Best AI tools for< Instruction Following >

Video2Recipe is an AI tool that allows users to convert their favorite cooking videos into recipes effortlessly. By simply pasting the video URL or ID, the AI generates step-by-step instructions and ingredient lists. The platform aims to simplify the process of following cooking tutorials and make it more accessible for users to recreate dishes they love.

Buddy.ai is an AI-powered early learning platform designed to teach English to children aged 3-7 in a playful and interactive way. The platform offers 1:1 voice-based learning games and lessons to help children develop essential skills for school success. With a focus on fun and personalized teaching, Buddy.ai provides a safe learning space free from ads and extra charges. The platform covers a wide range of subjects, including language, literacy, math, science, art, music, and more, following the U.S. educational system. Buddy.ai uses advanced voice recognition and AI technology to engage children in interactive lessons and games, promoting learning through storytelling, spaced repetition, and total physical response.

Tutor AI is an AI English-speaking application designed to assist individuals in practicing their spoken English skills with the aid of an artificial intelligence chatbot. The app offers a safe and judgment-free environment for users to engage in free-flowing, natural conversations with diverse AI characters. It provides real-time feedback, suggests better ways to express oneself, and offers adjustable features to enhance the learning experience. Tutor AI aims to improve users' spoken English skills confidently and effectively through personalized lessons and interactive learning.

Eduaide.Ai is an AI-driven platform designed to assist educators in creating lesson plans, teaching resources, and assessments. It offers features such as AI-assisted lesson planning, teaching resources generation, feedback bot, personalization tools, and assessment builder. The platform aims to streamline administrative tasks, provide personalized learning experiences, and enhance teaching efficiency through AI technology.

MailMaestro is an AI email assistant that helps users write better emails faster, allowing them to be more productive and focus on important tasks. The company behind MailMaestro, Maestro Labs, acquired Flowrite, the AI writing division of Flow AI, in September 2024. The team behind Flowrite is now focusing on Flow AI, an advanced platform for AI teams to evaluate and improve LLM systems effortlessly. MailMaestro integrates Flowrite's capabilities to enhance email writing experience for users.

Canopy Directory is an AI tool designed specifically for educators. It provides a comprehensive directory of AI tools that can be used in educational settings. The platform aims to streamline the process of finding and utilizing AI tools for teaching and learning purposes. Educators can explore a wide range of tools categorized based on their functionalities and applications, making it easier to integrate AI technology into their teaching practices. Canopy Directory serves as a valuable resource for educators looking to enhance their teaching methods through the use of AI tools.

Google Gemma is a lightweight, state-of-the-art open language model (LLM) developed by Google. It is part of the same research used in the creation of Google's Gemini models. Gemma models come in two sizes, the 2B and 7B parameter versions, where each has a base (pre-trained) and instruction-tuned modifications. Gemma models are designed to be cross-device compatible and optimized for Google Cloud and NVIDIA GPUs. They are also accessible through Kaggle, Hugging Face, Google Cloud with Vertex AI or GKE. Gemma models can be used for a variety of applications, including text generation, summarization, RAG, and both commercial and research use.

DoubleO AIPURE AI DOUBLE .O. is an AI automation tool designed for non-developers to easily create powerful AI automations. The tool allows users to give simple instructions, connect tools, and let a team of highly-trained DoubleO AI agents automate complex tasks. It offers pre-built and custom workflows for various teams, such as Sales, Marketing, Product, and Operations. The tool integrates with popular tools like Intercom, Slack, Salesforce, and more, ensuring data security and privacy with end-to-end encryption and compliance with data security standards. Users can benefit from features like automating pre-call prep, analyzing customer feedback, creating launch plans, and maintaining roadmaps.

OdiaGenAI is a collaborative initiative focused on conducting research on Generative AI and Large Language Models (LLM) for the Odia Language. The project aims to leverage AI technology to develop Generative AI and LLM-based solutions for the overall development of Odisha and the Odia language through collaboration among Odia technologists. The initiative offers pre-trained models, codes, and datasets for non-commercial and research purposes, with a focus on building language models for Indic languages like Odia and Bengali.

Diffit is an AI-powered educational tool designed to provide learning resources for teachers and students. It helps teachers create customized, grade-level content by generating standards-aligned resources from scratch. With features like text re-leveling, vocabulary customization, and question addition, Diffit aims to make instructional materials accessible to all students. The application offers a library of high-quality, student-ready exports to facilitate the teaching process. Testimonials from educators highlight the tool's effectiveness in differentiating instruction and engaging students across various subjects.

Grow with Google is an AI tool designed to provide training and resources to help individuals boost their productivity and skills in various fields such as cybersecurity, data analytics, digital marketing, IT support, project management, UX design, and AI essentials. The platform offers online courses, tools, and professional certificates to help users develop ideas, make informed decisions, and enhance their daily work tasks using generative AI tools. With a focus on career growth and business development, Grow with Google aims to empower individuals with essential AI skills to succeed in today's competitive job market.

LessonPlans.ai is an AI-powered lesson plan generator that helps teachers create high-quality lesson plans in seconds. With this tool, teachers can easily generate detailed, personalized lesson plans that are tailored to their students' needs. LessonPlans.ai also includes a step-by-step guide for each lesson, making it easy for teachers to follow and implement the plan in their classrooms.

Cognii is an AI-based educational technology provider that offers solutions for K-12, higher education, and corporate training markets. Their award-winning EdTech product enables personalized learning, intelligent tutoring, open response assessments, and rich analytics. Cognii's Virtual Learning Assistant engages students in chatbot-style conversations, providing instant feedback, personalized hints, and guiding towards mastery. The platform aims to deliver 21st-century online education with superior learning outcomes and cost efficiency.

Breakout Learning is an AI-powered educational platform that transforms traditional case studies into engaging, multifaceted experiences. It empowers professors with AI insights into small-group discussions, enabling them to customize lectures and foster deeper student comprehension. Students benefit from rich content, peer-led discussions, and AI assessment that provides personalized feedback and tracks their progress.

Undress App is an AI tool that allows users to nudify any person in a photo using AI technology. The application provides a 3-step instruction on how to achieve this, emphasizing the importance of photo quality and proper positioning of the person in the image. It discusses the ethical implications of using AI to undress individuals and highlights the creative and potentially harmful uses of such technology. Undress App aims to offer a platform for creative self-expression and entertainment while acknowledging the potential misuse of the tool.

The Cerebras API is a high-speed inferencing solution for AI model inference powered by Cerebras Wafer-Scale Engines and CS-3 systems. It offers developers access to two models: Meta’s Llama 3.1 8B and 70B models, which are instruction-tuned and suitable for conversational applications. The API provides low-latency solutions and invites developers to explore new possibilities in AI development.

Class Companion is an AI teaching assistant tool designed to provide instant coaching and AI feedback to students on their assignments. It helps improve student engagement and outcomes by offering multiple attempts, targeted help, and personalized feedback. The tool supports various subjects and grades, allowing teachers to save time on manual feedback and focus on lesson planning and individual instruction. With features like AI-generated content, in-depth reporting, and customizable rubrics, Class Companion aims to enhance student learning and comprehension.

DapperGPT is a user interface (UI) for ChatGPT that provides a better user experience and additional features. It offers an intuitive interface, AI-powered notes, a Chrome extension, smart search, the ability to pin favorites, image generation, character instruction prompts, and code generation. DapperGPT is free to use, but requires a valid OpenAI API key. Premium features are also available for purchase, which include additional customization options and cloud sync.

Promptmatic is a free Google Chrome extension that helps you bookmark, save, and organize your best ChatGPT prompt templates and GPTs all in one place. It also includes a smart prompt editor with built-in variable editor and 200+ role, instruction, style, and tone presets. With Promptmatic, you can easily create reusable prompt templates, save and bookmark GPTs and templates in folders, and access them whenever you need with a single click right inside your ChatGPT dashboard.

Paint by Text is a web application that allows users to edit their photos using written instructions, with the help of an AI. Users can upload an image and then type in a description of the changes they want to make. The AI will then generate a new image that reflects the user's instructions.

Cherry Data Selection project introduces a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, minimizing manual curation and cost for instruction tuning. The project focuses on selecting impactful training samples ('cherry data') to enhance LLM instruction tuning by estimating instruction-following difficulty. The method involves phases like 'Learning from Brief Experience', 'Evaluating Based on Experience', and 'Retraining from Self-Guided Experience' to improve LLM performance.

LLamaTuner is a repository for the Efficient Finetuning of Quantized LLMs project, focusing on building and sharing instruction-following Chinese baichuan-7b/LLaMA/Pythia/GLM model tuning methods. The project enables training on a single Nvidia RTX-2080TI and RTX-3090 for multi-round chatbot training. It utilizes bitsandbytes for quantization and is integrated with Huggingface's PEFT and transformers libraries. The repository supports various models, training approaches, and datasets for supervised fine-tuning, LoRA, QLoRA, and more. It also provides tools for data preprocessing and offers models in the Hugging Face model hub for inference and finetuning. The project is licensed under Apache 2.0 and acknowledges contributions from various open-source contributors.

InternLM is a powerful language model series with features such as 200K context window for long-context tasks, outstanding comprehensive performance in reasoning, math, code, chat experience, instruction following, and creative writing, code interpreter & data analysis capabilities, and stronger tool utilization capabilities. It offers models in sizes of 7B and 20B, suitable for research and complex scenarios. The models are recommended for various applications and exhibit better performance than previous generations. InternLM models may match or surpass other open-source models like ChatGPT. The tool has been evaluated on various datasets and has shown superior performance in multiple tasks. It requires Python >= 3.8, PyTorch >= 1.12.0, and Transformers >= 4.34 for usage. InternLM can be used for tasks like chat, agent applications, fine-tuning, deployment, and long-context inference.

Aidan Bench is a tool that rewards creativity, reliability, contextual attention, and instruction following. It is weakly correlated with Lmsys, has no score ceiling, and aligns with real-world open-ended use. The tool involves giving LLMs open-ended questions and evaluating their answers based on novelty scores. Users can set up the tool by installing required libraries and setting up API keys. The project allows users to run benchmarks for different models and provides flexibility in threading options.

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.

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, 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.

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.

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

Awesome-Papers-Autonomous-Agent is a curated collection of recent papers focusing on autonomous agents, specifically interested in RL-based agents and LLM-based agents. The repository aims to provide a comprehensive resource for researchers and practitioners interested in intelligent agents that can achieve goals, acquire knowledge, and continually improve. The collection includes papers on various topics such as instruction following, building agents based on world models, using language as knowledge, leveraging LLMs as a tool, generalization across tasks, continual learning, combining RL and LLM, transformer-based policies, trajectory to language, trajectory prediction, multimodal agents, training LLMs for generalization and adaptation, task-specific designing, multi-agent systems, experimental analysis, benchmarking, applications, algorithm design, and combining with RL.

EasyInstruct is a Python package proposed as an easy-to-use instruction processing framework for Large Language Models (LLMs) like GPT-4, LLaMA, ChatGLM in your research experiments. EasyInstruct modularizes instruction generation, selection, and prompting, while also considering their combination and interaction.

This repository provides a curated list of open-source projects that implement instruction-tuned large language models (LLMs) with reinforcement learning from human feedback (RLHF). The projects are evaluated in terms of their openness across a predefined set of criteria in the areas of Availability, Documentation, and Access. The goal of this repository is to promote transparency and accountability in the development and deployment of LLMs.

Reflection-Tuning is a project focused on improving the quality of instruction-tuning data through a reflection-based method. It introduces Selective Reflection-Tuning, where the student model can decide whether to accept the improvements made by the teacher model. The project aims to generate high-quality instruction-response pairs by defining specific criteria for the oracle model to follow and respond to. It also evaluates the efficacy and relevance of instruction-response pairs using the r-IFD metric. The project provides code for reflection and selection processes, along with data and model weights for both V1 and V2 methods.

NExT-GPT is an end-to-end multimodal large language model that can process input and generate output in various combinations of text, image, video, and audio. It leverages existing pre-trained models and diffusion models with end-to-end instruction tuning. The repository contains code, data, and model weights for NExT-GPT, allowing users to work with different modalities and perform tasks like encoding, understanding, reasoning, and generating multimodal content.

KULLM (구름) is a Korean Large Language Model developed by Korea University NLP & AI Lab and HIAI Research Institute. It is based on the upstage/SOLAR-10.7B-v1.0 model and has been fine-tuned for instruction. The model has been trained on 8×A100 GPUs and is capable of generating responses in Korean language. KULLM exhibits hallucination and repetition phenomena due to its decoding strategy. Users should be cautious as the model may produce inaccurate or harmful results. Performance may vary in benchmarks without a fixed system prompt.

PhoGPT is an open-source 4B-parameter generative model series for Vietnamese, including the base pre-trained monolingual model PhoGPT-4B and its chat variant, PhoGPT-4B-Chat. PhoGPT-4B is pre-trained from scratch on a Vietnamese corpus of 102B tokens, with an 8192 context length and a vocabulary of 20K token types. PhoGPT-4B-Chat is fine-tuned on instructional prompts and conversations, demonstrating superior performance. Users can run the model with inference engines like vLLM and Text Generation Inference, and fine-tune it using llm-foundry. However, PhoGPT has limitations in reasoning, coding, and mathematics tasks, and may generate harmful or biased responses.

LLM Datasets is a repository containing high-quality datasets, tools, and concepts for LLM fine-tuning. It provides datasets with characteristics like accuracy, diversity, and complexity to train large language models for various tasks. The repository includes datasets for general-purpose, math & logic, code, conversation & role-play, and agent & function calling domains. It also offers guidance on creating high-quality datasets through data deduplication, data quality assessment, data exploration, and data generation techniques.

Awesome-AI-Coding is a curated list of AI coding topics, projects, datasets, LLM models, embedding models, papers, blogs, products, startups, and peer awesome lists related to artificial intelligence in coding. It includes tools for code completion, code generation, code documentation, and code search, as well as AI models and techniques for improving developer productivity. The repository also features information on various AI-powered developer tools, copilots, and related resources in the AI coding domain.

Language Models is a Python package that provides building blocks to explore large language models with as little as 512MB of RAM. It simplifies the usage of large language models from Python, ensuring all inference is performed locally to keep data private. The package includes features such as text completions, chat capabilities, code completions, external text retrieval, semantic search, and more. It outperforms Hugging Face transformers for CPU inference and offers sensible default models with varying parameters based on memory constraints. The package is suitable for learners and educators exploring the intersection of large language models with modern software development.

Drafts detailed research papers with web-sourced citations, following user-specific instructions.

Full step by step guidance and copy & paste text for developing assistants with specific use cases.

Write your GPT instructions, context, persona, constraints. The more detailed the better.

Write your role and get your tailored persona for a tailored ChatGPT instructions.

Teaches origami with step-by-step visual instructions and provides templates for various skill levels.

Send keywords and an overview of the video you want to make, and this bot will create invideoAI (AI Video Creator) instructions for you!

A GPT of the General Handbook of Instructions for the Church of Jesus Christ of Latter-day Saints.

Differentiation advice for English Learners / Developing Bilinguals. For K-12 Teachers. EL, ESL, ELL, Bilingual, Dual Language instruction. Click a prompt below to begin:

Choose your own Custom Instruction. Type 'Activate ...'

Refines GPT instruction sets for optimal performance

Simplify Any Instruction Manual

Give me a lesson and I can give you feedback based on Rosenshine's "Principles of Instruction"

I'm a Language Tutor Bot for beginner Korean learners, offering personalized, engaging instruction.

An experiment in personal FileMaker guidance from the collective works of lifetime award-winning FileMaker trainer, Cris Ippolite. Not just links to resources, but direct access to 20+ years of custom training curriculum combined with expert AI instruction without the noise of external web links.

Virtual tattoo instructor, friendly and professional, focused on personalized learning.

Helps write instructions for other GPTs!

Friendly UDL expert, myth-busting inclusively.

Provides comprehensive guidance on educational standards and assessments.

Yoga Guru with 500-hour YRT certification knowledge, creating custom yoga programs.

Align lessons to Next Generation Science Standards