Best AI tools for< Create Baseline Models >

Phenaki is a model capable of generating realistic videos from a sequence of textual prompts. It is particularly challenging to generate videos from text due to the computational cost, limited quantities of high-quality text-video data, and variable length of videos. To address these issues, Phenaki introduces a new causal model for learning video representation, which compresses the video to a small representation of discrete tokens. This tokenizer uses causal attention in time, which allows it to work with variable-length videos. To generate video tokens from text, Phenaki uses a bidirectional masked transformer conditioned on pre-computed text tokens. The generated video tokens are subsequently de-tokenized to create the actual video. To address data issues, Phenaki demonstrates how joint training on a large corpus of image-text pairs as well as a smaller number of video-text examples can result in generalization beyond what is available in the video datasets. Compared to previous video generation methods, Phenaki can generate arbitrarily long videos conditioned on a sequence of prompts (i.e., time-variable text or a story) in an open domain. To the best of our knowledge, this is the first time a paper studies generating videos from time-variable prompts. In addition, the proposed video encoder-decoder outperforms all per-frame baselines currently used in the literature in terms of spatio-temporal quality and the number of tokens per video.

Create is a free-to-use AI app builder that lets you code using plain text and images. With Create, you can design and build apps like a pro, without having to write a single line of code. Create is perfect for building internal tools, prototypes, and even full-fledged applications.

This website allows users to create AI characters and chat with them. Users can customize their characters' appearance, personality, and interests. They can also choose from a variety of topics to chat about. The website uses artificial intelligence to generate the characters' responses, which are designed to be realistic and engaging.

RE:Create is an AI-powered app that provides endless content ideas and recreates any Instagram/Tiktok video in your style, tone, language, and even your voice! Our application streamlines the content creation process, eliminating the need for extensive planning and strategy. Save time and effort while achieving effective results. No need to hire a separate voiceover artist. Our application offers customizable voice options, ensuring your videos have the perfect audio to complement the visuals. No need to hire a professional scriptwriter. Our platform assists in creating engaging video scripts, guiding you through the process and ensuring your content flows seamlessly.

Create A Meme (C.A.M) is an AI-powered platform that allows users to easily create personalized and unique memes. With features like Magic, Custom, Template, and Classic modes, users can unleash their creativity and make viral memes online for free. C.A.M offers basic functionalities for free and a Plus tier for enhanced meme capabilities. The platform supports multiple languages and AI technology ensures that memes are always funny and relevant.

Create AI Voiceovers is an online text-to-speech generator that allows users to convert text into realistic-sounding AI voices. With over 530 AI voices available in 220+ languages and dialects, users can create voiceovers for various purposes, including marketing, eLearning, explainer videos, and animations. The platform offers a range of features, including the ability to adjust voice attributes such as pitch, emphasis, and speed, as well as add background music and sound effects. Create AI Voiceovers also provides a library of pre-recorded sound effects and music that users can incorporate into their voiceovers.

Create a Meme is a website that allows users to create and share memes. It offers a variety of features, including a library of pre-made memes, the ability to upload your own images, and a variety of editing tools. Create a Meme is a popular website with over 100 million users. It is a great way to create and share funny and entertaining memes with your friends and family.

This website provides a tool that allows users to create ebooks in seconds. It is a simple and easy-to-use tool that can be used by anyone, regardless of their technical expertise. The tool provides a variety of templates and features that can be used to create professional-looking ebooks.

Freepik is a website that provides high-quality stock content for creatives. It offers a wide range of assets, including images, vectors, videos, PSDs, AI images, and icons. Freepik also has a number of tools that can help creatives with their projects, such as an AI image generator, a mockup generator, and a photo editor.

Google Workspace is a suite of business apps and collaboration tools designed to enhance productivity and streamline communication for individuals, small businesses, enterprises, and frontline workers. With popular applications like Gmail, Calendar, Drive, Meet, and more, Google Workspace integrates AI-powered features through Gemini for Workspace to provide users with advanced capabilities for creating, connecting, and collaborating. The platform offers various plans tailored to meet diverse business needs, ensuring data control and productivity enhancement.

Photoroom is an AI photo editor application that offers a wide range of tools to enhance and edit images. It allows users to remove backgrounds, create product pictures, and generate professional visuals for various purposes. With features like AI Background Remover, AI Retouch, and AI Shadows, Photoroom simplifies the editing process and helps users create stunning images effortlessly. The application caters to individuals, small businesses, and creative teams, offering different subscription plans to suit varying needs. Photoroom is known for its user-friendly interface, affordable pricing, and efficient editing capabilities, making it a popular choice among online sellers, content creators, and small businesses.

VEED.IO is an online video editor that uses AI to help users create professional-quality videos quickly and easily. With VEED.IO, users can add subtitles, remove background noise, and more. VEED.IO is also a great tool for creating videos for social media, marketing, and education.

Yodayo is an AI-enabled creative platform for anime fandom. It is a place where anime fans can share and create more of what they love. The platform includes an AI Art Tavern, where users can create and share AI-generated anime art. Yodayo also hosts contests and provides guides for creating anime art.

Slidesgo is an online platform that provides free and premium Google Slides and PowerPoint templates. With Slidesgo, you can create presentations in minutes using AI presentation maker or choose from a variety of editable templates. Slidesgo also offers a variety of resources to help you learn how to use Google Slides and PowerPoint, including tutorials, blog articles, and presentation tips.

NightCafe Creator is an AI Art Generator app with multiple methods of AI art generation. Using neural style transfer, you can turn your photo into a masterpiece. Using text-to-image AI, you can create an artwork from nothing but words on a page. Enter a text prompt, and the generator will make stunning images. With modern diffusion technology, creating art couldn't be simpler (or more fun). Your creations belong to you, and you can do whatever you like with them (provided you are - or have permission from - the copyright owner of any input images, and subject to Copyright laws in your jurisdiction).

Vidnoz AI is a free online AI video generator that allows users to create engaging videos quickly and easily. With over 600 AI avatars, 470 realistic AI voices, and 600 templates to choose from, users can create videos for a variety of purposes, including marketing, education, and communication. Vidnoz AI is also easy to use, with a simple drag-and-drop interface and no prior video editing experience required.

Undress AI is a free online tool that allows users to create deepnude images. Deepnude images are realistic, nude images of people that are generated using artificial intelligence. The tool is easy to use and does not require any special skills or knowledge. Simply upload an image of a person and the tool will generate a deepnude image of that person.

NightCafe is an AI Image Generator and Community platform where users can create beautiful art in seconds with the help of Artificial Intelligence. It offers a vibrant AI Art community where millions of people come together to create, share, and discuss AI art. NightCafe provides access to a variety of algorithms such as Stable Diffusion, DALL-E 2, CLIP-Guided Diffusion, VQGAN+CLIP, and Neural Style Transfer. Users can participate in daily AI Art challenges, share their creations, and engage in conversations with other creatives. The platform aims to inspire creativity and provide a space for art enthusiasts to explore the world of AI-generated art.

MailerLite is an email marketing service that helps businesses grow their audience and drive revenue. It offers a range of features, including email marketing, automation, website building, and e-commerce integrations. MailerLite is known for its user-friendly interface, award-winning support, and affordable pricing.

HyperBooth is an AI image generator tool that allows users to create stunning AI photos instantly with just one selfie. It offers a wide range of artistic AI images in various styles, making it easy for users to generate high-quality AI photos for professional or social media profiles, personal projects, or simply for fun. With a user-friendly interface and quick processing time, HyperBooth simplifies the process of creating photorealistic AI images without the need for prior AI or coding knowledge.

Pgx is a collection of GPU/TPU-accelerated parallel game simulators for reinforcement learning (RL). It provides JAX-native game simulators for various games like Backgammon, Chess, Shogi, and Go, offering super fast parallel execution on accelerators and beautiful visualization in SVG format. Pgx focuses on faster implementations while also being sufficiently general, allowing environments to be converted to the AEC API of PettingZoo for running Pgx environments through the PettingZoo API.

K2 (GeoLLaMA) is a large language model for geoscience, trained on geoscience literature and fine-tuned with knowledge-intensive instruction data. It outperforms baseline models on objective and subjective tasks. The repository provides K2 weights, core data of GeoSignal, GeoBench benchmark, and code for further pretraining and instruction tuning. The model is available on Hugging Face for use. The project aims to create larger and more powerful geoscience language models in the future.

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.

Qwen is a series of large language models developed by Alibaba DAMO Academy. It outperforms the baseline models of similar model sizes on a series of benchmark datasets, e.g., MMLU, C-Eval, GSM8K, MATH, HumanEval, MBPP, BBH, etc., which evaluate the models’ capabilities on natural language understanding, mathematic problem solving, coding, etc. Qwen models outperform the baseline models of similar model sizes on a series of benchmark datasets, e.g., MMLU, C-Eval, GSM8K, MATH, HumanEval, MBPP, BBH, etc., which evaluate the models’ capabilities on natural language understanding, mathematic problem solving, coding, etc. Qwen-72B achieves better performance than LLaMA2-70B on all tasks and outperforms GPT-3.5 on 7 out of 10 tasks.

Woodpecker is a tool designed to correct hallucinations in Multimodal Large Language Models (MLLMs) by introducing a training-free method that picks out and corrects inconsistencies between generated text and image content. It consists of five stages: key concept extraction, question formulation, visual knowledge validation, visual claim generation, and hallucination correction. Woodpecker can be easily integrated with different MLLMs and provides interpretable results by accessing intermediate outputs of the stages. The tool has shown significant improvements in accuracy over baseline models like MiniGPT-4 and mPLUG-Owl.

The AI Scientist is a comprehensive system for fully automatic scientific discovery, enabling Foundation Models to perform research independently. It aims to tackle the grand challenge of developing agents capable of conducting scientific research and discovering new knowledge. The tool generates papers on various topics using Large Language Models (LLMs) and provides a platform for exploring new research ideas. Users can create their own templates for specific areas of study and run experiments to generate papers. However, caution is advised as the codebase executes LLM-written code, which may pose risks such as the use of potentially dangerous packages and web access.

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.

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.

LLM-Blender is a framework for ensembling large language models (LLMs) to achieve superior performance. It consists of two modules: PairRanker and GenFuser. PairRanker uses pairwise comparisons to distinguish between candidate outputs, while GenFuser merges the top-ranked candidates to create an improved output. LLM-Blender has been shown to significantly surpass the best LLMs and baseline ensembling methods across various metrics on the MixInstruct benchmark dataset.

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. |  |

Eval-Scope is a framework designed to support the evaluation of large language models (LLMs) by providing pre-configured benchmark datasets, common evaluation metrics, model integration, automatic evaluation for objective questions, complex task evaluation using expert models, reports generation, visualization tools, and model inference performance evaluation. It is lightweight, easy to customize, supports new dataset integration, model hosting on ModelScope, deployment of locally hosted models, and rich evaluation metrics. Eval-Scope also supports various evaluation modes like single mode, pairwise-baseline mode, and pairwise (all) mode, making it suitable for assessing and improving LLMs.

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.

TriForce is a training-free tool designed to accelerate long sequence generation. It supports long-context Llama models and offers both on-chip and offloading capabilities. Users can achieve a 2.2x speedup on a single A100 GPU. TriForce also provides options for offloading with tensor parallelism or without it, catering to different hardware configurations. The tool includes a baseline for comparison and is optimized for performance on RTX 4090 GPUs. Users can cite the associated paper if they find TriForce useful for their projects.

This repository provides the latest implementation for the AI Horde Worker, allowing users to utilize their graphics card(s) to generate, post-process, or analyze images for others. It offers a platform where users can create images and earn 'kudos' in return, granting priority for their own image generations. The repository includes important details for setup, recommendations for system configurations, instructions for installation on Windows and Linux, basic usage guidelines, and information on updating the AI Horde Worker. Users can also run the worker with multiple GPUs and receive notifications for updates through Discord. Additionally, the repository contains models that are licensed under the CreativeML OpenRAIL License.

MLE-Agent is an intelligent companion designed for machine learning engineers and researchers. It features autonomous baseline creation, integration with Arxiv and Papers with Code, smart debugging, file system organization, comprehensive tools integration, and an interactive CLI chat interface for seamless AI engineering and research workflows.

This repository compiles a list of academic papers that evaluate, align, simulate, and provide surveys or perspectives on the use of Large Language Models (LLMs) in the field of Social Science. The papers cover various aspects of LLM research, including assessing their alignment with human values, evaluating their capabilities in tasks such as opinion formation and moral reasoning, and exploring their potential for simulating social interactions and addressing issues in diverse fields of Social Science. The repository aims to provide a comprehensive resource for researchers and practitioners interested in the intersection of LLMs and Social Science.

FuseMedML is a Python framework designed to accelerate machine learning-based discovery in the medical field by promoting code reuse. It provides a flexible design concept where data is stored in a nested dictionary, allowing easy handling of multi-modality information. The framework includes components for creating custom models, loss functions, metrics, and data processing operators. Additionally, FuseMedML offers 'batteries included' key components such as fuse.data for data processing, fuse.eval for model evaluation, and fuse.dl for reusable deep learning components. It supports PyTorch and PyTorch Lightning libraries and encourages the creation of domain extensions for specific medical domains.

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.

First, please say "Create an agent team to do 〇〇." / 最初に「〇〇をするためのエージェントチームを作成してください」とお伝え下さい

Let's get started by telling me about your business: What do you offer? Who do you serve? ------------------------------------------------------- Need help Prompt Engineering? Reach out on LinkedIn: StephenHnilica

AI tool for designing engaging, trendy Pinterest pins.

Generates 3D stereogram pairs for parallel viewing.

2500+ word stories in target language with images, for language learning.

Level up Now. Upload a selfie for some superhero flair. Create a backstory. Select a superpower, arch-villain, and crew. Answer trivia. Pow!

Tell me about your situation and the type of prayer you would like

利用专业的周易知识和命理知识进行头像设计 Generates and explains lucky profile pictures based on I Ching, zodiac.

创建你自己的数字人形象，Sponsor：小红书“ItsJoe就出行”

I'll recreate a competitor website for your business

Create a very detailed prompt from the image. 画像からめっちゃ詳細なプロンプトを作成します。まずは解析して欲しい画像を送ってみてください。

1) Input a URL, attachment, or copy/paste a bunch of info about your biz. 2) I will return a summary of what's important. 3) Use what I give you for other prompts, e.g.: marketing strategy, content ideas, competitive analysis, etc

Create a Mythological Creature for playing with imagination and possibilities

Autonomously creates complete TikTok scenarios with images.

Simulates advisory board meetings with investors. Get generated advice for your startup from a GPT educated by domain experts.

Advisor for hairstyles, top products, and salon recommendations matched with your hair type and location.

Replicate Image, Images Mergeve, Imaginative Edit, Style Transfer. Use "Help" for more info. 20+ features of the source image will be transferred. You also can call this GPT via @ in any chat (desktop only).

I create soothing cat images.

Create business processes using Flowscript markup

I create nursing care plans based on triage info.