Best AI tools for< Shard Models >

Entry Point AI is a modern AI optimization platform for fine-tuning proprietary and open-source language models. It provides a user-friendly interface to manage prompts, fine-tunes, and evaluations in one place. The platform enables users to optimize models from leading providers, train across providers, work collaboratively, write templates, import/export data, share models, and avoid common pitfalls associated with fine-tuning. Entry Point AI simplifies the fine-tuning process, making it accessible to users without the need for extensive data, infrastructure, or insider knowledge.

Cortex Labs is a decentralized world computer that enables AI and AI-powered decentralized applications (dApps) to run on the blockchain. It offers a Layer2 solution called ZkMatrix, which utilizes zkRollup technology to enhance transaction speed and reduce fees. Cortex Virtual Machine (CVM) supports on-chain AI inference using GPU, ensuring deterministic results across computing environments. Cortex also enables machine learning in smart contracts and dApps, fostering an open-source ecosystem for AI researchers and developers to share models. The platform aims to solve the challenge of on-chain machine learning execution efficiently and deterministically, providing tools and resources for developers to integrate AI into blockchain applications.

Contentable.ai is a platform for comparing multiple AI models, rapidly moving from prototyping to production, and management of your custom AI solutions across multiple vendors. It allows users to test multiple AI models in seconds, compare models side-by-side across top AI providers, collaborate on AI models with their team seamlessly, design complex AI workflows without coding, and pay as they go.

Gradio is a tool that allows users to quickly and easily create web-based interfaces for their machine learning models. With Gradio, users can share their models with others, allowing them to interact with and use the models remotely. Gradio is easy to use and can be integrated with any Python library. It can be used to create a variety of different types of interfaces, including those for image classification, natural language processing, and time series analysis.

Kaedim is an online 3D model marketplace that allows users to browse, purchase, and download high-quality 3D models for use in various creative projects. The marketplace features a wide range of models, including characters, animals, vehicles, furniture, and more. Kaedim also offers a unique feature that allows users to generate custom 3D models on-the-spot using artificial intelligence.

Neptune is an MLOps stack component for experiment tracking. It allows users to track, compare, and share their models in one place. Neptune is used by scaling ML teams to skip days of debugging disorganized models, avoid long and messy model handovers, and start logging for free.

Masterpiece Studio is a powerful 3D creation tool that allows users to generate, edit, share, and use 3D models. With its intuitive interface and comprehensive set of features, Masterpiece Studio is perfect for artists, designers, engineers, and anyone else who wants to create stunning 3D models.

Nendo is a cloud-based 3D modeling software that allows users to create, edit, and share 3D models online. It is designed to be easy to use, even for beginners, and it offers a wide range of features that make it suitable for a variety of tasks, from simple 3D printing to complex architectural modeling.

RunwayML Experiments is a platform that allows users to create and share machine learning models. It provides a variety of tools and resources to help users get started with machine learning, including a library of pre-trained models, a visual programming interface, and a community of experts. RunwayML Experiments is used by a variety of people, including researchers, students, and hobbyists.

thisorthis.ai is an AI tool that allows users to compare generative AI models and AI model responses. It helps users analyze and evaluate different AI models to make informed decisions. The tool requires JavaScript to be enabled for optimal functionality.

Voicemy.ai is an AI application that allows users to create AI voices and songs. Users can clone voices of famous personalities, compose melodies, and convert text into spoken words using chosen voice models. The platform aims to inspire creativity and enable users to share their passion with the world.

DVC is an open-source platform for managing machine learning data and experiments. It provides a unified interface for working with data from various sources, including local files, cloud storage, and databases. DVC also includes tools for versioning data and experiments, tracking metrics, and automating compute resources. DVC is designed to make it easy for data scientists and machine learning engineers to collaborate on projects and share their work with others.

Chat Data is an AI application that allows users to create custom chatbots using their own data sources. Users can easily build and integrate chatbots with their websites or other platforms, personalize the chatbot's interface, and access advanced features like human support escalation and product updates synchronization. The platform offers HIPAA-compliant medical chat models and ensures data privacy by retaining conversation data exclusively within the user's browser. With Chat Data, users can enhance customer interactions, gather insights, and streamline communication processes.

Civitai is the home of open-source generative AI, offering a platform where users can create various digital content such as models, images, videos, posts, and articles. The platform fosters creativity and inspiration by providing a virtual canvas for users to express themselves artistically. Additionally, Civitai hosts contests, showcases community creations, and provides educational resources for users to enhance their skills in generative AI.

Civitai is an open-source generative AI platform that allows users to create images, videos, posts, articles, and bounties. It also provides a virtual canvas where users can unleash their creativity or get inspired by others. Civitai is a community-driven platform that offers a variety of resources for users, including tutorials, guides, and analysis on particular topics.

LLM Clash is a web-based application that allows users to compare the outputs of different large language models (LLMs) on a given task. Users can input a prompt and select which LLMs they want to compare. The application will then display the outputs of the LLMs side-by-side, allowing users to compare their strengths and weaknesses.

Qlone is a user-friendly 3D scanning app that allows users to easily create 3D models using their smartphone or tablet. The app offers seamless integration with leading 3D platforms for printing, sharing, and selling models. Users can create AR menus, scan various objects like food, people, and art, and engage in educational activities. Qlone is developed by EyeCue Vision Technologies LTD and is designed to provide a simple and efficient 3D scanning experience.

CrayEye is a multimodal multitool that allows users to craft and share vision prompts infused with real-world context from device sensors and APIs. It is a free, open-source tool written by AI, enabling users to experiment with visual multimodal models and interpret their environment in new ways. Users can analyze their surroundings using their smartphone's camera, customize prompts augmented by sensors and APIs, and share their creations with friends. CrayEye is a product of AI-driven development, offering a range of features to enhance user experience.

Quivr is an open-source chat-powered second brain application that transforms private and enterprise knowledge into a personal AI assistant. It continuously learns and improves at every interaction, offering AI-powered workplace search synced with user data. Quivr allows users to connect with their favorite tools, databases, and applications, and configure their 'second brain' to train on their company's unique context for improved search relevance and knowledge discovery.

Gooey.AI is a platform that provides access to a variety of AI models and tools, making it easy for users to build and deploy AI solutions. The platform offers a no-code interface, making it accessible to users of all skill levels. Gooey.AI also provides a community of users who share workflows and examples, making it easy to get started with AI development.

This repository contains Refact WebUI for fine-tuning and self-hosting of code models, which can be used inside Refact plugins for code completion and chat. Users can fine-tune open-source code models, self-host them, download and upload Lloras, use models for code completion and chat inside Refact plugins, shard models, host multiple small models on one GPU, and connect GPT-models for chat using OpenAI and Anthropic keys. The repository provides a Docker container for running the self-hosted server and supports various models for completion, chat, and fine-tuning. Refact is free for individuals and small teams under the BSD-3-Clause license, with custom installation options available for GPU support. The community and support include contributing guidelines, GitHub issues for bugs, a community forum, Discord for chatting, and Twitter for product news and updates.

Shards is a high-performance, multi-platform, type-safe programming language designed for visual development. It is a dataflow visual programming language that enables building full-fledged apps and games without traditional coding. Shards features automatic type checking, optimized shard implementations for high performance, and an intuitive visual workflow for beginners. The language allows seamless round-trip engineering between code and visual models, empowering users to create multi-platform apps easily. Shards also powers an upcoming AI-powered game creation system, enabling real-time collaboration and game development in a low to no-code environment.

llm-analysis is a tool designed for Latency and Memory Analysis of Transformer Models for Training and Inference. It automates the calculation of training or inference latency and memory usage for Large Language Models (LLMs) or Transformers based on specified model, GPU, data type, and parallelism configurations. The tool helps users to experiment with different setups theoretically, understand system performance, and optimize training/inference scenarios. It supports various parallelism schemes, communication methods, activation recomputation options, data types, and fine-tuning strategies. Users can integrate llm-analysis in their code using the `LLMAnalysis` class or use the provided entry point functions for command line interface. The tool provides lower-bound estimations of memory usage and latency, and aims to assist in achieving feasible and optimal setups for training or inference.

Prime is a framework for efficient, globally distributed training of AI models over the internet. It includes features such as fault-tolerant training with ElasticDeviceMesh, asynchronous distributed checkpointing, live checkpoint recovery, custom Int8 All-Reduce Kernel, maximizing bandwidth utilization, PyTorch FSDP2/DTensor ZeRO-3 implementation, and CPU off-loading. The framework aims to optimize communication, checkpointing, and bandwidth utilization for large-scale AI model training.

SuperAdapters is a tool designed to finetune Large Language Models (LLMs) with various adapters on different platforms. It supports models like Bloom, LLaMA, ChatGLM, Qwen, Baichuan, Mixtral, Phi, and more. Users can finetune LLMs on Windows, Linux, and Mac M1/2, handle train/test data with Terminal, File, or DataBase, and perform tasks like CausalLM and SequenceClassification. The tool provides detailed instructions on how to use different models with specific adapters for tasks like finetuning and inference. It also includes requirements for CentOS, Ubuntu, and MacOS, along with information on LLM downloads and data formats. Additionally, it offers parameters for finetuning and inference, as well as options for web and API-based inference.

The 'gritlm' repository provides all materials for the paper Generative Representational Instruction Tuning. It includes code for inference, training, evaluation, and known issues related to the GritLM model. The repository also offers models for embedding and generation tasks, along with instructions on how to train and evaluate the models. Additionally, it contains visualizations, acknowledgements, and a citation for referencing the work.

MaskLLM is a learnable pruning method that establishes Semi-structured Sparsity in Large Language Models (LLMs) to reduce computational overhead during inference. It is scalable and benefits from larger training datasets. The tool provides examples for running MaskLLM with Megatron-LM, preparing LLaMA checkpoints, pre-tokenizing C4 data for Megatron, generating prior masks, training MaskLLM, and evaluating the model. It also includes instructions for exporting sparse models to Huggingface.

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.

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.

cake is a pure Rust implementation of the llama3 LLM distributed inference based on Candle. The project aims to enable running large models on consumer hardware clusters of iOS, macOS, Linux, and Windows devices by sharding transformer blocks. It allows running inferences on models that wouldn't fit in a single device's GPU memory by batching contiguous transformer blocks on the same worker to minimize latency. The tool provides a way to optimize memory and disk space by splitting the model into smaller bundles for workers, ensuring they only have the necessary data. cake supports various OS, architectures, and accelerations, with different statuses for each configuration.

AMchat is a large language model that integrates advanced math concepts, exercises, and solutions. The model is based on the InternLM2-Math-7B model and is specifically designed to answer advanced math problems. It provides a comprehensive dataset that combines Math and advanced math exercises and solutions. Users can download the model from ModelScope or OpenXLab, deploy it locally or using Docker, and even retrain it using XTuner for fine-tuning. The tool also supports LMDeploy for quantization, OpenCompass for evaluation, and various other features for model deployment and evaluation. The project contributors have provided detailed documentation and guides for users to utilize the tool effectively.

Welcome to the ultimate hub for on-device Large Language Models (LLMs)! This repository is your go-to resource for all things related to LLMs designed for on-device deployment. Whether you're a seasoned researcher, an innovative developer, or an enthusiastic learner, this comprehensive collection of cutting-edge knowledge is your gateway to understanding, leveraging, and contributing to the exciting world of on-device LLMs.

This repository contains an uncensored list of free to use APIs and sites for several AI models. > _This list is mainly managed by @zukixa, the queen of zukijourney, so any decisions may have bias!~_ > > **Scroll down for the sites, APIs come first!** * * * > [!WARNING] > We are not endorsing _any_ of the listed services! Some of them might be considered controversial. We are not responsible for any legal, technical or any other damage caused by using the listed services. Data is provided without warranty of any kind. **Use these at your own risk!** * * * # APIs Table of Contents #### Overview of Existing APIs #### Overview of Existing APIs -- Top LLM Models Available #### Overview of Existing APIs -- Top Image Models Available #### Overview of Existing APIs -- Top Other Features & Models Available #### Overview of Existing APIs -- Available Donator Perks * * * ## API List:* *: This list solely covers all providers I (@zukixa) was able to collect metrics in. Any mistakes are not my responsibility, as I am either banned, or not aware of x API. \ 1: Last Updated 4/14/24 ### Overview of APIs: | Service | # of Users1 | Link | Stablity | NSFW Ok? | Open Source? | Owner(s) | Other Notes | | ----------- | ---------- | ------------------------------------------ | ------------------------------------------ | --------------------------- | ------------------------------------------------------ | -------------------------- | ----------------------------------------------------------------------------------------------------------- | | zukijourney| 4441 | D | High | On /unf/, not /v1/ | ✅, Here | @zukixa | Largest & Oldest GPT-4 API still continuously around. Offers other popular AI-related Bots too. | | Hyzenberg| 1234 | D | High | Forbidden | ❌ | @thatlukinhasguy & @voidiii | Experimental sister API to Zukijourney. Successor to HentAI | | NagaAI | 2883 | D | High | Forbidden | ❌ | @zentixua | Honorary successor to ChimeraGPT, the largest API in history (15k users). | | WebRaftAI | 993 | D | High | Forbidden | ❌ | @ds_gamer | Largest API by model count. Provides a lot of service/hosting related stuff too. | | KrakenAI | 388 | D | High | Discouraged | ❌ | @paninico | It is an API of all time. | | ShuttleAI | 3585 | D | Medium | Generally Permitted | ❌ | @xtristan | Faked GPT-4 Before 1, 2 | | Mandrill | 931 | D | Medium | Enterprise-Tier-Only | ❌ | @fredipy | DALL-E-3 access pioneering API. Has some issues with speed & stability nowadays. | oxygen | 742 | D | Medium | Donator-Only | ❌ | @thesketchubuser | Bri'ish 🤮 & Fren'sh 🤮 | | Skailar | 399 | D | Medium | Forbidden | ❌ | @aquadraws | Service is the personification of the word 'feature creep'. Lots of things announced, not much operational. |

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.

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

This repository contains an implementation of Ring Attention, a technique for processing large sequences in transformers. Ring Attention splits the data across the sequence dimension and applies ring reduce to the processing of the tiles of the attention matrix, similar to flash attention. It also includes support for Striped Attention, a follow-up paper that permutes the sequence for better workload balancing for autoregressive transformers, and grouped query attention, which saves on communication costs during the ring reduce. The repository includes a CUDA version of the flash attention kernel, which is used for the forward and backward passes of the ring attention. It also includes logic for splitting the sequence evenly among ranks, either within the attention function or in the external ring transformer wrapper, and basic test cases with two processes to check for equivalent output and gradients.

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.

This repository provides a set of ROS 2 packages to integrate llama.cpp into ROS 2. By using the llama_ros packages, you can easily incorporate the powerful optimization capabilities of llama.cpp into your ROS 2 projects by running GGUF-based LLMs and VLMs.

This repository contains the code that Defog uses for the evaluation of generated SQL. It's based off the schema from the Spider, but with a new set of hand-selected questions and queries grouped by query category. The testing procedure involves generating a SQL query, running both the 'gold' query and the generated query on their respective database to obtain dataframes with the results, comparing the dataframes using an 'exact' and a 'subset' match, logging these alongside other metrics of interest, and aggregating the results for reporting. The repository provides comprehensive instructions for installing dependencies, starting a Postgres instance, importing data into Postgres, importing data into Snowflake, using private data, implementing a query generator, and running the test with different runners.

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.

This GPT reviews business plans and pitch decks—Please note: This GPT does NOT share information for training in GPT models. It is responsible for assigning scores and providing feedback based on key criteria such as team background, financial projections, as well as conducting sentiment analysis.

Dream your own LEGO set.

This GPT can read all Streamlit Documantation and helps you about Streamlit.

Colab script expert, ensuring error-free, compatible code.

I'm here to make your Streamlit apps go viral!

I cannot share free OpenAI API keys. https://gptsapp123.com

落ちぶれた元トレーダー、現皮肉Tiktoker

Creates a share button for GPTs using a URL.

I authentically simulate the Shark Tank experience, complete with business pitches and realistic offers.

A zoological guide on sharks, providing informative insights.

I craft short, persuasive emails and catchy subject lines.

Jordan Belfort like financial expert with direct API integration

Host a comedic game show of absurd inventions!

Writes LI posts from article links you share, and you give tone and style for personalization, Then copy and paste to LI social profile, or via sharing tool

Sharp, humorous, and honest ENS appraiser.

Sharp, cunning Catan expert with concise advice.

Sharp, sarcastic tweets countering hate speech in 220 characters.

Share a shape and 3 colours and I will generate a beautiful generative art.

I'm a playful virtual pet 🐶🐱 eager to share fun images 📷 and adventures 🏞️!

A sharp-tongued GPT that subtly mocks using file-based phrases.