. * **Easier deployment:** Lightning makes it easy to deploy models to a variety of platforms, including the cloud, on-premises servers, and mobile devices. * **Better reproducibility:** Lightning's logging and visualization tools make it easy to track and reproduce training results.

CompressAI-Vision is a tool that helps you develop, test, and evaluate compression models with standardized tests in the context of compression methods optimized for machine tasks algorithms such as Neural-Network (NN)-based detectors. It currently focuses on two types of pipeline: Video compression for remote inference (`compressai-remote-inference`), which corresponds to the MPEG "Video Coding for Machines" (VCM) activity. Split inference (`compressai-split-inference`), which includes an evaluation framework for compressing intermediate features produced in the context of split models. The software supports all the pipelines considered in the related MPEG activity: "Feature Compression for Machines" (FCM).

Kornia is a differentiable computer vision library for PyTorch. It consists of a set of routines and differentiable modules to solve generic computer vision problems. At its core, the package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions.

Python package for concise, transparent, and accurate predictive modeling. All sklearn-compatible and easy to use. _For interpretability in NLP, check out our new package:imodelsX _

Colossal-AI is a deep learning system for large-scale parallel training. It provides a unified interface to scale sequential code of model training to distributed environments. Colossal-AI supports parallel training methods such as data, pipeline, tensor, and sequence parallelism and is integrated with heterogeneous training and zero redundancy optimizer.

This repository provides a detailed tutorial on how to build your own large language model (LLM) from scratch. It includes all the code necessary to create a GPT-like LLM, covering the encoding, pre-training, and fine-tuning processes. The tutorial is written in a clear and concise style, with plenty of examples and illustrations to help you understand the concepts involved. It is suitable for developers and researchers with some programming experience who are interested in learning more about LLMs and how to build them.

This book aims to provide readers with a comprehensive understanding of large language model technology, including its basic principles, key technologies, and application prospects. Through in-depth research and practice, we can continuously explore and improve large language model technology, and contribute to the development of the field of artificial intelligence.

InternLM-XComposer2 is a groundbreaking vision-language large model (VLLM) based on InternLM2-7B excelling in free-form text-image composition and comprehension. It boasts several amazing capabilities and applications: * **Free-form Interleaved Text-Image Composition** : InternLM-XComposer2 can effortlessly generate coherent and contextual articles with interleaved images following diverse inputs like outlines, detailed text requirements and reference images, enabling highly customizable content creation. * **Accurate Vision-language Problem-solving** : InternLM-XComposer2 accurately handles diverse and challenging vision-language Q&A tasks based on free-form instructions, excelling in recognition, perception, detailed captioning, visual reasoning, and more. * **Awesome performance** : InternLM-XComposer2 based on InternLM2-7B not only significantly outperforms existing open-source multimodal models in 13 benchmarks but also **matches or even surpasses GPT-4V and Gemini Pro in 6 benchmarks** We release InternLM-XComposer2 series in three versions: * **InternLM-XComposer2-4KHD-7B** 🤗: The high-resolution multi-task trained VLLM model with InternLM-7B as the initialization of the LLM for _High-resolution understanding_ , _VL benchmarks_ and _AI assistant_. * **InternLM-XComposer2-VL-7B** 🤗 : The multi-task trained VLLM model with InternLM-7B as the initialization of the LLM for _VL benchmarks_ and _AI assistant_. **It ranks as the most powerful vision-language model based on 7B-parameter level LLMs, leading across 13 benchmarks.** * **InternLM-XComposer2-VL-1.8B** 🤗 : A lightweight version of InternLM-XComposer2-VL based on InternLM-1.8B. * **InternLM-XComposer2-7B** 🤗: The further instruction tuned VLLM for _Interleaved Text-Image Composition_ with free-form inputs. Please refer to Technical Report and 4KHD Technical Reportfor more details.

InterpretML is an open-source package that incorporates state-of-the-art machine learning interpretability techniques under one roof. With this package, you can train interpretable glassbox models and explain blackbox systems. InterpretML helps you understand your model's global behavior, or understand the reasons behind individual predictions. Interpretability is essential for: - Model debugging - Why did my model make this mistake? - Feature Engineering - How can I improve my model? - Detecting fairness issues - Does my model discriminate? - Human-AI cooperation - How can I understand and trust the model's decisions? - Regulatory compliance - Does my model satisfy legal requirements? - High-risk applications - Healthcare, finance, judicial, ...

The OpenAI Completion plugin for Sublime Text provides first-class code assistant support within the editor. It utilizes LLM models to manipulate code, engage in chat mode, and perform various tasks. The plugin supports OpenAI, llama.cpp, and ollama models, allowing users to customize their AI assistant experience. It offers separated chat histories and assistant settings for different projects, enabling context-specific interactions. Additionally, the plugin supports Markdown syntax with code language syntax highlighting, server-side streaming for faster response times, and proxy support for secure connections. Users can configure the plugin's settings to set their OpenAI API key, adjust assistant modes, and manage chat history. Overall, the OpenAI Completion plugin enhances the Sublime Text editor with powerful AI capabilities, streamlining coding workflows and fostering collaboration with AI assistants.

Agency is a python library that provides an Actor model framework for creating agent-integrated systems. It offers an easy-to-use API for connecting agents with traditional software systems, enabling flexible and scalable architectures. Agency aims to empower developers in creating custom agent-based applications by providing a foundation for experimentation and development. Key features include an intuitive API, performance and scalability through multiprocessing and AMQP support, observability and control with action and lifecycle callbacks, access policies, and detailed logging. The library also includes a demo application with multiple agent examples, OpenAI agent examples, HuggingFace transformers agent example, operating system access, Gradio UI, and Docker configuration for reference and development.

HelixML is a private GenAI platform that allows users to deploy the best of open AI in their own data center or VPC while retaining complete data security and control. It includes support for fine-tuning models with drag-and-drop functionality. HelixML brings the best of open source AI to businesses in an ergonomic and scalable way, optimizing the tradeoff between GPU memory and latency.

This repository contains code released by Google Research. All datasets in this repository are released under the CC BY 4.0 International license, which can be found here: https://creativecommons.org/licenses/by/4.0/legalcode. All source files in this repository are released under the Apache 2.0 license, the text of which can be found in the LICENSE file.

OpenCRISPR is a set of free and open gene editing systems designed by Profluent Bio. The OpenCRISPR-1 protein maintains the prototypical architecture of a Type II Cas9 nuclease but is hundreds of mutations away from SpCas9 or any other known natural CRISPR-associated protein. You can view OpenCRISPR-1 as a drop-in replacement for many protocols that need a cas9-like protein with an NGG PAM and you can even use it with canonical SpCas9 gRNAs. OpenCRISPR-1 can be fused in a deactivated or nickase format for next generation gene editing techniques like base, prime, or epigenome editing.

NNStreamer is a set of Gstreamer plugins that allow Gstreamer developers to adopt neural network models easily and efficiently and neural network developers to manage neural network pipelines and their filters easily and efficiently.

A comprehensive guide to building Retrieval Augmented Generation (RAG)-based LLM applications for production. This guide covers developing a RAG-based LLM application from scratch, scaling the major components, evaluating different configurations, implementing LLM hybrid routing, serving the application in a highly scalable and available manner, and sharing the impacts LLM applications have had on products.

Tonic Validate is a framework for the evaluation of LLM outputs, such as Retrieval Augmented Generation (RAG) pipelines. Validate makes it easy to evaluate, track, and monitor your LLM and RAG applications. Validate allows you to evaluate your LLM outputs through the use of our provided metrics which measure everything from answer correctness to LLM hallucination. Additionally, Validate has an optional UI to visualize your evaluation results for easy tracking and monitoring.

Pax is a framework to configure and run machine learning experiments on top of Jax.

The Google Gemini Documentation repository contains the source files for the guide and tutorials on the Generative AI developer site, which is home to the Gemini API and Gemma. The repository includes notebooks and other content used directly on ai.google.dev, as well as demos and examples. To contribute to the site documentation, please read CONTRIBUTING.md. To contribute as a demo app maintainer, please read DEMO_MAINTAINERS.md. To file an issue, please use the GitHub issue tracker.

The LLM Hosting Container repository provides Dockerfile and associated resources for building and hosting containers for large language models, specifically the HuggingFace Text Generation Inference (TGI) container. This tool allows users to easily deploy and manage large language models in a containerized environment, enabling efficient inference and deployment of language-based applications.

This repository contains example code to demonstrate how to connect MATLAB to the OpenAI™ Chat Completions API (which powers ChatGPT™) as well as OpenAI Images API (which powers DALL·E™). This allows you to leverage the natural language processing capabilities of large language models directly within your MATLAB environment.

BitBLAS is a library for mixed-precision BLAS operations on GPUs, for example, the $W_{wdtype}A_{adtype}$ mixed-precision matrix multiplication where $C_{cdtype}[M, N] = A_{adtype}[M, K] \times W_{wdtype}[N, K]$. BitBLAS aims to support efficient mixed-precision DNN model deployment, especially the $W_{wdtype}A_{adtype}$ quantization in large language models (LLMs), for example, the $W_{UINT4}A_{FP16}$ in GPTQ, the $W_{INT2}A_{FP16}$ in BitDistiller, the $W_{INT2}A_{INT8}$ in BitNet-b1.58. BitBLAS is based on techniques from our accepted submission at OSDI'24.

cuVS is a library that contains state-of-the-art implementations of several algorithms for running approximate nearest neighbors and clustering on the GPU. It can be used directly or through the various databases and other libraries that have integrated it. The primary goal of cuVS is to simplify the use of GPUs for vector similarity search and clustering.

This repository provides a comprehensive list of academic papers, articles, tutorials, slides, and projects related to Large Language Model (LLM) systems. It covers various aspects of LLM research, including pre-training, serving, system efficiency optimization, multi-model systems, image generation systems, LLM applications in systems, ML systems, survey papers, LLM benchmarks and leaderboards, and other relevant resources. The repository is regularly updated to include the latest developments in this rapidly evolving field, making it a valuable resource for researchers, practitioners, and anyone interested in staying abreast of the advancements in LLM technology.

The Google AI Python SDK is the easiest way for Python developers to build with the Gemini API. The Gemini API gives you access to Gemini models created by Google DeepMind. Gemini models are built from the ground up to be multimodal, so you can reason seamlessly across text, images, and code.

This repository contains a collection of resources for learning about and using Large Language Models (LLMs). The resources include tutorials, code examples, and links to additional resources. LLMs are a type of artificial intelligence that can understand and generate human-like text. They have a wide range of potential applications, including natural language processing, machine translation, and chatbot development.

imodelsX is a Scikit-learn friendly library that provides tools for explaining, predicting, and steering text models/data. It also includes a collection of utilities for getting started with text data. **Explainable modeling/steering** | Model | Reference | Output | Description | |---|---|---|---| | Tree-Prompt | [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/tree_prompt) | Explanation + Steering | Generates a tree of prompts to steer an LLM (_Official_) | | iPrompt | [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/iprompt) | Explanation + Steering | Generates a prompt that explains patterns in data (_Official_) | | AutoPrompt | [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/autoprompt) | Explanation + Steering | Find a natural-language prompt using input-gradients (⌛ In progress)| | D3 | [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/d3) | Explanation | Explain the difference between two distributions | | SASC | [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/sasc) | Explanation | Explain a black-box text module using an LLM (_Official_) | | Aug-Linear | [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/aug_linear) | Linear model | Fit better linear model using an LLM to extract embeddings (_Official_) | | Aug-Tree | [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/aug_tree) | Decision tree | Fit better decision tree using an LLM to expand features (_Official_) | **General utilities** | Model | Reference | |---|---| | LLM wrapper| [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/llm) | Easily call different LLMs | | | Dataset wrapper| [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/data) | Download minimially processed huggingface datasets | | | Bag of Ngrams | [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/bag_of_ngrams) | Learn a linear model of ngrams | | | Linear Finetune | [Reference](https://github.com/microsoft/AugML/tree/main/imodelsX/linear_finetune) | Finetune a single linear layer on top of LLM embeddings | | **Related work** * [imodels package](https://github.com/microsoft/interpretml/tree/main/imodels) (JOSS 2021) - interpretable ML package for concise, transparent, and accurate predictive modeling (sklearn-compatible). * [Adaptive wavelet distillation](https://arxiv.org/abs/2111.06185) (NeurIPS 2021) - distilling a neural network into a concise wavelet model * [Transformation importance](https://arxiv.org/abs/1912.04938) (ICLR 2020 workshop) - using simple reparameterizations, allows for calculating disentangled importances to transformations of the input (e.g. assigning importances to different frequencies) * [Hierarchical interpretations](https://arxiv.org/abs/1807.03343) (ICLR 2019) - extends CD to CNNs / arbitrary DNNs, and aggregates explanations into a hierarchy * [Interpretation regularization](https://arxiv.org/abs/2006.14340) (ICML 2020) - penalizes CD / ACD scores during training to make models generalize better * [PDR interpretability framework](https://www.pnas.org/doi/10.1073/pnas.1814225116) (PNAS 2019) - an overarching framewwork for guiding and framing interpretable machine learning

UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured evaluations (covering language, code, embedding use cases), perform root cause analysis on failure cases and give insights on how to resolve them.

The IBM Analog Hardware Acceleration Kit is an open-source Python toolkit for exploring and using the capabilities of in-memory computing devices in the context of artificial intelligence. It consists of two main components: Pytorch integration and Analog devices simulator. The Pytorch integration provides a series of primitives and features that allow using the toolkit within PyTorch, including analog neural network modules, analog training using torch training workflow, and analog inference using torch inference workflow. The Analog devices simulator is a high-performant (CUDA-capable) C++ simulator that allows for simulating a wide range of analog devices and crossbar configurations by using abstract functional models of material characteristics with adjustable parameters. Along with the two main components, the toolkit includes other functionalities such as a library of device presets, a module for executing high-level use cases, a utility to automatically convert a downloaded model to its equivalent Analog model, and integration with the AIHW Composer platform. The toolkit is currently in beta and under active development, and users are advised to be mindful of potential issues and keep an eye for improvements, new features, and bug fixes in upcoming versions.

This repository is a curated list of research papers that explore the integration of Large Language Model (LLM) technology with tabular data. It aims to provide a comprehensive resource for researchers and practitioners interested in this emerging field. The repository includes papers on a wide range of topics, including table-to-text generation, table question answering, and tabular data classification. It also includes a section on related datasets and resources.

This package integrates Large Language Models (LLMs) into spaCy, featuring a modular system for **fast prototyping** and **prompting** , and turning unstructured responses into **robust outputs** for various NLP tasks, **no training data** required. It supports open-source LLMs hosted on Hugging Face 🤗: Falcon, Dolly, Llama 2, OpenLLaMA, StableLM, Mistral. Integration with LangChain 🦜️🔗 - all `langchain` models and features can be used in `spacy-llm`. Tasks available out of the box: Named Entity Recognition, Text classification, Lemmatization, Relationship extraction, Sentiment analysis, Span categorization, Summarization, Entity linking, Translation, Raw prompt execution for maximum flexibility. Soon: Semantic role labeling. Easy implementation of **your own functions** via spaCy's registry for custom prompting, parsing and model integrations. For an example, see here. Map-reduce approach for splitting prompts too long for LLM's context window and fusing the results back together

Awesome LLM plaza is a curated list of awesome LLM papers, projects, and resources. It is updated daily and includes resources from a variety of sources, including huggingface daily papers, twitter, github trending, paper with code, weixin, etc.

This repository maintains a list of research papers on LLM-based Multi-Agents, categorized into five main streams: Multi-Agents Framework, Multi-Agents Orchestration and Efficiency, Multi-Agents for Problem Solving, Multi-Agents for World Simulation, and Multi-Agents Datasets and Benchmarks. The repository also includes a survey paper on LLM-based Multi-Agents and a table summarizing the key findings of the survey.

H2O LLM Studio is a framework and no-code GUI designed for fine-tuning state-of-the-art large language models (LLMs). With H2O LLM Studio, you can easily and effectively fine-tune LLMs without the need for any coding experience. The GUI is specially designed for large language models, and you can finetune any LLM using a large variety of hyperparameters. You can also use recent finetuning techniques such as Low-Rank Adaptation (LoRA) and 8-bit model training with a low memory footprint. Additionally, you can use Reinforcement Learning (RL) to finetune your model (experimental), use advanced evaluation metrics to judge generated answers by the model, track and compare your model performance visually, and easily export your model to the Hugging Face Hub and share it with the community.

This repository provides a comprehensive overview of large language models (LLMs), covering various aspects such as their history, types, underlying architecture, training techniques, and applications. It includes detailed explanations of key concepts like Transformer models, distributed training, fine-tuning, and reinforcement learning. The repository also discusses the evaluation and limitations of LLMs, including the phenomenon of hallucinations. Additionally, it provides a list of related courses and references for further exploration.

Eval-Scope is a framework for evaluating and improving large language models (LLMs). It provides a set of commonly used test datasets, metrics, and a unified model interface for generating and evaluating LLM responses. Eval-Scope also includes an automatic evaluator that can score objective questions and use expert models to evaluate complex tasks. Additionally, it offers a visual report generator, an arena mode for comparing multiple models, and a variety of other features to support LLM evaluation and development.

TensorRT-LLM is an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM contains components to create Python and C++ runtimes that execute those TensorRT engines. It also includes a backend for integration with the NVIDIA Triton Inference Server; a production-quality system to serve LLMs. Models built with TensorRT-LLM can be executed on a wide range of configurations going from a single GPU to multiple nodes with multiple GPUs (using Tensor Parallelism and/or Pipeline Parallelism).

SeaLLMs are a family of language models optimized for Southeast Asian (SEA) languages. They were pre-trained from Llama-2, on a tailored publicly-available dataset, which comprises texts in Vietnamese 🇻🇳, Indonesian 🇮🇩, Thai 🇹🇭, Malay 🇲🇾, Khmer🇰🇭, Lao🇱🇦, Tagalog🇵🇭 and Burmese🇲🇲. The SeaLLM-chat underwent supervised finetuning (SFT) and specialized self-preferencing DPO using a mix of public instruction data and a small number of queries used by SEA language native speakers in natural settings, which **adapt to the local cultural norms, customs, styles and laws in these areas**. SeaLLM-13b models exhibit superior performance across a wide spectrum of linguistic tasks and assistant-style instruction-following capabilities relative to comparable open-source models. Moreover, they outperform **ChatGPT-3.5** in non-Latin languages, such as Thai, Khmer, Lao, and Burmese.

This repository provides a comprehensive collection of resources, open-source tools, and knowledge related to quantitative analysis. It serves as a valuable knowledge base and navigation guide for individuals interested in various aspects of quantitative investing, including platforms, programming languages, mathematical foundations, machine learning, deep learning, and practical applications. The repository is well-structured and organized, with clear sections covering different topics. It includes resources on system platforms, programming codes, mathematical foundations, algorithm principles, machine learning, deep learning, reinforcement learning, graph networks, model deployment, and practical applications. Additionally, there are dedicated sections on quantitative trading and investment, as well as large models. The repository is actively maintained and updated, ensuring that users have access to the latest information and resources.

Ort is an unofficial ONNX Runtime 1.17 wrapper for Rust based on the now inactive onnxruntime-rs. ONNX Runtime accelerates ML inference on both CPU and GPU.

Aim is an open-source, self-hosted ML experiment tracking tool designed to handle 10,000s of training runs. Aim provides a performant and beautiful UI for exploring and comparing training runs. Additionally, its SDK enables programmatic access to tracked metadata — perfect for automations and Jupyter Notebook analysis. **Aim's mission is to democratize AI dev tools 🎯**

The Ersilia Model Hub is a unified platform of pre-trained AI/ML models dedicated to infectious and neglected disease research. It offers an open-source, low-code solution that provides seamless access to AI/ML models for drug discovery. Models housed in the hub come from two sources: published models from literature (with due third-party acknowledgment) and custom models developed by the Ersilia team or contributors.

DVC, or Data Version Control, is a command-line tool and VS Code extension that helps you develop reproducible machine learning projects. With DVC, you can version your data and models, iterate fast with lightweight pipelines, track experiments in your local Git repo, compare any data, code, parameters, model, or performance plots, and share experiments and automatically reproduce anyone's experiment.

Haystack is an open-source framework for building production-ready LLM applications, retrieval-augmented generative pipelines, and state-of-the-art search systems that work intelligently over large document collections. It lets you quickly try out the latest models in natural language processing (NLP) while being flexible and easy to use.

BasicLingua is a Python library that provides functionalities for linguistic tasks such as tokenization, stemming, lemmatization, and many others. It is based on the Gemini Language Model, which has demonstrated promising results in dealing with text data. BasicLingua can be used as an API or through a web demo. It is available under the MIT license and can be used in various projects.

The second edition of "PyTorch Practical Tutorial" was completed after 5 years, 4 years, and 2 years. On the basis of the essence of the first edition, rich and detailed deep learning application cases and reasoning deployment frameworks have been added, so that this book can more systematically cover the knowledge involved in deep learning engineers. As the development of artificial intelligence technology continues to emerge, the second edition of "PyTorch Practical Tutorial" is not the end, but the beginning, opening up new technologies, new fields, and new chapters. I hope to continue learning and making progress in artificial intelligence technology with you in the future.

This repository contains a collection of papers and code for the CVPR 2024 conference. The papers cover a wide range of topics in computer vision, including object detection, image segmentation, image generation, and video analysis. The code provides implementations of the algorithms described in the papers, making it easy for researchers and practitioners to reproduce the results and build upon the work of others. The repository is maintained by a team of researchers at the University of California, Berkeley.

Awesome-AGI is a curated list of resources related to Artificial General Intelligence (AGI), including models, pipelines, applications, and concepts. It provides a comprehensive overview of the current state of AGI research and development, covering various aspects such as model training, fine-tuning, deployment, and applications in different domains. The repository also includes resources on prompt engineering, RLHF, LLM vocabulary expansion, long text generation, hallucination mitigation, controllability and safety, and text detection. It serves as a valuable resource for researchers, practitioners, and anyone interested in the field of AGI.

Petals is a tool that allows users to run large language models at home in a BitTorrent-style manner. It enables fine-tuning and inference up to 10x faster than offloading. Users can generate text with distributed models like Llama 2, Falcon, and BLOOM, and fine-tune them for specific tasks directly from their desktop computer or Google Colab. Petals is a community-run system that relies on people sharing their GPUs to increase its capacity and offer a distributed network for hosting model layers.

CGraph is a cross-platform **D** irected **A** cyclic **G** raph framework based on pure C++ without any 3rd-party dependencies. You, with it, can **build your own operators simply, and describe any running schedules** as you need, such as dependence, parallelling, aggregation and so on. Some useful tools and plugins are also provide to improve your project. Tutorials and contact information are show as follows. Please **get in touch with us for free** if you need more about this repository.

This repository serves as a comprehensive hub for updates on generative AI research, interview materials, notebooks, and more. It includes monthly best GenAI papers list, interview resources, free courses, and code repositories/notebooks for developing generative AI applications. The repository is regularly updated with the latest additions to keep users informed and engaged in the field of generative AI.

This repository contains tools and libraries for building AIR platforms, runtimes and compilers.

Cognita is an open-source framework to organize your RAG codebase along with a frontend to play around with different RAG customizations. It provides a simple way to organize your codebase so that it becomes easy to test it locally while also being able to deploy it in a production ready environment. The key issues that arise while productionizing RAG system from a Jupyter Notebook are: 1. **Chunking and Embedding Job** : The chunking and embedding code usually needs to be abstracted out and deployed as a job. Sometimes the job will need to run on a schedule or be trigerred via an event to keep the data updated. 2. **Query Service** : The code that generates the answer from the query needs to be wrapped up in a api server like FastAPI and should be deployed as a service. This service should be able to handle multiple queries at the same time and also autoscale with higher traffic. 3. **LLM / Embedding Model Deployment** : Often times, if we are using open-source models, we load the model in the Jupyter notebook. This will need to be hosted as a separate service in production and model will need to be called as an API. 4. **Vector DB deployment** : Most testing happens on vector DBs in memory or on disk. However, in production, the DBs need to be deployed in a more scalable and reliable way. Cognita makes it really easy to customize and experiment everything about a RAG system and still be able to deploy it in a good way. It also ships with a UI that makes it easier to try out different RAG configurations and see the results in real time. You can use it locally or with/without using any Truefoundry components. However, using Truefoundry components makes it easier to test different models and deploy the system in a scalable way. Cognita allows you to host multiple RAG systems using one app. ### Advantages of using Cognita are: 1. A central reusable repository of parsers, loaders, embedders and retrievers. 2. Ability for non-technical users to play with UI - Upload documents and perform QnA using modules built by the development team. 3. Fully API driven - which allows integration with other systems. > If you use Cognita with Truefoundry AI Gateway, you can get logging, metrics and feedback mechanism for your user queries. ### Features: 1. Support for multiple document retrievers that use `Similarity Search`, `Query Decompostion`, `Document Reranking`, etc 2. Support for SOTA OpenSource embeddings and reranking from `mixedbread-ai` 3. Support for using LLMs using `Ollama` 4. Support for incremental indexing that ingests entire documents in batches (reduces compute burden), keeps track of already indexed documents and prevents re-indexing of those docs.

An opinionated .NET framework, that is built on top of Semantic Kernel and Orleans, which helps creating and hosting event-driven AI Agents.

Reinforcement Learning from AI Feedback (RLAIF) is a concept that describes a type of machine learning approach where **an AI agent learns by receiving feedback or guidance from another AI system**. This concept is closely related to the field of Reinforcement Learning (RL), which is a type of machine learning where an agent learns to make a sequence of decisions in an environment to maximize a cumulative reward. In traditional RL, an agent interacts with an environment and receives feedback in the form of rewards or penalties based on the actions it takes. It learns to improve its decision-making over time to achieve its goals. In the context of Reinforcement Learning from AI Feedback, the AI agent still aims to learn optimal behavior through interactions, but **the feedback comes from another AI system rather than from the environment or human evaluators**. This can be **particularly useful in situations where it may be challenging to define clear reward functions or when it is more efficient to use another AI system to provide guidance**. The feedback from the AI system can take various forms, such as: - **Demonstrations** : The AI system provides demonstrations of desired behavior, and the learning agent tries to imitate these demonstrations. - **Comparison Data** : The AI system ranks or compares different actions taken by the learning agent, helping it to understand which actions are better or worse. - **Reward Shaping** : The AI system provides additional reward signals to guide the learning agent's behavior, supplementing the rewards from the environment. This approach is often used in scenarios where the RL agent needs to learn from **limited human or expert feedback or when the reward signal from the environment is sparse or unclear**. It can also be used to **accelerate the learning process and make RL more sample-efficient**. Reinforcement Learning from AI Feedback is an area of ongoing research and has applications in various domains, including robotics, autonomous vehicles, and game playing, among others.

The official Node.js client for Pinecone, written in TypeScript. This client library provides a high-level interface for interacting with the Pinecone vector database service. With this client, you can create and manage indexes, upsert and query vector data, and perform other operations related to vector search and retrieval. The client is designed to be easy to use and provides a consistent and idiomatic experience for Node.js developers. It supports all the features and functionality of the Pinecone API, making it a comprehensive solution for building vector-powered applications in Node.js.

mlx-llm is a library that allows you to run Large Language Models (LLMs) on Apple Silicon devices in real-time using Apple's MLX framework. It provides a simple and easy-to-use API for creating, loading, and using LLM models, as well as a variety of applications such as chatbots, fine-tuning, and retrieval-augmented generation.

Awesome LLM compression research papers and tools to accelerate LLM training and inference.

Redis Vector Library (RedisVL) is a Python client library for building AI applications on top of Redis. It provides a high-level interface for managing vector indexes, performing vector search, and integrating with popular embedding models and providers. RedisVL is designed to make it easy for developers to build and deploy AI applications that leverage the speed, flexibility, and reliability of Redis.

SEED-Bench is a comprehensive benchmark for evaluating the performance of multimodal large language models (LLMs) on a wide range of tasks that require both text and image understanding. It consists of two versions: SEED-Bench-1 and SEED-Bench-2. SEED-Bench-1 focuses on evaluating the spatial and temporal understanding of LLMs, while SEED-Bench-2 extends the evaluation to include text and image generation tasks. Both versions of SEED-Bench provide a diverse set of tasks that cover different aspects of multimodal understanding, making it a valuable tool for researchers and practitioners working on LLMs.

VSP-LLM (Visual Speech Processing incorporated with LLMs) is a novel framework that maximizes context modeling ability by leveraging the power of LLMs. It performs multi-tasks of visual speech recognition and translation, where given instructions control the task type. The input video is mapped to the input latent space of a LLM using a self-supervised visual speech model. To address redundant information in input frames, a deduplication method is employed using visual speech units. VSP-LLM utilizes Low Rank Adaptors (LoRA) for computationally efficient training.

Unofficial Julia Bindings for wandb.ai. Wandb is a platform for tracking and visualizing machine learning experiments. It provides a simple and consistent way to log metrics, parameters, and other data from your experiments, and to visualize them in a variety of ways. Wandb.jl provides a convenient way to use Wandb from Julia.

Scikit-decide is an AI framework for Reinforcement Learning, Automated Planning and Scheduling. It provides a unified interface to define and solve decision-making problems, making it easy to switch between different algorithms and domains.

Awesome Ruby AI is a curated list of awesome AI projects built in Ruby. It includes open source API libraries, vector database clients, bot platforms, composability frameworks, and i18n tools. These tools can be used for a variety of tasks, such as natural language processing, computer vision, and machine learning.

This repository contains a collection of tools that can be used with vastai. The tools are free to use, modify and distribute. If you find this useful and wish to donate your welcome to send your donations to the following wallets. BTC 15qkQSYXP2BvpqJkbj2qsNFb6nd7FyVcou XMR 897VkA8sG6gh7yvrKrtvWningikPteojfSgGff3JAUs3cu7jxPDjhiAZRdcQSYPE2VGFVHAdirHqRZEpZsWyPiNK6XPQKAg RVN RSgWs9Co8nQeyPqQAAqHkHhc5ykXyoMDUp USDT(ETH ERC20) 0xa5955cf9fe7af53bcaa1d2404e2b17a1f28aac4f Paypal PayPal.Me/cryptolabsZA

Vertex AI is a platform for end-to-end model development. It consist of core components that make the processes of MLOps possible for design patterns of all types.

This repository is dedicated to the learning and exchange of resources for the School of Artificial Intelligence at Anhui University. Notes will be published on this website first: https://www.aoaoaoao.cn and will be synchronized to the repository regularly. You can also contact me at [email protected].

AI Flow is an open-source, user-friendly UI application that empowers you to seamlessly connect multiple AI models together, specifically leveraging the capabilities of multiples AI APIs such as OpenAI, StabilityAI and Replicate. In a nutshell, AI Flow provides a visual platform for crafting and managing AI-driven workflows, thereby facilitating diverse and dynamic AI interactions.

This repository provides a curated list of papers, datasets, and resources related to the detection and mitigation of hallucinations in large language models (LLMs). Hallucinations refer to the generation of factually incorrect or nonsensical text by LLMs, which can be a significant challenge for their use in real-world applications. The resources in this repository aim to help researchers and practitioners better understand and address this issue.

This repository, LLaVA++, extends the visual capabilities of the LLaVA 1.5 model by incorporating the latest LLMs, Phi-3 Mini Instruct 3.8B, and LLaMA-3 Instruct 8B. It provides various models for instruction-following LMMS and academic-task-oriented datasets, along with training scripts for Phi-3-V and LLaMA-3-V. The repository also includes installation instructions and acknowledgments to related open-source contributions.

Mergoo is a library for easily merging multiple LLM experts and efficiently training the merged LLM. With Mergoo, you can efficiently integrate the knowledge of different generic or domain-based LLM experts. Mergoo supports several merging methods, including Mixture-of-Experts, Mixture-of-Adapters, and Layer-wise merging. It also supports various base models, including LLaMa, Mistral, and BERT, and trainers, including Hugging Face Trainer, SFTrainer, and PEFT. Mergoo provides flexible merging for each layer and supports training choices such as only routing MoE layers or fully fine-tuning the merged LLM.

This repository contains code for building cooperative embodied agents modularly with large language models. The agents are trained to perform tasks in two different environments: ThreeDWorld Multi-Agent Transport (TDW-MAT) and Communicative Watch-And-Help (C-WAH). TDW-MAT is a multi-agent environment where agents must transport objects to a goal position using containers. C-WAH is an extension of the Watch-And-Help challenge, which enables agents to send messages to each other. The code in this repository can be used to train agents to perform tasks in both of these environments.

llm-finetuning is a repository that provides a serverless twist to the popular axolotl fine-tuning library using Modal's serverless infrastructure. It allows users to quickly fine-tune any LLM model with state-of-the-art optimizations like Deepspeed ZeRO, LoRA adapters, Flash attention, and Gradient checkpointing. The repository simplifies the fine-tuning process by not exposing all CLI arguments, instead allowing users to specify options in a config file. It supports efficient training and scaling across multiple GPUs, making it suitable for production-ready fine-tuning jobs.

LLM-Tuning is a collection of tools and resources for fine-tuning large language models (LLMs). It includes a library of pre-trained LoRA models, a set of tutorials and examples, and a community forum for discussion and support. LLM-Tuning makes it easy to fine-tune LLMs for a variety of tasks, including text classification, question answering, and dialogue generation. With LLM-Tuning, you can quickly and easily improve the performance of your LLMs on downstream tasks.

The Awesome-LM-SSP repository is a collection of resources related to the trustworthiness of large models (LMs) across multiple dimensions, with a special focus on multi-modal LMs. It includes papers, surveys, toolkits, competitions, and leaderboards. The resources are categorized into three main dimensions: safety, security, and privacy. Within each dimension, there are several subcategories. For example, the safety dimension includes subcategories such as jailbreak, alignment, deepfake, ethics, fairness, hallucination, prompt injection, and toxicity. The security dimension includes subcategories such as adversarial examples, poisoning, and system security. The privacy dimension includes subcategories such as contamination, copyright, data reconstruction, membership inference attacks, model extraction, privacy-preserving computation, and unlearning.

GPT4Point is a unified framework for point-language understanding and generation. It aligns 3D point clouds with language, providing a comprehensive solution for tasks such as 3D captioning and controlled 3D generation. The project includes an automated point-language dataset annotation engine, a novel object-level point cloud benchmark, and a 3D multi-modality model. Users can train and evaluate models using the provided code and datasets, with a focus on improving models' understanding capabilities and facilitating the generation of 3D objects.

Vearch is a cloud-native distributed vector database designed for efficient similarity search of embedding vectors in AI applications. It supports hybrid search with vector search and scalar filtering, offers fast vector retrieval from millions of objects in milliseconds, and ensures scalability and reliability through replication and elastic scaling out. Users can deploy Vearch cluster on Kubernetes, add charts from the repository or locally, start with Docker-compose, or compile from source code. The tool includes components like Master for schema management, Router for RESTful API, and PartitionServer for hosting document partitions with raft-based replication. Vearch can be used for building visual search systems for indexing images and offers a Python SDK for easy installation and usage. The tool is suitable for AI developers and researchers looking for efficient vector search capabilities in their applications.

PaddleScience is a scientific computing suite developed based on the deep learning framework PaddlePaddle. It utilizes the learning ability of deep neural networks and the automatic (higher-order) differentiation mechanism of PaddlePaddle to solve problems in physics, chemistry, meteorology, and other fields. It supports three solving methods: physics mechanism-driven, data-driven, and mathematical fusion, and provides basic APIs and detailed documentation for users to use and further develop.

HuggingFaceGuidedTourForMac is a guided tour on how to install optimized pytorch and optionally Apple's new MLX, JAX, and TensorFlow on Apple Silicon Macs. The repository provides steps to install homebrew, pytorch with MPS support, MLX, JAX, TensorFlow, and Jupyter lab. It also includes instructions on running large language models using HuggingFace transformers. The repository aims to help users set up their Macs for deep learning experiments with optimized performance.

KG-LLM-Papers is a repository that collects papers integrating knowledge graphs (KGs) and large language models (LLMs). It serves as a comprehensive resource for research on the role of KGs in the era of LLMs, covering surveys, methods, and resources related to this integration.

Lean Copilot is a tool that enables the use of large language models (LLMs) in Lean for proof automation. It provides features such as suggesting tactics/premises, searching for proofs, and running inference of LLMs. Users can utilize built-in models from LeanDojo or bring their own models to run locally or on the cloud. The tool supports platforms like Linux, macOS, and Windows WSL, with optional CUDA and cuDNN for GPU acceleration. Advanced users can customize behavior using Tactic APIs and Model APIs. Lean Copilot also allows users to bring their own models through ExternalGenerator or ExternalEncoder. The tool comes with caveats such as occasional crashes and issues with premise selection and proof search. Users can get in touch through GitHub Discussions for questions, bug reports, feature requests, and suggestions. The tool is designed to enhance theorem proving in Lean using LLMs.

This repository provides a real-world trace dataset of LLM serving workloads for research and academic purposes. The dataset includes two files, BurstGPT.csv with trace data for 2 months including some failures, and BurstGPT_without_fails.csv without any failures. Users can scale the RPS in the trace, model patterns, and leverage the trace for various evaluations. Future plans include updating the time range of the trace, adding request end times, updating conversation logs, and open-sourcing a benchmark suite for LLM inference. The dataset covers 61 consecutive days, contains 1.4 million lines, and is approximately 50MB in size.

Firefly is an open-source large model training project that supports pre-training, fine-tuning, and DPO of mainstream large models. It includes models like Llama3, Gemma, Qwen1.5, MiniCPM, Llama, InternLM, Baichuan, ChatGLM, Yi, Deepseek, Qwen, Orion, Ziya, Xverse, Mistral, Mixtral-8x7B, Zephyr, Vicuna, Bloom, etc. The project supports full-parameter training, LoRA, QLoRA efficient training, and various tasks such as pre-training, SFT, and DPO. Suitable for users with limited training resources, QLoRA is recommended for fine-tuning instructions. The project has achieved good results on the Open LLM Leaderboard with QLoRA training process validation. The latest version has significant updates and adaptations for different chat model templates.

Lhotse is a Python library designed to make speech and audio data preparation flexible and accessible. It aims to attract a wider community to speech processing tasks by providing a Python-centric design and an expressive command-line interface. Lhotse offers standard data preparation recipes, PyTorch Dataset classes for speech tasks, and efficient data preparation for model training with audio cuts. It supports data augmentation, feature extraction, and feature-space cut mixing. The tool extends Kaldi's data preparation recipes with seamless PyTorch integration, human-readable text manifests, and convenient Python classes.

MathCoder is a repository focused on enhancing mathematical reasoning by fine-tuning open-source language models to use code for modeling and deriving math equations. It introduces MathCodeInstruct dataset with solutions interleaving natural language, code, and execution results. The repository provides MathCoder models capable of generating code-based solutions for challenging math problems, achieving state-of-the-art scores on MATH and GSM8K datasets. It offers tools for model deployment, inference, and evaluation, along with a citation for referencing the work.

Ragna is a RAG orchestration framework designed for managing workflows and orchestrating tasks. It provides a comprehensive set of features for users to streamline their processes and automate repetitive tasks. With Ragna, users can easily create, schedule, and monitor workflows, making it an ideal tool for teams and individuals looking to improve their productivity and efficiency. The framework offers extensive documentation, community support, and a user-friendly interface, making it accessible to users of all skill levels. Whether you are a developer, data scientist, or project manager, Ragna can help you simplify your workflow management and boost your overall performance.

Awesome-LLMs-for-Video-Understanding is a repository dedicated to exploring Video Understanding with Large Language Models. It provides a comprehensive survey of the field, covering models, pretraining, instruction tuning, and hybrid methods. The repository also includes information on tasks, datasets, and benchmarks related to video understanding. Contributors are encouraged to add new papers, projects, and materials to enhance the repository.

llm-swarm is a tool designed to manage scalable open LLM inference endpoints in Slurm clusters. It allows users to generate synthetic datasets for pretraining or fine-tuning using local LLMs or Inference Endpoints on the Hugging Face Hub. The tool integrates with huggingface/text-generation-inference and vLLM to generate text at scale. It manages inference endpoint lifetime by automatically spinning up instances via `sbatch`, checking if they are created or connected, performing the generation job, and auto-terminating the inference endpoints to prevent idling. Additionally, it provides load balancing between multiple endpoints using a simple nginx docker for scalability. Users can create slurm files based on default configurations and inspect logs for further analysis. For users without a Slurm cluster, hosted inference endpoints are available for testing with usage limits based on registration status.

Edgen is a local GenAI API server that serves as a drop-in replacement for OpenAI's API. It provides multi-endpoint support for chat completions and speech-to-text, is model agnostic, offers optimized inference, and features model caching. Built in Rust, Edgen is natively compiled for Windows, MacOS, and Linux, eliminating the need for Docker. It allows users to utilize GenAI locally on their devices for free and with data privacy. With features like session caching, GPU support, and support for various endpoints, Edgen offers a scalable, reliable, and cost-effective solution for running GenAI applications locally.

OpenAI Kotlin API client is a Kotlin client for OpenAI's API with multiplatform and coroutines capabilities. It allows users to interact with OpenAI's API using Kotlin programming language. The client supports various features such as models, chat, images, embeddings, files, fine-tuning, moderations, audio, assistants, threads, messages, and runs. It also provides guides on getting started, chat & function call, file source guide, and assistants. Sample apps are available for reference, and troubleshooting guides are provided for common issues. The project is open-source and licensed under the MIT license, allowing contributions from the community.

AudioSeal is a method for speech localized watermarking, designed with state-of-the-art robustness and detector speed. It jointly trains a generator to embed a watermark in audio and a detector to detect watermarked fragments in longer audios, even in the presence of editing. The tool achieves top-notch detection performance at the sample level, generates minimal alteration of signal quality, and is robust to various audio editing types. With a fast, single-pass detector, AudioSeal surpasses existing models in speed, making it ideal for large-scale and real-time applications.

Beyond LLM offers an all-in-one toolkit for experimentation, evaluation, and deployment of Retrieval-Augmented Generation (RAG) systems. It simplifies the process with automated integration, customizable evaluation metrics, and support for various Large Language Models (LLMs) tailored to specific needs. The aim is to reduce LLM hallucination risks and enhance reliability.

DataDreamer is a powerful open-source Python library designed for prompting, synthetic data generation, and training workflows. It is simple, efficient, and research-grade, allowing users to create prompting workflows, generate synthetic datasets, and train models with ease. The library is built for researchers, by researchers, focusing on correctness, best practices, and reproducibility. It offers features like aggressive caching, resumability, support for bleeding-edge techniques, and easy sharing of datasets and models. DataDreamer enables users to run multi-step prompting workflows, generate synthetic datasets for various tasks, and train models by aligning, fine-tuning, instruction-tuning, and distilling them using existing or synthetic data.

Open-DocLLM is an open-source project that addresses data extraction and processing challenges using OCR and LLM technologies. It consists of two main layers: OCR for reading document content and LLM for extracting specific content in a structured manner. The project offers a larger context window size compared to JP Morgan's DocLLM and integrates tools like Tesseract OCR and Mistral for efficient data analysis. Users can run the models on-premises using LLM studio or Ollama, and the project includes a FastAPI app for testing purposes.

Chinese-LLaMA-Alpaca-3 is a project based on Meta's latest release of the new generation open-source large model Llama-3. It is the third phase of the Chinese-LLaMA-Alpaca open-source large model series projects (Phase 1, Phase 2). This project open-sources the Chinese Llama-3 base model and the Chinese Llama-3-Instruct instruction fine-tuned large model. These models incrementally pre-train with a large amount of Chinese data on the basis of the original Llama-3 and further fine-tune using selected instruction data, enhancing Chinese basic semantics and instruction understanding capabilities. Compared to the second-generation related models, significant performance improvements have been achieved.

OntoGPT is a Python package for extracting structured information from text using large language models, instruction prompts, and ontology-based grounding. It provides a command line interface and a minimal web app for easy usage. The tool has been evaluated on test data and is used in related projects like TALISMAN for gene set analysis. OntoGPT enables users to extract information from text by specifying relevant terms and provides the extracted objects as output.

LLM_QLoRA is a repository for fine-tuning Large Language Models (LLMs) using QLoRA methodology. It provides scripts for training LLMs on custom datasets, pushing models to HuggingFace Hub, and performing inference. Additionally, it includes models trained on HuggingFace Hub, a blog post detailing the QLoRA fine-tuning process, and instructions for converting and quantizing models. The repository also addresses troubleshooting issues related to Python versions and dependencies.

Julep is an advanced platform for creating stateful and functional AI apps powered by large language models. It offers features like statefulness by design, automatic function calling, production-ready deployment, cron-like asynchronous functions, 90+ built-in tools, and the ability to switch between different LLMs easily. Users can build AI applications without the need to write code for embedding, saving, and retrieving conversation history, and can connect to third-party applications using Composio. Julep simplifies the process of getting started with AI apps, whether they are conversational, functional, or agentic.

AIKA (Artificial Intelligence for Knowledge Acquisition) is a new type of artificial neural network designed to mimic the behavior of a biological brain more closely and bridge the gap to classical AI. The network conceptually separates activations from neurons, creating two separate graphs to represent acquired knowledge and inferred information. It uses different types of neurons and synapses to propagate activation values, binding signals, causal relations, and training gradients. The network structure allows for flexible topology and supports the gradual population of neurons and synapses during training.

LitServe is a high-throughput serving engine for deploying AI models at scale. It generates an API endpoint for a model, handles batching, streaming, autoscaling across CPU/GPUs, and more. Built for enterprise scale, it supports every framework like PyTorch, JAX, Tensorflow, and more. LitServe is designed to let users focus on model performance, not the serving boilerplate. It is like PyTorch Lightning for model serving but with broader framework support and scalability.

LLM-as-HH is a codebase that accompanies the paper ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution. It introduces Language Hyper-Heuristics (LHHs) that leverage LLMs for heuristic generation with minimal manual intervention and open-ended heuristic spaces. Reflective Evolution (ReEvo) is presented as a searching framework that emulates the reflective design approach of human experts while surpassing human capabilities with scalable LLM inference, Internet-scale domain knowledge, and powerful evolutionary search. The tool can improve various algorithms on problems like Traveling Salesman Problem, Capacitated Vehicle Routing Problem, Orienteering Problem, Multiple Knapsack Problems, Bin Packing Problem, and Decap Placement Problem in both black-box and white-box settings.

LinGoose is a modular Go framework designed for building AI/LLM applications. It offers the flexibility to import only the necessary modules, abstracts features for customization, and provides a comprehensive solution for developing AI/LLM applications from scratch. The framework simplifies the process of creating intelligent applications by allowing users to choose preferred implementations or create their own. LinGoose empowers developers to leverage its capabilities to streamline the development of cutting-edge AI and LLM projects.

Groma is a grounded multimodal assistant that excels in region understanding and visual grounding. It can process user-defined region inputs and generate contextually grounded long-form responses. The tool presents a unique paradigm for multimodal large language models, focusing on visual tokenization for localization. Groma achieves state-of-the-art performance in referring expression comprehension benchmarks. The tool provides pretrained model weights and instructions for data preparation, training, inference, and evaluation. Users can customize training by starting from intermediate checkpoints. Groma is designed to handle tasks related to detection pretraining, alignment pretraining, instruction finetuning, instruction following, and more.

The fsdp_qlora repository provides a script for training Large Language Models (LLMs) with Quantized LoRA and Fully Sharded Data Parallelism (FSDP). It integrates FSDP+QLoRA into the Axolotl platform and offers installation instructions for dependencies like llama-recipes, fastcore, and PyTorch. Users can finetune Llama-2 70B on Dual 24GB GPUs using the provided command. The script supports various training options including full params fine-tuning, LoRA fine-tuning, custom LoRA fine-tuning, quantized LoRA fine-tuning, and more. It also discusses low memory loading, mixed precision training, and comparisons to existing trainers. The repository addresses limitations and provides examples for training with different configurations, including BnB QLoRA and HQQ QLoRA. Additionally, it offers SLURM training support and instructions for adding support for a new model.

The one-click-llms repository provides templates for quickly setting up an API for language models. It includes advanced inferencing scripts for function calling and offers various models for text generation and fine-tuning tasks. Users can choose between Runpod and Vast.AI for different GPU configurations, with recommendations for optimal performance. The repository also supports Trelis Research and offers templates for different model sizes and types, including multi-modal APIs and chat models.

TinyLLM is a project that helps build a small locally hosted language model with a web interface using consumer-grade hardware. It supports multiple language models, builds a local OpenAI API web service, and serves a Chatbot web interface with customizable prompts. The project requires specific hardware and software configurations for optimal performance. Users can run a local language model using inference servers like vLLM, llama-cpp-python, and Ollama. The Chatbot feature allows users to interact with the language model through a web-based interface, supporting features like summarizing websites, displaying news headlines, stock prices, weather conditions, and using vector databases for queries.

This repository, RLHF-Reward-Modeling, is dedicated to training reward models for DRL-based RLHF (PPO), Iterative SFT, and iterative DPO. It provides state-of-the-art performance in reward models with a base model size of up to 13B. The installation instructions involve setting up the environment and aligning the handbook. Dataset preparation requires preprocessing conversations into a standard format. The code can be run with Gemma-2b-it, and evaluation results can be obtained using provided datasets. The to-do list includes various reward models like Bradley-Terry, preference model, regression-based reward model, and multi-objective reward model. The repository is part of iterative rejection sampling fine-tuning and iterative DPO.

High Performance LLMs 2024 is a comprehensive course focused on building a high-performance Large Language Model (LLM) from scratch using Jax. The course covers various aspects such as training, inference, roofline analysis, compilation, sharding, profiling, and optimization techniques. Participants will gain a deep understanding of Jax and learn how to design high-performance computing systems that operate close to their physical limits.

xef.ai is a one-stop library designed to bring the power of modern AI to applications and services. It offers integration with Large Language Models (LLM), image generation, and other AI services. The library is packaged in two layers: core libraries for basic AI services integration and integrations with other libraries. xef.ai aims to simplify the transition to modern AI for developers by providing an idiomatic interface, currently supporting Kotlin. Inspired by LangChain and Hugging Face, xef.ai may transmit source code and user input data to third-party services, so users should review privacy policies and take precautions. Libraries are available in Maven Central under the `com.xebia` group, with `xef-core` as the core library. Developers can add these libraries to their projects and explore examples to understand usage.

GPTSwarm is a graph-based framework for LLM-based agents that enables the creation of LLM-based agents from graphs and facilitates the customized and automatic self-organization of agent swarms with self-improvement capabilities. The library includes components for domain-specific operations, graph-related functions, LLM backend selection, memory management, and optimization algorithms to enhance agent performance and swarm efficiency. Users can quickly run predefined swarms or utilize tools like the file analyzer. GPTSwarm supports local LM inference via LM Studio, allowing users to run with a local LLM model. The framework has been accepted by ICML2024 and offers advanced features for experimentation and customization.

Only Train Once (OTO) is an automatic, architecture-agnostic DNN training and compression framework that allows users to train a general DNN from scratch or a pretrained checkpoint to achieve high performance and slimmer architecture simultaneously in a one-shot manner without fine-tuning. The framework includes features for automatic structured pruning and erasing operators, as well as hybrid structured sparse optimizers for efficient model compression. OTO provides tools for pruning zero-invariant group partitioning, constructing pruned models, and visualizing pruning and erasing dependency graphs. It supports the HESSO optimizer and offers a sanity check for compliance testing on various DNNs. The repository also includes publications, installation instructions, quick start guides, and a roadmap for future enhancements and collaborations.

Boxcars is a Ruby gem that enables users to create new systems with AI composability, incorporating concepts such as LLMs, Search, SQL, Rails Active Record, Vector Search, and more. It allows users to work with Boxcars, Trains, Prompts, Engines, and VectorStores to solve problems and generate text results. The gem is designed to be user-friendly for beginners and can be extended with custom concepts. Boxcars is actively seeking ways to enhance security measures to prevent malicious actions. Users can use Boxcars for tasks like running calculations, performing searches, generating Ruby code for math operations, and interacting with APIs like OpenAI, Anthropic, and Google SERP.

Awesome-LLM-Interpretability is a curated list of materials related to LLM (Large Language Models) interpretability, covering tutorials, code libraries, surveys, videos, papers, and blogs. It includes resources on transformer mechanistic interpretability, visualization, interventions, probing, fine-tuning, feature representation, learning dynamics, knowledge editing, hallucination detection, and redundancy analysis. The repository aims to provide a comprehensive overview of tools, techniques, and methods for understanding and interpreting the inner workings of large language models.

LLM-jp-eval is a tool designed to automatically evaluate Japanese large language models across multiple datasets. It provides functionalities such as converting existing Japanese evaluation data to text generation task evaluation datasets, executing evaluations of large language models across multiple datasets, and generating instruction data (jaster) in the format of evaluation data prompts. Users can manage the evaluation settings through a config file and use Hydra to load them. The tool supports saving evaluation results and logs using wandb. Users can add new evaluation datasets by following specific steps and guidelines provided in the tool's documentation. It is important to note that using jaster for instruction tuning can lead to artificially high evaluation scores, so caution is advised when interpreting the results.

LLMLingua is a tool that utilizes a compact, well-trained language model to identify and remove non-essential tokens in prompts. This approach enables efficient inference with large language models, achieving up to 20x compression with minimal performance loss. The tool includes LLMLingua, LongLLMLingua, and LLMLingua-2, each offering different levels of prompt compression and performance improvements for tasks involving large language models.

Scalene is a high-performance CPU, GPU, and memory profiler for Python that provides detailed information and runs faster than many other profilers. It incorporates AI-powered proposed optimizations, allowing users to generate optimization suggestions by clicking on specific lines or regions of code. Scalene separates time spent in Python from native code, highlights hotspots, and identifies memory usage per line. It supports GPU profiling on NVIDIA-based systems and detects memory leaks. Users can generate reduced profiles, profile specific functions using decorators, and suspend/resume profiling for background processes. Scalene is available as a pip or conda package and works on various platforms. It offers features like profiling at the line level, memory trends, copy volume reporting, and leak detection.

Open AI is a powerful tool for artificial intelligence research and development. It provides a wide range of machine learning models and algorithms, making it easier for developers to create innovative AI applications. With Open AI, users can explore cutting-edge technologies such as natural language processing, computer vision, and reinforcement learning. The platform offers a user-friendly interface and comprehensive documentation to support users in building and deploying AI solutions. Whether you are a beginner or an experienced AI practitioner, Open AI offers the tools and resources you need to accelerate your AI projects and stay ahead in the rapidly evolving field of artificial intelligence.

OAD is a powerful open-source tool for analyzing and visualizing data. It provides a user-friendly interface for exploring datasets, generating insights, and creating interactive visualizations. With OAD, users can easily import data from various sources, clean and preprocess data, perform statistical analysis, and create customizable visualizations to communicate findings effectively. Whether you are a data scientist, analyst, or researcher, OAD can help you streamline your data analysis workflow and uncover valuable insights from your data.

Prometheus-Eval is a repository dedicated to evaluating large language models (LLMs) in generation tasks. It provides state-of-the-art language models like Prometheus 2 (7B & 8x7B) for assessing in pairwise ranking formats and achieving high correlation scores with benchmarks. The repository includes tools for training, evaluating, and using these models, along with scripts for fine-tuning on custom datasets. Prometheus aims to address issues like fairness, controllability, and affordability in evaluations by simulating human judgments and proprietary LM-based assessments.

Awesome-LLM is a curated list of resources related to large language models, focusing on papers, projects, frameworks, tools, tutorials, courses, opinions, and other useful resources in the field. It covers trending LLM projects, milestone papers, other papers, open LLM projects, LLM training frameworks, LLM evaluation frameworks, tools for deploying LLM, prompting libraries & tools, tutorials, courses, books, and opinions. The repository provides a comprehensive overview of the latest advancements and resources in the field of large language models.

Embedchain is an Open Source Framework for personalizing LLM responses. It simplifies the creation and deployment of personalized AI applications by efficiently managing unstructured data, generating relevant embeddings, and storing them in a vector database. With diverse APIs, users can extract contextual information, find precise answers, and engage in interactive chat conversations tailored to their data. The framework follows the design principle of being 'Conventional but Configurable' to cater to both software engineers and machine learning engineers.

This repository is designed to inject backdoors into Language Model Models (LLMs) for code. The injected backdoors serve as timestamps for the training dataset of the LLMs. The code is randomly generated and includes watermark backdoors to show specific behaviors. A script automatically updates the repository with a new backdoor every month. Validating the existence of the backdoor can infer when the training dataset was collected. The backdoors are constructed in a specific format, and verifying them may require multiple tries. The repository keeps a record of backdoors injected along with associated dates.

AgentBench is a benchmark designed to evaluate Large Language Models (LLMs) as autonomous agents in various environments. It includes 8 distinct environments such as Operating System, Database, Knowledge Graph, Digital Card Game, and Lateral Thinking Puzzles. The tool provides a comprehensive evaluation of LLMs' ability to operate as agents by offering Dev and Test sets for each environment. Users can quickly start using the tool by following the provided steps, configuring the agent, starting task servers, and assigning tasks. AgentBench aims to bridge the gap between LLMs' proficiency as agents and their practical usability.

LLMFarm is an iOS and MacOS app designed to work with large language models (LLM). It allows users to load different LLMs with specific parameters, test the performance of various LLMs on iOS and macOS, and identify the most suitable model for their projects. The tool is based on ggml and llama.cpp by Georgi Gerganov and incorporates sources from rwkv.cpp by saharNooby, Mia by byroneverson, and LlamaChat by alexrozanski. LLMFarm features support for MacOS (13+) and iOS (16+), various inferences and sampling methods, Metal compatibility (not supported on Intel Mac), model setting templates, LoRA adapters support, LoRA finetune support, LoRA export as model support, and more. It also offers a range of inferences including LLaMA, GPTNeoX, Replit, GPT2, Starcoder, RWKV, Falcon, MPT, Bloom, and others. Additionally, it supports multimodal models like LLaVA, Obsidian, and MobileVLM. Users can customize inference options through JSON files and access supported models for download.

Humanoid-Gym is a reinforcement learning framework designed for training locomotion skills for humanoid robots, focusing on zero-shot transfer from simulation to real-world environments. It integrates a sim-to-sim framework from Isaac Gym to Mujoco for verifying trained policies in different physical simulations. The codebase is verified with RobotEra's XBot-S and XBot-L humanoid robots. It offers comprehensive training guidelines, step-by-step configuration instructions, and execution scripts for easy deployment. The sim2sim support allows transferring trained policies to accurate simulated environments. The upcoming features include Denoising World Model Learning and Dexterous Hand Manipulation. Installation and usage guides are provided along with examples for training PPO policies and sim-to-sim transformations. The code structure includes environment and configuration files, with instructions on adding new environments. Troubleshooting tips are provided for common issues, along with a citation and acknowledgment section.

GOLEM is an open-source AI framework focused on optimization and learning of structured graph-based models using meta-heuristic methods. It emphasizes the potential of meta-heuristics in complex problem spaces where gradient-based methods are not suitable, and the importance of structured models in various problem domains. The framework offers features like structured model optimization, metaheuristic methods, multi-objective optimization, constrained optimization, extensibility, interpretability, and reproducibility. It can be applied to optimization problems represented as directed graphs with defined fitness functions. GOLEM has applications in areas like AutoML, Bayesian network structure search, differential equation discovery, geometric design, and neural architecture search. The project structure includes packages for core functionalities, adapters, graph representation, optimizers, genetic algorithms, utilities, serialization, visualization, examples, and testing. Contributions are welcome, and the project is supported by ITMO University's Research Center Strong Artificial Intelligence in Industry.

Spark AI Free 服务 provides high-speed streaming output, multi-turn dialogue support, AI drawing support, long document interpretation, and image parsing. It offers zero-configuration deployment, multi-token support, and automatic session trace cleaning. It is fully compatible with the ChatGPT interface. The repository includes multiple free-api projects for various AI services. Users can access the API for tasks such as chat completions, AI drawing, document interpretation, image analysis, and ssoSessionId live checking. The project also provides guidelines for deployment using Docker, Docker-compose, Render, Vercel, and native deployment methods. It recommends using custom clients for faster and simpler access to the free-api series projects.

Qwen AI Free service supports high-speed streaming output, multi-turn dialogue, watermark-free AI drawing, long document interpretation, image parsing, zero-configuration deployment, multi-token support, automatic session trace cleaning. It is fully compatible with the ChatGPT interface. The repository provides various free APIs for different AI services. Users can access the service through different deployment methods like Docker, Docker-compose, Render, Vercel, and native deployment. It offers interfaces for chat completions, AI drawing, document interpretation, image parsing, and token checking. Users need to provide 'login_tongyi_ticket' for authorization. The project emphasizes research, learning, and personal use only, discouraging commercial use to avoid service pressure on the official platform.

Fairseq is a sequence modeling toolkit that enables researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. It provides reference implementations of various sequence modeling papers covering CNN, LSTM networks, Transformer networks, LightConv, DynamicConv models, Non-autoregressive Transformers, Finetuning, and more. The toolkit supports multi-GPU training, fast generation on CPU and GPU, mixed precision training, extensibility, flexible configuration based on Hydra, and full parameter and optimizer state sharding. Pre-trained models are available for translation and language modeling with a torch.hub interface. Fairseq also offers pre-trained models and examples for tasks like XLS-R, cross-lingual retrieval, wav2vec 2.0, unsupervised quality estimation, and more.

AIdea is an app that integrates mainstream large language models and drawing models, developed using Flutter. The code is completely open-source and supports various functions such as GPT-3.5, GPT-4 from OpenAI, Claude instant, Claude 2.1 from Anthropic, Gemini Pro and visual language models from Google, as well as various Chinese and open-source models. It also supports features like text-to-image, super-resolution, coloring black and white images, artistic fonts, artistic QR codes, and more.

AIdea Server is an open-source Golang-based server that integrates mainstream large language models and drawing models. It supports various functionalities including OpenAI's GPT-3.5 and GPT-4, Anthropic's Claude instant and Claude 2.1, Google's Gemini Pro, as well as Chinese models like Tongyi Qianwen, Wenxin Yiyuan, and more. It also supports open-source large models like Yi 34B, Llama2, and AquilaChat 7B. Additionally, it provides features for text-to-image, super-resolution, coloring black and white images, generating art fonts and QR codes, among others.

Ollamac is a macOS app designed for interacting with Ollama models. It is optimized for macOS, allowing users to easily use any model from the Ollama library. The app features a user-friendly interface, chat archive for saving interactions, and real-time communication using HTTP streaming technology. Ollamac is open-source, enabling users to contribute to its development and enhance its capabilities. It requires macOS 14 or later and the Ollama system to be installed on the user's Mac with at least one Ollama model downloaded.

Time-LLM is a reprogramming framework that repurposes large language models (LLMs) for time series forecasting. It allows users to treat time series analysis as a 'language task' and effectively leverage pre-trained LLMs for forecasting. The framework involves reprogramming time series data into text representations and providing declarative prompts to guide the LLM reasoning process. Time-LLM supports various backbone models such as Llama-7B, GPT-2, and BERT, offering flexibility in model selection. The tool provides a general framework for repurposing language models for time series forecasting tasks.

MLX-VLM is a package designed for running Vision LLMs on Mac systems using MLX. It provides a convenient way to install and utilize the package for processing large language models related to vision tasks. The tool simplifies the process of running LLMs on Mac computers, offering a seamless experience for users interested in leveraging MLX for vision-related projects.

The enhance_llm repository contains three main parts: 1. Vector model domain fine-tuning based on llama_index and qwen fine-tuning BGE vector model. 2. Large model domain fine-tuning based on PEFT fine-tuning qwen1.5-7b-chat, with sft and dpo. 3. High-order retrieval enhanced generation (RAG) system based on the above domain work, implementing a two-stage RAG system. It includes query rewriting, recall reordering, retrieval reordering, multi-turn dialogue, and more. The repository also provides hardware and environment configurations along with star history and licensing information.

MMMU is a benchmark designed to evaluate multimodal models on college-level subject knowledge tasks, covering 30 subjects and 183 subfields with 11.5K questions. It focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of various models highlights substantial challenges, with room for improvement to stimulate the community towards expert artificial general intelligence (AGI).

FigStep is a black-box jailbreaking algorithm against large vision-language models (VLMs). It feeds harmful instructions through the image channel and uses benign text prompts to induce VLMs to output contents that violate common AI safety policies. The tool highlights the vulnerability of VLMs to jailbreaking attacks, emphasizing the need for safety alignments between visual and textual modalities.

EvalPlus is a rigorous evaluation framework for LLM4Code, providing HumanEval+ and MBPP+ tests to evaluate large language models on code generation tasks. It offers precise evaluation and ranking, coding rigorousness analysis, and pre-generated code samples. Users can use EvalPlus to generate code solutions, post-process code, and evaluate code quality. The tool includes tools for code generation and test input generation using various backends.

Quantus is a toolkit designed for the evaluation of neural network explanations. It offers more than 30 metrics in 6 categories for eXplainable Artificial Intelligence (XAI) evaluation. The toolkit supports different data types (image, time-series, tabular, NLP) and models (PyTorch, TensorFlow). It provides built-in support for explanation methods like captum, tf-explain, and zennit. Quantus is under active development and aims to provide a comprehensive set of quantitative evaluation metrics for XAI methods.

Minic is a chess engine developed for learning about chess programming and modern C++. It is compatible with CECP and UCI protocols, making it usable in various software. Minic has evolved from a one-file code to a more classic C++ style, incorporating features like evaluation tuning, perft, tests, and more. It has integrated NNUE frameworks from Stockfish and Seer implementations to enhance its strength. Minic is currently ranked among the top engines with an Elo rating around 3400 at CCRL scale.

SwanLab is an open-source, lightweight AI experiment tracking tool that provides a platform for tracking, comparing, and collaborating on experiments, aiming to accelerate the research and development efficiency of AI teams by 100 times. It offers a friendly API and a beautiful interface, combining hyperparameter tracking, metric recording, online collaboration, experiment link sharing, real-time message notifications, and more. With SwanLab, researchers can document their training experiences, seamlessly communicate and collaborate with collaborators, and machine learning engineers can develop models for production faster.

Instruct NER is a solution for complex Named Entity Recognition tasks, including Nested NER, based on modern Large Language Models (LLMs). It provides tools for dataset creation, training, automatic metric calculation, inference, error analysis, and model implementation. Users can create instructions for LLM, build dictionaries with labels, and generate model input templates. The tool supports various entity types and datasets, such as RuDReC, NEREL-BIO, CoNLL-2003, and MultiCoNER II. It offers training scripts for LLMs and metric calculation functions. Instruct NER models like Llama, Mistral, T5, and RWKV are implemented, with HuggingFace models available for adaptation and merging.

seemore is a vision language model developed in Pytorch, implementing components like image encoder, vision-language projector, and decoder language model. The model is built from scratch, including attention mechanisms and patch creation. It is designed for readability and hackability, with the intention to be improved upon. The implementation is based on public publications and borrows attention mechanism from makemore by Andrej Kapathy. The code was developed on Databricks using a single A100 for compute, and MLFlow is used for tracking metrics. The tool aims to provide a simplistic version of vision language models like Grok 1.5/GPT-4 Vision, suitable for experimentation and learning.

The NaLLM project repository explores the synergies between Neo4j and Large Language Models (LLMs) through three primary use cases: Natural Language Interface to a Knowledge Graph, Creating a Knowledge Graph from Unstructured Data, and Generating a Report using static and LLM data. The repository contains backend and frontend code organized for easy navigation. It includes blog posts, a demo database, instructions for running demos, and guidelines for contributing. The project aims to showcase the potential of Neo4j and LLMs in various applications.

Xwin-LM is a powerful and stable open-source tool for aligning large language models, offering various alignment technologies like supervised fine-tuning, reward models, reject sampling, and reinforcement learning from human feedback. It has achieved top rankings in benchmarks like AlpacaEval and surpassed GPT-4. The tool is continuously updated with new models and features.

LLMBox is a comprehensive library designed for implementing Large Language Models (LLMs) with a focus on a unified training pipeline and comprehensive model evaluation. It serves as a one-stop solution for training and utilizing LLMs, offering flexibility and efficiency in both training and utilization stages. The library supports diverse training strategies, comprehensive datasets, tokenizer vocabulary merging, data construction strategies, parameter efficient fine-tuning, and efficient training methods. For utilization, LLMBox provides comprehensive evaluation on various datasets, in-context learning strategies, chain-of-thought evaluation, evaluation methods, prefix caching for faster inference, support for specific LLM models like vLLM and Flash Attention, and quantization options. The tool is suitable for researchers and developers working with LLMs for natural language processing tasks.

ICE-Score is a tool designed to instruct large language models to evaluate code. It provides a minimum viable product (MVP) for evaluating generated code snippets using inputs such as problem, output, task, aspect, and model. Users can also evaluate with reference code and enable zero-shot chain-of-thought evaluation. The tool is built on codegen-metrics and code-bert-score repositories and includes datasets like CoNaLa and HumanEval. ICE-Score has been accepted to EACL 2024.

The 'create-million-parameter-llm-from-scratch' repository provides a detailed guide on creating a Large Language Model (LLM) with 2.3 million parameters from scratch. The blog replicates the LLaMA approach, incorporating concepts like RMSNorm for pre-normalization, SwiGLU activation function, and Rotary Embeddings. The model is trained on a basic dataset to demonstrate the ease of creating a million-parameter LLM without the need for a high-end GPU.

YaneuraOu is the World's Strongest Shogi engine (AI player), winner of WCSC29 and other prestigious competitions. It is an educational and USI compliant engine that supports various features such as Ponder, MultiPV, and ultra-parallel search. The engine is known for its compatibility with different platforms like Windows, Ubuntu, macOS, and ARM. Additionally, YaneuraOu offers a standard opening book format, on-the-fly opening book support, and various maintenance commands for opening books. With a massive transposition table size of up to 33TB, YaneuraOu is a powerful and versatile tool for Shogi enthusiasts and developers.

Co-LLM (Collaborative Language Models) is a tool for learning to decode collaboratively with multiple language models. It provides a method for data processing, training, and inference using a collaborative approach. The tool involves steps such as formatting/tokenization, scoring logits, initializing Z vector, deferral training, and generating results using multiple models. Co-LLM supports training with different collaboration pairs and provides baseline training scripts for various models. In inference, it uses 'vllm' services to orchestrate models and generate results through API-like services. The tool is inspired by allenai/open-instruct and aims to improve decoding performance through collaborative learning.

LLM Finetuning toolkit is a config-based CLI tool for launching a series of LLM fine-tuning experiments on your data and gathering their results. It allows users to control all elements of a typical experimentation pipeline - prompts, open-source LLMs, optimization strategy, and LLM testing - through a single YAML configuration file. The toolkit supports basic, intermediate, and advanced usage scenarios, enabling users to run custom experiments, conduct ablation studies, and automate fine-tuning workflows. It provides features for data ingestion, model definition, training, inference, quality assurance, and artifact outputs, making it a comprehensive tool for fine-tuning large language models.

BoCoEL is a tool that leverages Bayesian Optimization to efficiently evaluate large language models by selecting a subset of the corpus for evaluation. It encodes individual entries into embeddings, uses Bayesian optimization to select queries, retrieves from the corpus, and provides easily managed evaluations. The tool aims to reduce computation costs during evaluation with a dynamic budget, supporting models like GPT2, Pythia, and LLAMA through integration with Hugging Face transformers and datasets. BoCoEL offers a modular design and efficient representation of the corpus to enhance evaluation quality.

Prompt Panel is a tool designed to accelerate the adoption of AI agents by providing a platform where users can run large language models across any inference provider, create custom agent plugins, and use their own data safely. The tool allows users to break free from walled-gardens and have full control over their models, conversations, and logic. With Prompt Panel, users can pair their data with any language model, online or offline, and customize the system to meet their unique business needs without any restrictions.

This repository evaluates Large Language Models (LLMs) trained on PGN format chess games using linear probes. It assesses the LLMs' internal understanding of board state and their ability to estimate player skill levels. The repo provides tools to train, evaluate, and visualize linear probes on LLMs trained to play chess with PGN strings. Users can visualize the model's predictions, perform interventions on the model's internal board state, and analyze board state and player skill level accuracy across different LLMs. The experiments in the repo can be conducted with less than 1 GB of VRAM, and training probes on the 8 layer model takes about 10 minutes on an RTX 3050. The repo also includes scripts for performing board state interventions and skill interventions, along with useful links to open-source code, models, datasets, and pretrained models.

AiOS is a tool for human pose and shape estimation, performing human localization and SMPL-X estimation in a progressive manner. It consists of body localization, body refinement, and whole-body refinement stages. Users can download datasets for evaluation, SMPL-X body models, and AiOS checkpoint. Installation involves creating a conda virtual environment, installing PyTorch, torchvision, Pytorch3D, MMCV, and other dependencies. Inference requires placing the video for inference and pretrained models in specific directories. Test results are provided for NMVE, NMJE, MVE, and MPJPE on datasets like BEDLAM and AGORA. Users can run scripts for AGORA validation, AGORA test leaderboard, and BEDLAM leaderboard. The tool acknowledges codes from MMHuman3D, ED-Pose, and SMPLer-X.

Forust is a lightweight package for building gradient boosted decision tree ensembles. The algorithm code is written in Rust with a Python wrapper. It implements the same algorithm as XGBoost and provides nearly identical results. The package was developed to better understand XGBoost, as a fun project in Rust, and to experiment with adding new features to the algorithm in a simpler codebase. Forust allows training gradient boosted decision tree ensembles with multiple objective functions, predicting on datasets, inspecting model structures, calculating feature importance, and saving/loading trained boosters.

SWE-agent is a tool that turns language models (e.g. GPT-4) into software engineering agents capable of fixing bugs and issues in real GitHub repositories. It achieves state-of-the-art performance on the full test set by resolving 12.29% of issues. The tool is built and maintained by researchers from Princeton University. SWE-agent provides a command line tool and a graphical web interface for developers to interact with. It introduces an Agent-Computer Interface (ACI) to facilitate browsing, viewing, editing, and executing code files within repositories. The tool includes features such as a linter for syntax checking, a specialized file viewer, and a full-directory string searching command to enhance the agent's capabilities. SWE-agent aims to improve prompt engineering and ACI design to enhance the performance of language models in software engineering tasks.

NPi is an open-source platform providing Tool-use APIs to empower AI agents with the ability to take action in the virtual world. It is currently under active development, and the APIs are subject to change in future releases. NPi offers a command line tool for installation and setup, along with a GitHub app for easy access to repositories. The platform also includes a Python SDK and examples like Calendar Negotiator and Twitter Crawler. Join the NPi community on Discord to contribute to the development and explore the roadmap for future enhancements.

AlphaFold3 is an implementation of the Alpha Fold 3 model in PyTorch for accurate structure prediction of biomolecular interactions. It includes modules for genetic diffusion and full model examples for forward pass computations. The tool allows users to generate random pair and single representations, operate on atomic coordinates, and perform structure predictions based on input tensors. The implementation also provides functionalities for training and evaluating the model.

qlora-pipe is a pipeline parallel training script designed for efficiently training large language models that cannot fit on one GPU. It supports QLoRA, LoRA, and full fine-tuning, with efficient model loading and the ability to load any dataset that Axolotl can handle. The script allows for raw text training, resuming training from a checkpoint, logging metrics to Tensorboard, specifying a separate evaluation dataset, training on multiple datasets simultaneously, and supports various models like Llama, Mistral, Mixtral, Qwen-1.5, and Cohere (Command R). It handles pipeline- and data-parallelism using Deepspeed, enabling users to set the number of GPUs, pipeline stages, and gradient accumulation steps for optimal utilization.

Evalverse is an open-source project designed to support Large Language Model (LLM) evaluation needs. It provides a standardized and user-friendly solution for processing and managing LLM evaluations, catering to AI research engineers and scientists. Evalverse supports various evaluation methods, insightful reports, and no-code evaluation processes. Users can access unified evaluation with submodules, request evaluations without code via Slack bot, and obtain comprehensive reports with scores, rankings, and visuals. The tool allows for easy comparison of scores across different models and swift addition of new evaluation tools.

Amber is the first model in the LLM360 family, an initiative for comprehensive and fully open-sourced LLMs. It is a 7B English language model with the LLaMA architecture. The model type is a language model with the same architecture as LLaMA-7B. It is licensed under Apache 2.0. The resources available include training code, data preparation, metrics, and fully processed Amber pretraining data. The model has been trained on various datasets like Arxiv, Book, C4, Refined-Web, StarCoder, StackExchange, and Wikipedia. The hyperparameters include a total of 6.7B parameters, hidden size of 4096, intermediate size of 11008, 32 attention heads, 32 hidden layers, RMSNorm ε of 1e^-6, max sequence length of 2048, and a vocabulary size of 32000.

This repository contains the code to prepare the data for the Amber 7B language model. The final training data comes from three sources: RedPajama V1, RefinedWeb, and StarCoderData. The data preparation involves downloading untokenized data, tokenizing the data using the Huggingface tokenizer, concatenating tokens into 2048 token sequences, merging datasets, and splitting the merged dataset into 360 chunks. Each tokenized data chunk is a jsonl file containing samples with 2049 tokens. The repository provides scripts for downloading datasets, tokenizing and concatenating sequences, validating data, and merging subsets into chunks.

The 'fms-fsdp' repository is a companion to the Foundation Model Stack, providing a (pre)training example to efficiently train FMS models, specifically Llama2, using native PyTorch features like FSDP for training and SDPA implementation of Flash attention v2. It focuses on leveraging FSDP for training efficiently, not as an end-to-end framework. The repo benchmarks training throughput on different GPUs, shares strategies, and provides installation and training instructions. It trained a model on IBM curated data achieving high efficiency and performance metrics.

SoM-LLaVA is a new data source and learning paradigm for Multimodal LLMs, empowering open-source Multimodal LLMs with Set-of-Mark prompting and improved visual reasoning ability. The repository provides a new dataset that is complementary to existing training sources, enhancing multimodal LLMs with Set-of-Mark prompting and improved general capacity. By adding 30k SoM data to the visual instruction tuning stage of LLaVA, the tool achieves 1% to 6% relative improvements on all benchmarks. Users can train SoM-LLaVA via command line and utilize the implementation to annotate COCO images with SoM. Additionally, the tool can be loaded in Huggingface for further usage.

This repository provides all the necessary items to build a Language Model from scratch, inspired by Karpathy's nanoGPT and Shakespeare generator. It includes data collection tools, data processing scripts, various models like BERT, GPT, and Seq-2-Seq, along with tokenizer and training files.

Chinese-Tiny-LLM is a repository containing procedures for cleaning Chinese web corpora and pre-training code. It introduces CT-LLM, a 2B parameter language model focused on the Chinese language. The model primarily uses Chinese data from a 1,200 billion token corpus, showing excellent performance in Chinese language tasks. The repository includes tools for filtering, deduplication, and pre-training, aiming to encourage further research and innovation in language model development.

The KAN-GPT repository is a PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling. It provides a model for generating text based on prompts, with a focus on improving performance compared to traditional MLP-GPT models. The repository includes scripts for training the model, downloading datasets, and evaluating model performance. Development tasks include integrating with other libraries, testing, and documentation.

SuperAGI is an open-source framework designed to build, manage, and run autonomous AI agents. It enables developers to create production-ready and scalable agents, extend agent capabilities with toolkits, and interact with agents through a graphical user interface. The framework allows users to connect to multiple Vector DBs, optimize token usage, store agent memory, utilize custom fine-tuned models, and automate tasks with predefined steps. SuperAGI also provides a marketplace for toolkits that enable agents to interact with external systems and third-party plugins.

NeoGPT is an AI assistant that transforms your local workspace into a powerhouse of productivity from your CLI. With features like code interpretation, multi-RAG support, vision models, and LLM integration, NeoGPT redefines how you work and create. It supports executing code seamlessly, multiple RAG techniques, vision models, and interacting with various language models. Users can run the CLI to start using NeoGPT and access features like Code Interpreter, building vector database, running Streamlit UI, and changing LLM models. The tool also offers magic commands for chat sessions, such as resetting chat history, saving conversations, exporting settings, and more. Join the NeoGPT community to experience a new era of efficiency and contribute to its evolution.

rag-chatbot is a tool that allows users to chat with multiple PDFs using Ollama and LlamaIndex. It provides an easy setup for running on local machines or Kaggle notebooks. Users can leverage models from Huggingface and Ollama, process multiple PDF inputs, and chat in multiple languages. The tool offers a simple UI with Gradio, supporting chat with history and QA modes. Setup instructions are provided for both Kaggle and local environments, including installation steps for Docker, Ollama, Ngrok, and the rag_chatbot package. Users can run the tool locally and access it via a web interface. Future enhancements include adding evaluation, better embedding models, knowledge graph support, improved document processing, MLX model integration, and Corrective RAG.

LLM4Decompile is an open-source large language model dedicated to decompilation of Linux x86_64 binaries, supporting GCC's O0 to O3 optimization levels. It focuses on assessing re-executability of decompiled code through HumanEval-Decompile benchmark. The tool includes models with sizes ranging from 1.3 billion to 33 billion parameters, available on Hugging Face. Users can preprocess C code into binary and assembly instructions, then decompile assembly instructions into C using LLM4Decompile. Ongoing efforts aim to expand capabilities to support more architectures and configurations, integrate with decompilation tools like Ghidra and Rizin, and enhance performance with larger training datasets.

LLM Steer is a Python module designed to steer Large Language Models (LLMs) towards specific topics or subjects by adding steer vectors to different layers of the model. It enhances the model's capabilities, such as providing correct responses to logical puzzles. The tool should be used in conjunction with the transformers library. Users can add steering vectors to specific layers of the model with coefficients and text, retrieve applied steering vectors, and reset all steering vectors to the initial model. Advanced usage involves changing default parameters, but it may lead to the model outputting gibberish in most cases. The tool is meant for experimentation and can be used to enhance role-play characteristics in LLMs.

LLM4IR-Survey is a collection of papers related to large language models for information retrieval, organized according to the survey paper 'Large Language Models for Information Retrieval: A Survey'. It covers various aspects such as query rewriting, retrievers, rerankers, readers, search agents, and more, providing insights into the integration of large language models with information retrieval systems.

GrAIdient is a framework designed to enable the development of deep learning models using the internal GPU of a Mac. It provides access to the graph of layers, allowing for unique model design with greater understanding, control, and reproducibility. The goal is to challenge the understanding of deep learning models, transitioning from black box to white box models. Key features include direct access to layers, native Mac GPU support, Swift language implementation, gradient checking, PyTorch interoperability, and more. The documentation covers main concepts, architecture, and examples. GrAIdient is MIT licensed.

The Octopus-v4 project aims to build the world's largest graph of language models, integrating specialized models and training Octopus models to connect nodes efficiently. The project focuses on identifying, training, and connecting specialized models. The repository includes scripts for running the Octopus v4 model, methods for managing the graph, training code for specialized models, and inference code. Environment setup instructions are provided for Linux with NVIDIA GPU. The Octopus v4 model helps users find suitable models for tasks and reformats queries for effective processing. The project leverages Language Large Models for various domains and provides benchmark results. Users are encouraged to train and add specialized models following recommended procedures.

Caissa is a strong, UCI command-line chess engine optimized for regular chess, FRC, and DFRC. It features its own neural network trained with self-play games, supports various UCI options, and provides different EXE versions for different CPU architectures. The engine uses advanced search algorithms, neural network evaluation, and endgame tablebases. It offers outstanding performance in ultra-short games and is written in C++ with modules for backend, frontend, and utilities like neural network trainer and self-play data generator.

Fast-stable-diffusion is a project that offers notebooks for RunPod, Paperspace, and Colab Pro adaptations with AUTOMATIC1111 Webui and Dreambooth. It provides tools for running and implementing Dreambooth, a stable diffusion project. The project includes implementations by XavierXiao and is sponsored by Runpod, Paperspace, and Colab Pro.

AgentForge is a low-code framework tailored for the rapid development, testing, and iteration of AI-powered autonomous agents and Cognitive Architectures. It is compatible with a range of LLM models and offers flexibility to run different models for different agents based on specific needs. The framework is designed for seamless extensibility and database-flexibility, making it an ideal playground for various AI projects. AgentForge is a beta-testing ground and future-proof hub for crafting intelligent, model-agnostic autonomous agents.

Dialog is an API-focused tool designed to simplify the deployment of Large Language Models (LLMs) for programmers interested in AI. It allows users to deploy any LLM based on the structure provided by dialog-lib, enabling them to spend less time coding and more time training their models. The tool aims to humanize Retrieval-Augmented Generative Models (RAGs) and offers features for better RAG deployment and maintenance. Dialog requires a knowledge base in CSV format and a prompt configuration in TOML format to function effectively. It provides functionalities for loading data into the database, processing conversations, and connecting to the LLM, with options to customize prompts and parameters. The tool also requires specific environment variables for setup and configuration.

STaRK is a large-scale semi-structure retrieval benchmark on Textual and Relational Knowledge Bases. It provides natural-sounding and practical queries crafted to incorporate rich relational information and complex textual properties, closely mirroring real-life scenarios. The benchmark aims to assess how effectively large language models can handle the interplay between textual and relational requirements in queries, using three diverse knowledge bases constructed from public sources.

Awesome Mamba is a curated collection of groundbreaking research papers and articles on Mamba Architecture, a pioneering framework in deep learning known for its selective state spaces and efficiency in processing complex data structures. The repository offers a comprehensive exploration of Mamba architecture through categorized research papers covering various domains like visual recognition, speech processing, remote sensing, video processing, activity recognition, image enhancement, medical imaging, reinforcement learning, natural language processing, 3D recognition, multi-modal understanding, time series analysis, graph neural networks, point cloud analysis, and tabular data handling.

ALMA (Advanced Language Model-based Translator) is a many-to-many LLM-based translation model that utilizes a two-step fine-tuning process on monolingual and parallel data to achieve strong translation performance. ALMA-R builds upon ALMA models with LoRA fine-tuning and Contrastive Preference Optimization (CPO) for even better performance, surpassing GPT-4 and WMT winners. The repository provides ALMA and ALMA-R models, datasets, environment setup, evaluation scripts, training guides, and data information for users to leverage these models for translation tasks.

This repository focuses on exploring tools that enhance the performance of language models for various tasks. It provides a structured list of literature relevant to tool-augmented language models, covering topics such as tool basics, tool use paradigm, scenarios, advanced methods, and evaluation. The repository includes papers, preprints, and books that discuss the use of tools in conjunction with language models for tasks like reasoning, question answering, mathematical calculations, accessing knowledge, interacting with the world, and handling non-textual modalities.

Anima is the first open-source 33B Chinese large language model based on QLoRA, supporting DPO alignment training and open-sourcing a 100k context window model. The latest update includes AirLLM, a library that enables inference of 70B LLM from a single GPU with just 4GB memory. The tool optimizes memory usage for inference, allowing large language models to run on a single 4GB GPU without the need for quantization or other compression techniques. Anima aims to democratize AI by making advanced models accessible to everyone and contributing to the historical process of AI democratization.

Data-to-paper is an AI-driven framework designed to guide users through the process of conducting end-to-end scientific research, starting from raw data to the creation of comprehensive and human-verifiable research papers. The framework leverages a combination of LLM and rule-based agents to assist in tasks such as hypothesis generation, literature search, data analysis, result interpretation, and paper writing. It aims to accelerate research while maintaining key scientific values like transparency, traceability, and verifiability. The framework is field-agnostic, supports both open-goal and fixed-goal research, creates data-chained manuscripts, involves human-in-the-loop interaction, and allows for transparent replay of the research process.

LLM Alchemy Chamber is a repository dedicated to exploring the world of Language Models (LLMs) through various experiments and projects. It contains scripts, notebooks, and experiments focused on tasks such as fine-tuning different LLM models, quantization for performance optimization, dataset generation for instruction/QA tasks, and more. The repository offers a collection of resources for beginners and enthusiasts interested in delving into the mystical realm of LLMs.

This repository provides code to deploy a chatbot powered by Multi-Model and Multi-RAG using AWS CDK on AWS. Users can experiment with various Large Language Models and Multimodal Language Models from different providers. The solution supports Amazon Bedrock, Amazon SageMaker self-hosted models, and third-party providers via API. It also offers additional resources like AWS Generative AI CDK Constructs and Project Lakechain for building generative AI solutions and document processing. The roadmap and authors are listed, along with contributors. The library is licensed under the MIT-0 License with information on changelog, code of conduct, and contributing guidelines. A legal disclaimer advises users to conduct their own assessment before using the content for production purposes.

StableToolBench is a new benchmark developed to address the instability of Tool Learning benchmarks. It aims to balance stability and reality by introducing features such as a Virtual API System with caching and API simulators, a new set of solvable queries determined by LLMs, and a Stable Evaluation System using GPT-4. The Virtual API Server can be set up either by building from source or using a prebuilt Docker image. Users can test the server using provided scripts and evaluate models with Solvable Pass Rate and Solvable Win Rate metrics. The tool also includes model experiments results comparing different models' performance.

Baal is an active learning library that supports both industrial applications and research use cases. It provides a framework for Bayesian active learning methods such as Monte-Carlo Dropout, MCDropConnect, Deep ensembles, and Semi-supervised learning. Baal helps in labeling the most uncertain items in the dataset pool to improve model performance and reduce annotation effort. The library is actively maintained by a dedicated team and has been used in various research papers for production and experimentation.

AI Summer is a repository focused on providing workshops and resources for developing foundational skills in generative AI models and transformer models. The repository offers practical applications for inferencing and training, with a specific emphasis on understanding and utilizing advanced AI chat models like BingGPT. Participants are encouraged to engage in interactive programming environments, decide on projects to work on, and actively participate in discussions and breakout rooms. The workshops cover topics such as generative AI models, retrieval-augmented generation, building AI solutions, and fine-tuning models. The goal is to equip individuals with the necessary skills to work with AI technologies effectively and securely, both locally and in the cloud.

IBM Generative AI Python SDK is a tool designed for the Tech Preview program for IBM Foundation Models Studio. It brings IBM Generative AI (GenAI) into Python programs, offering various operations and types. Users can start a trial version or request a demo via the provided link. The SDK was recently rewritten and released under V2 in 2024, with a migration guide available. Contributors are welcome to participate in the open-source project by contributing documentation, tests, bug fixes, and new functionality.

The oneAPI-samples repository contains a collection of samples for the Intel oneAPI Toolkits. These samples cover various topics such as AI and analytics, end-to-end workloads, features and functionality, getting started samples, Jupyter notebooks, direct programming, C++, Fortran, libraries, publications, rendering toolkit, and tools. Users can find samples based on expertise, programming language, and target device. The repository structure is organized by high-level categories, and platform validation includes Ubuntu 22.04, Windows 11, and macOS. The repository provides instructions for getting samples, including cloning the repository or downloading specific tagged versions. Users can also use integrated development environments (IDEs) like Visual Studio Code. The code samples are licensed under the MIT license.

The 'Dive into Large Language Models' series programming practice tutorial is an extension of the 'Artificial Intelligence Security Technology' course lecture notes from Shanghai Jiao Tong University (Instructor: Zhang Zhuosheng). It aims to provide introductory programming references related to large models. Through simple practice, it helps students quickly grasp large models, better engage in course design, or academic research. The tutorial covers topics such as fine-tuning and deployment, prompt learning and thought chains, knowledge editing, model watermarking, jailbreak attacks, multimodal models, large model intelligent agents, and security. Disclaimer: The content is based on contributors' personal experiences, internet data, and accumulated research work, provided for reference only.

pyLLMSearch is an advanced RAG system that offers a convenient question-answering system with a simple YAML-based configuration. It enables interaction with multiple collections of local documents, with improvements in document parsing, hybrid search, chat history, deep linking, re-ranking, customizable embeddings, and more. The package is designed to work with custom Large Language Models (LLMs) from OpenAI or installed locally. It supports various document formats, incremental embedding updates, dense and sparse embeddings, multiple embedding models, 'Retrieve and Re-rank' strategy, HyDE (Hypothetical Document Embeddings), multi-querying, chat history, and interaction with embedded documents using different models. It also offers simple CLI and web interfaces, deep linking, offline response saving, and an experimental API.

LLMinator is a Gradio-based tool with an integrated chatbot designed to locally run and test Language Model Models (LLMs) directly from HuggingFace. It provides an easy-to-use interface made with Gradio, LangChain, and Torch, offering features such as context-aware streaming chatbot, inbuilt code syntax highlighting, loading any LLM repo from HuggingFace, support for both CPU and CUDA modes, enabling LLM inference with llama.cpp, and model conversion capabilities.

The Beta Machine Learning Toolkit is a package containing various algorithms and utilities for implementing machine learning workflows in multiple languages, including Julia, Python, and R. It offers a range of supervised and unsupervised models, data transformers, and assessment tools. The models are implemented entirely in Julia and are not wrappers for third-party models. Users can easily contribute new models or request implementations. The focus is on user-friendliness rather than computational efficiency, making it suitable for educational and research purposes.

Podman AI Lab is an open source extension for Podman Desktop designed to work with Large Language Models (LLMs) on a local environment. It features a recipe catalog with common AI use cases, a curated set of open source models, and a playground for learning, prototyping, and experimentation. Users can quickly and easily get started bringing AI into their applications without depending on external infrastructure, ensuring data privacy and security.

AgentGPT is a platform that allows users to configure and deploy autonomous AI agents. Users can name their own custom AI and set it on any goal. The AI will think of tasks, execute them, and learn from the results to reach the goal. The platform provides a demo experience, automatic setup CLI, and a tech stack including Next.js, FastAPI, Prisma, TailwindCSS, Zod, and more. AgentGPT is designed to help users easily create and deploy AI agents for various tasks.

DataRobot AI Accelerators are code-first workflows to speed up model development, deployment, and time to value using the DataRobot API. The accelerators include approaches for specific business challenges, generative AI, ecosystem integration templates, and advanced ML and API usage. Users can clone the repo, import desired accelerators into notebooks, execute them, learn and modify content to solve their own problems.

AI Agents Framework is a .NET framework built on Semantic Kernel and Orleans for creating and hosting event-driven AI Agents. It is currently in an experimental phase and not recommended for production use. The framework aims to automate requirements engineering, planning, and coding processes using event-driven agents.

TableLLM is a large language model designed for efficient tabular data manipulation tasks in real office scenarios. It can generate code solutions or direct text answers for tasks like insert, delete, update, query, merge, and chart operations on tables embedded in spreadsheets or documents. The model has been fine-tuned based on CodeLlama-7B and 13B, offering two scales: TableLLM-7B and TableLLM-13B. Evaluation results show its performance on benchmarks like WikiSQL, Spider, and self-created table operation benchmark. Users can use TableLLM for code and text generation tasks on tabular data.

PyLLMs is a minimal Python library designed to connect to various Language Model Models (LLMs) such as OpenAI, Anthropic, Google, AI21, Cohere, Aleph Alpha, and HuggingfaceHub. It provides a built-in model performance benchmark for fast prototyping and evaluating different models. Users can easily connect to top LLMs, get completions from multiple models simultaneously, and evaluate models on quality, speed, and cost. The library supports asynchronous completion, streaming from compatible models, and multi-model initialization for testing and comparison. Additionally, it offers features like passing chat history, system messages, counting tokens, and benchmarking models based on quality, speed, and cost.

ppl.llm.kernel.cuda is a primitive cuda kernel library for ppl.nn.llm system, designed for Ampere and Hopper architectures. It requires Linux running on x86_64 or arm64 CPUs with specific versions of GCC, CMake, Git, and CUDA Toolkit. Users can follow the provided Quick Start guide to install prerequisites, clone the source code, and build from source. The project is distributed under the Apache License, Version 2.0.

MeeseeksAI is a framework designed to orchestrate AI agents using a mermaid graph and networkx. It provides a structured approach to managing and coordinating multiple AI agents within a system. The framework allows users to define the interactions and dependencies between agents through a visual representation, making it easier to understand and modify the behavior of the AI system. By leveraging the power of networkx, MeeseeksAI enables efficient graph-based computations and optimizations, enhancing the overall performance of AI workflows. With its intuitive design and flexible architecture, MeeseeksAI simplifies the process of building and deploying complex AI systems, empowering users to create sophisticated agent interactions with ease.

Geoweaver is an in-browser software that enables users to easily compose and execute full-stack data processing workflows using online spatial data facilities, high-performance computation platforms, and open-source deep learning libraries. It provides server management, code repository, workflow orchestration software, and history recording capabilities. Users can run it from both local and remote machines. Geoweaver aims to make data processing workflows manageable for non-coder scientists and preserve model run history. It offers features like progress storage, organization, SSH connection to external servers, and a web UI with Python support.

Azure OpenAI demos is a repository showcasing various demos and use cases of Azure OpenAI services. It includes demos for tasks such as image comparisons, car damage copilot, video to checklist generation, automatic data visualization, text analytics, and more. The repository provides a wide range of examples on how to leverage Azure OpenAI for different applications and industries.

This repository focuses on organizing resources for building synthetic datasets using large language models. It covers important datasets, libraries, tools, tutorials, and papers related to synthetic data generation. The goal is to provide pragmatic and practical resources for individuals interested in creating synthetic datasets for machine learning applications.

tgpt is a cross-platform command-line interface (CLI) tool that allows users to interact with AI chatbots in the Terminal without needing API keys. It supports various AI providers such as KoboldAI, Phind, Llama2, Blackbox AI, and OpenAI. Users can generate text, code, and images using different flags and options. The tool can be installed on GNU/Linux, MacOS, FreeBSD, and Windows systems. It also supports proxy configurations and provides options for updating and uninstalling the tool.

ActionWeaver is an AI application framework designed for simplicity, relying on OpenAI and Pydantic. It supports both OpenAI API and Azure OpenAI service. The framework allows for function calling as a core feature, extensibility to integrate any Python code, function orchestration for building complex call hierarchies, and telemetry and observability integration. Users can easily install ActionWeaver using pip and leverage its capabilities to create, invoke, and orchestrate actions with the language model. The framework also provides structured extraction using Pydantic models and allows for exception handling customization. Contributions to the project are welcome, and users are encouraged to cite ActionWeaver if found useful.

LLMeBench is a flexible framework designed for accelerating benchmarking of Large Language Models (LLMs) in the field of Natural Language Processing (NLP). It supports evaluation of various NLP tasks using model providers like OpenAI, HuggingFace Inference API, and Petals. The framework is customizable for different NLP tasks, LLM models, and datasets across multiple languages. It features extensive caching capabilities, supports zero- and few-shot learning paradigms, and allows on-the-fly dataset download and caching. LLMeBench is open-source and continuously expanding to support new models accessible through APIs.

BABILong is a generative benchmark designed to evaluate the performance of NLP models in processing long documents with distributed facts. It consists of 20 tasks that simulate interactions between characters and objects in various locations, requiring models to distinguish important information from irrelevant details. The tasks vary in complexity and reasoning aspects, with test samples potentially containing millions of tokens. The benchmark aims to challenge and assess the capabilities of Large Language Models (LLMs) in handling complex, long-context information.

AI-TOD is a dataset for tiny object detection in aerial images, containing 700,621 object instances across 28,036 images. Objects in AI-TOD are smaller with a mean size of 12.8 pixels compared to other aerial image datasets. To use AI-TOD, download xView training set and AI-TOD_wo_xview, then generate the complete dataset using the provided synthesis tool. The dataset is publicly available for academic and research purposes under CC BY-NC-SA 4.0 license.

PromptAgent is a repository for a novel automatic prompt optimization method that crafts expert-level prompts using language models. It provides a principled framework for prompt optimization by unifying prompt sampling and rewarding using MCTS algorithm. The tool supports different models like openai, palm, and huggingface models. Users can run PromptAgent to optimize prompts for specific tasks by strategically sampling model errors, generating error feedbacks, simulating future rewards, and searching for high-reward paths leading to expert prompts.

BIA `bob` is a Jupyter-based assistant for interacting with data using large language models to generate Python code. It can utilize OpenAI's chatGPT, Google's Gemini, Helmholtz' blablador, and Ollama. Users need respective accounts to access these services. Bob can assist in code generation, bug fixing, code documentation, GPU-acceleration, and offers a no-code custom Jupyter Kernel. It provides example notebooks for various tasks like bio-image analysis, model selection, and bug fixing. Installation is recommended via conda/mamba environment. Custom endpoints like blablador and ollama can be used. Google Cloud AI API integration is also supported. The tool is extensible for Python libraries to enhance Bob's functionality.

LLM-SFT is a Chinese large model fine-tuning tool that supports models such as ChatGLM, LlaMA, Bloom, Baichuan-7B, and frameworks like LoRA, QLoRA, DeepSpeed, UI, and TensorboardX. It facilitates tasks like fine-tuning, inference, evaluation, and API integration. The tool provides pre-trained weights for various models and datasets for Chinese language processing. It requires specific versions of libraries like transformers and torch for different functionalities.

Experts.js is a tool that simplifies the creation and deployment of OpenAI's Assistants, allowing users to link them together as Tools to create a Panel of Experts system with expanded memory and attention to detail. It leverages the new Assistants API from OpenAI, which offers advanced features such as referencing attached files & images as knowledge sources, supporting instructions up to 256,000 characters, integrating with 128 tools, and utilizing the Vector Store API for efficient file search. Experts.js introduces Assistants as Tools, enabling the creation of Multi AI Agent Systems where each Tool is an LLM-backed Assistant that can take on specialized roles or fulfill complex tasks.

This repository is a curated list of papers related to 3D tasks empowered by Large Language Models (LLMs). It covers tasks such as 3D understanding, reasoning, generation, and embodied agents. The repository also includes other Foundation Models like CLIP and SAM to provide a comprehensive view of the area. It is actively maintained and updated to showcase the latest advances in the field. Users can find a variety of research papers and projects related to 3D tasks and LLMs in this repository.

This repository contains the implementation of Self-Play of Adversarial Language Game (SPAG) as described in the paper 'Self-playing Adversarial Language Game Enhances LLM Reasoning'. The SPAG involves training Language Models (LLMs) in an adversarial language game called Adversarial Taboo. The repository provides tools for imitation learning, self-play episode collection, and reinforcement learning on game episodes to enhance LLM reasoning abilities. The process involves training models using GPUs, launching imitation learning, conducting self-play episodes, assigning rewards based on outcomes, and learning the SPAG model through reinforcement learning. Continuous improvements on reasoning benchmarks can be observed by repeating the episode-collection and SPAG-learning processes.

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.

LLM Blueprint is an official implementation of a paper that enables text-to-image generation with complex and detailed prompts. It leverages Large Language Models (LLMs) to extract critical components from text prompts, including bounding box coordinates for foreground objects, detailed textual descriptions for individual objects, and a succinct background context. The tool operates in two phases: Global Scene Generation creates an initial scene using object layouts and background context, and an Iterative Refinement Scheme refines box-level content to align with textual descriptions, ensuring consistency and improving recall compared to baseline diffusion models.

Open LLMs is a repository containing various Large Language Models licensed for commercial use. It includes models like T5, GPT-NeoX, UL2, Bloom, Cerebras-GPT, Pythia, Dolly, and more. These models are designed for tasks such as transfer learning, language understanding, chatbot development, code generation, and more. The repository provides information on release dates, checkpoints, papers/blogs, parameters, context length, and licenses for each model. Contributions to the repository are welcome, and it serves as a resource for exploring the capabilities of different language models.

libLLM is an open-source project designed for efficient inference of large language models (LLM) on personal computers and mobile devices. It is optimized to run smoothly on common devices, written in C++14 without external dependencies, and supports CUDA for accelerated inference. Users can build the tool for CPU only or with CUDA support, and run libLLM from the command line. Additionally, there are API examples available for Python and the tool can export Huggingface models.

Crabml is a llama.cpp compatible AI inference engine written in Rust, designed for efficient inference on various platforms with WebGPU support. It focuses on running inference tasks with SIMD acceleration and minimal memory requirements, supporting multiple models and quantization methods. The project is hackable, embeddable, and aims to provide high-performance AI inference capabilities.

Vodalus Expert LLM Forge is a tool designed for crafting datasets and efficiently fine-tuning models using free open-source tools. It includes components for data generation, LLM interaction, RAG engine integration, model training, fine-tuning, and quantization. The tool is suitable for users at all levels and is accompanied by comprehensive documentation. Users can generate synthetic data, interact with LLMs, train models, and optimize performance for local execution. The tool provides detailed guides and instructions for setup, usage, and customization.

This repository contains code and configurations for the LLM - Detect AI Generated Text competition. It includes setup instructions for hardware, software, dependencies, and datasets. The training section covers scripts and configurations for training LLM models, DeBERTa ranking models, and an embedding model. Text generation section details fine-tuning LLMs using the CLM objective on the PERSUADE corpus to generate student-like essays.

This repository is dedicated to the ANZ LLM Workshop Series, providing a series of notebooks developed and tested on Databricks ML Runtime 14.3. The notebooks cover topics such as setting up HuggingFace models, working with sample documents, constructing RAG architectures, and running applications on the driver node in Databricks. Additionally, the repository offers recordings of past webinars and further reading materials related to LLM.