Best AI tools for< Train Policy >

The C3.ai Digital Transformation Institute is a research consortium focused on accelerating the benefits of artificial intelligence for business, government, and society. It engages leading scientists in research related to the Science of Digital Transformation, which encompasses artificial intelligence, machine learning, cloud computing, internet of things, big data analytics, organizational behavior, public policy, and ethics. Established in March 2020, the institute consists of prominent institutions such as C3 AI, Microsoft Corporation, and various universities. The institute aims to drive innovation and collaboration in the field of AI and digital transformation.

Stanford HAI is a research institute at Stanford University dedicated to advancing AI research, education, and policy to improve the human condition. The institute brings together researchers from a variety of disciplines to work on a wide range of AI-related projects, including developing new AI algorithms, studying the ethical and societal implications of AI, and creating educational programs to train the next generation of AI leaders. Stanford HAI is committed to developing human-centered AI technologies and applications that benefit all of humanity.

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.

Cyberday.ai is an AI-powered platform designed to help organizations improve and certify their cybersecurity. The platform offers a comprehensive set of tools and resources to guide users in implementing security tasks, creating policies, and generating compliance reports. With a focus on automation and efficiency, Cyberday.ai streamlines the process of managing information security, from risk assessment to employee training. By leveraging AI technology, Cyberday.ai aims to simplify the complex task of cybersecurity management for organizations of all sizes.

Dobb·E is an open-source, general framework for learning household robotic manipulation. It aims to create a generalist machine for homes that can adapt and learn from users' needs efficiently. Dobb·E can learn a new task with just five minutes of demonstration, achieving an 81% success rate in various household environments. The project focuses on accelerating research on home robots and making robot assistants a common sight in every home.

Whale is an AI-powered software designed to help businesses document their standard operating procedures, policies, and internal company knowledge. It streamlines the process of onboarding, training, and growing teams by leveraging AI technology to assist in creating and organizing documentation. Whale offers features such as AI-assisted SOP and process documentation, automated training flows, a single source of truth for knowledge management, and an AI assistant named Alice to help with various tasks. The platform aims to systemize and scale businesses by providing a user-friendly interface and dedicated support services.

IBM Watsonx is an enterprise studio for AI builders. It provides a platform to train, validate, tune, and deploy AI models quickly and efficiently. With Watsonx, users can access a library of pre-trained AI models, build their own models, and deploy them to the cloud or on-premises. Watsonx also offers a range of tools and services to help users manage and monitor their AI models.

Athletica AI is an AI-powered athletic training and personalized fitness application that offers tailored coaching and training plans for various sports like cycling, running, duathlon, triathlon, and rowing. It adapts to individual fitness levels, abilities, and availability, providing daily step-by-step training plans and comprehensive session analyses. Athletica AI integrates seamlessly with workout data from platforms like Garmin, Strava, and Concept 2 to craft personalized training plans and workouts. The application aims to help athletes train smarter, not harder, by leveraging the power of AI to optimize performance and achieve fitness goals.

Backend.AI is an enterprise-scale cluster backend for AI frameworks that offers scalability, GPU virtualization, HPC optimization, and DGX-Ready software products. It provides a fast and efficient way to build, train, and serve AI models of any type and size, with flexible infrastructure options. Backend.AI aims to optimize backend resources, reduce costs, and simplify deployment for AI developers and researchers. The platform integrates seamlessly with existing tools and offers fractional GPU usage and pay-as-you-play model to maximize resource utilization.

Kaiden AI is an AI-powered training platform that offers personalized, immersive simulations to enhance skills and performance across various industries and roles. It provides feedback-rich scenarios, voice-enabled interactions, and detailed performance insights. Users can create custom training scenarios, engage with AI personas, and receive real-time feedback to improve communication skills. Kaiden AI aims to revolutionize training solutions by combining AI technology with real-world practice.

Endurance is a platform designed for runners, swimmers, and cyclists to engage in group training activities with friends or local communities. Users can create or join teams, share structured workouts, and benefit from collective motivation and accountability. The platform aims to make training fun and effective by leveraging the power of group workouts and social connections.

ChatCube is an AI-powered chatbot maker that allows users to create chatbots for their websites without coding. It uses advanced AI technology to train chatbots on any document or website within 60 seconds. ChatCube offers a range of features, including a user-friendly visual editor, lightning-fast integration, fine-tuning on specific data sources, data encryption and security, and customizable chatbots. By leveraging the power of AI, ChatCube helps businesses improve customer support efficiency and reduce support ticket reductions by up to 28%.

Workout Tools is an AI-powered personal trainer that helps you train smarter and reach your fitness goals faster. It takes into account different parameters, such as your physics, the type of workout you're interested in, your available equipment, and comes up with a suggested workout. Don't like the workout? Just generate another one. It's that simple.

CoRover.ai is an AI-powered chatbot designed to help users book train tickets seamlessly through conversation. The chatbot, named AskDISHA, is integrated with the IRCTC platform, allowing users to inquire about train schedules, ticket availability, and make bookings effortlessly. CoRover.ai leverages artificial intelligence to provide personalized assistance and streamline the ticket booking process for users, enhancing their overall experience.

IllumiDesk is a generative AI platform for instructors and content developers that helps teams create and monetize content tailored 10X faster. With IllumiDesk, you can automate grading tasks, collaborate with your learners, create awesome content at the speed of AI, and integrate with the services you know and love. IllumiDesk's AI will help you create, maintain, and structure your content into interactive lessons. You can also leverage IllumiDesk's flexible integration options using the RESTful API and/or LTI v1.3 to leverage existing content and flows. IllumiDesk is trusted by training agencies and universities around the world.

Tovuti LMS is an adaptive, people-first learning platform that helps organizations create engaging courses, train teams, and track progress. With its easy-to-use interface and powerful features, Tovuti LMS makes learning fun and easy. Tovuti LMS is trusted by leading organizations around the world to provide their employees with the training they need to succeed.

Chatbond is an AI chatbot builder that enables users to create customized chatbots for websites and messaging platforms without the need for coding skills. With Chatbond, users can design conversational interfaces, integrate AI capabilities, and deploy chatbots to enhance customer engagement and streamline communication processes. The platform offers a user-friendly interface with drag-and-drop functionality, pre-built templates, and analytics tools to monitor chatbot performance and optimize interactions. Chatbond empowers businesses to automate customer support, lead generation, and sales processes, improving efficiency and scalability.

Teachable Machine is a web-based tool that makes it easy to create custom machine learning models, even if you don't have any coding experience. With Teachable Machine, you can train models to recognize images, sounds, and poses. Once you've trained a model, you can export it to use in your own projects.

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.

Surge AI is a data labeling platform that provides human-generated data for training and evaluating large language models (LLMs). It offers a global workforce of annotators who can label data in over 40 languages. Surge AI's platform is designed to be easy to use and integrates with popular machine learning tools and frameworks. The company's customers include leading AI companies, research labs, and startups.

ReST-MCTS is a reinforced self-training approach that integrates process reward guidance with tree search MCTS to collect higher-quality reasoning traces and per-step value for training policy and reward models. It eliminates the need for manual per-step annotation by estimating the probability of steps leading to correct answers. The inferred rewards refine the process reward model and aid in selecting high-quality traces for policy model self-training.

Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy is a research project focusing on addressing the challenge of generalizing language-conditioned robotic policies to new tasks. The project introduces GemBench, a benchmark to evaluate the generalization capabilities of vision-language robotic manipulation policies. It also presents the 3D-LOTUS approach, which leverages rich 3D information for action prediction conditioned on language. Additionally, the project introduces 3D-LOTUS++, a framework that integrates 3D-LOTUS's motion planning capabilities with the task planning capabilities of LLMs and the object grounding accuracy of VLMs to achieve state-of-the-art performance on novel tasks in robotic manipulation.

LeRobot is a state-of-the-art AI library for real-world robotics in PyTorch. It aims to provide models, datasets, and tools to lower the barrier to entry to robotics, focusing on imitation learning and reinforcement learning. LeRobot offers pretrained models, datasets with human-collected demonstrations, and simulation environments. It plans to support real-world robotics on affordable and capable robots. The library hosts pretrained models and datasets on the Hugging Face community page.

This repository contains code for training reward models for Deep Reinforcement Learning-based Reward-modulated Hierarchical Fine-tuning (DRL-based RLHF), Iterative Selection Fine-tuning (Rejection sampling fine-tuning), and iterative Decision Policy Optimization (DPO). The reward models are trained using a Bradley-Terry model based on the Gemma and Mistral language models. The resulting reward models achieve state-of-the-art performance on the RewardBench leaderboard for reward models with base models of up to 13B parameters.

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.

MineStudio is a simple and efficient Minecraft development kit for AI research. It contains tools and APIs for developing Minecraft AI agents, including a customizable simulator, trajectory data structure, policy models, offline and online training pipelines, inference framework, and benchmarking automation. The repository is under development and welcomes contributions and suggestions.

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

Zeta is a tool designed to build state-of-the-art AI models faster by providing modular, high-performance, and scalable building blocks. It addresses the common issues faced while working with neural nets, such as chaotic codebases, lack of modularity, and low performance modules. Zeta emphasizes usability, modularity, and performance, and is currently used in hundreds of models across various GitHub repositories. It enables users to prototype, train, optimize, and deploy the latest SOTA neural nets into production. The tool offers various modules like FlashAttention, SwiGLUStacked, RelativePositionBias, FeedForward, BitLinear, PalmE, Unet, VisionEmbeddings, niva, FusedDenseGELUDense, FusedDropoutLayerNorm, MambaBlock, Film, hyper_optimize, DPO, and ZetaCloud for different tasks in AI model development.

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.

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.

WebRL is a self-evolving online curriculum learning framework designed for training web agents in the WebArena environment. It provides model checkpoints, training instructions, and evaluation processes for training the actor and critic models. The tool enables users to generate new instructions and interact with WebArena to configure tasks for training and evaluation.

OREAL is a reinforcement learning framework designed for mathematical reasoning tasks, aiming to achieve optimal performance through outcome reward-based learning. The framework utilizes behavior cloning, reshaping rewards, and token-level reward models to address challenges in sparse rewards and partial correctness. OREAL has achieved significant results, with a 7B model reaching 94.0 pass@1 accuracy on MATH-500 and surpassing previous 32B models. The tool provides training tutorials and Hugging Face model repositories for easy access and implementation.

LLM-PowerHouse is a comprehensive and curated guide designed to empower developers, researchers, and enthusiasts to harness the true capabilities of Large Language Models (LLMs) and build intelligent applications that push the boundaries of natural language understanding. This GitHub repository provides in-depth articles, codebase mastery, LLM PlayLab, and resources for cost analysis and network visualization. It covers various aspects of LLMs, including NLP, models, training, evaluation metrics, open LLMs, and more. The repository also includes a collection of code examples and tutorials to help users build and deploy LLM-based applications.

SkyPilot is a framework for running LLMs, AI, and batch jobs on any cloud, offering maximum cost savings, highest GPU availability, and managed execution. SkyPilot abstracts away cloud infra burdens: - Launch jobs & clusters on any cloud - Easy scale-out: queue and run many jobs, automatically managed - Easy access to object stores (S3, GCS, R2) SkyPilot maximizes GPU availability for your jobs: * Provision in all zones/regions/clouds you have access to (the _Sky_), with automatic failover SkyPilot cuts your cloud costs: * Managed Spot: 3-6x cost savings using spot VMs, with auto-recovery from preemptions * Optimizer: 2x cost savings by auto-picking the cheapest VM/zone/region/cloud * Autostop: hands-free cleanup of idle clusters SkyPilot supports your existing GPU, TPU, and CPU workloads, with no code changes.

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.

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

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.

OpenRL is an open-source general reinforcement learning research framework that supports training for various tasks such as single-agent, multi-agent, offline RL, self-play, and natural language. Developed based on PyTorch, the goal of OpenRL is to provide a simple-to-use, flexible, efficient and sustainable platform for the reinforcement learning research community. It supports a universal interface for all tasks/environments, single-agent and multi-agent tasks, offline RL training with expert dataset, self-play training, reinforcement learning training for natural language tasks, DeepSpeed, Arena for evaluation, importing models and datasets from Hugging Face, user-defined environments, models, and datasets, gymnasium environments, callbacks, visualization tools, unit testing, and code coverage testing. It also supports various algorithms like PPO, DQN, SAC, and environments like Gymnasium, MuJoCo, Atari, and more.

This repository contains the training and inference code needed to replicate the winning solution to the AI Mathematical Olympiad - Progress Prize 1. It consists of fine-tuning DeepSeekMath-Base 7B, high-quality training datasets, a self-consistency decoding algorithm, and carefully chosen validation sets. The training methodology involves Chain of Thought (CoT) and Tool Integrated Reasoning (TIR) training stages. Two datasets, NuminaMath-CoT and NuminaMath-TIR, were used to fine-tune the models. The models were trained using open-source libraries like TRL, PyTorch, vLLM, and DeepSpeed. Post-training quantization to 8-bit precision was done to improve performance on Kaggle's T4 GPUs. The project structure includes scripts for training, quantization, and inference, along with necessary installation instructions and hardware/software specifications.

ms-swift is an official framework provided by the ModelScope community for fine-tuning and deploying large language models and multi-modal large models. It supports training, inference, evaluation, quantization, and deployment of over 400 large models and 100+ multi-modal large models. The framework includes various training technologies and accelerates inference, evaluation, and deployment modules. It offers a Gradio-based Web-UI interface and best practices for easy application of large models. ms-swift supports a wide range of model types, dataset types, hardware support, lightweight training methods, distributed training techniques, quantization training, RLHF training, multi-modal training, interface training, plugin and extension support, inference acceleration engines, model evaluation, and model quantization.

An expert chatbot on AR 600-20, Army Command Policy

AI Battle Realism Simulator | Realistic combat outcomes, with policy-compliant visuals

Strategize in global crises and see what the AI will do in this interactive game!

Especialista em Análise de Direitos Humanos em Contextos Multilíngues

Ensures organizational adherence to laws, regulations, and internal policies.

Guides through healthcare app legalities

Trained in kindness, empathy & respect based on ethics from global philosophies

A safeguarding advisor for schools, aligned with 'Keeping Children Safe In Education' guidelines.

Leading-edge Urban Ag Expert, blending accuracy with approachability. Powered by OpenAI.

你是课程设计专家，心理学家，两个孩子的母亲，你非常关注如何让孩子更好地适应未来地世界，帮他们筛选最必要的技能。你擅长保护孩子的天然的兴趣，用游戏等有趣的方式帮助他们找到各种学习的乐趣。

Expert in the precise and detailed creation of identikits.

Promotes inclusive culture and diversity within the organization.

Real Estate Agencies and Brokers deal with personal data of clients, including financial information and preferences, requiring careful handling and protection of such data.

Expert in HIPAA compliance for medical supplies

🤓💡📃Engaging and positive US compliance expert helping professionals with DOJ-guidance based programs.

Expert in answering Data Compliance queries for small businesses in the USA

Expert on privacy laws: GDPR, CCPA, PIPEDA, U.S. state laws

Expert in cyber security (NIST, OWASP, NIS2, MITRE ATT&CK, DORA) and GDPR, offering clear and concise guidance.

Specialist in people operations and technology, offering tailored advice.

I simulate the governance of a unique company focused on AI for good