H2O.ai ORG

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/

h2oGPT is a self-hosted AI chat assistant you run on your own computer, upload documents and ask the AI questions about them while all data stays private.

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.

H2O is an open-source machine learning platform that trains models on large datasets across distributed clusters, with AutoML to automatically find and rank the best algorithm without manual tuning.

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

Realtime Web Apps and Dashboards for Python and R

Please visit https://github.com/h2oai/h2o-3 for latest H2O

A Python package for manipulating 2-dimensional tabular data structures

Tutorials and training material for the H2O Machine Learning Platform

Sparkling Water provides H2O functionality inside Spark cluster

H2O.ai Machine Learning Interpretability Resources

H2Oai GPU Edition

Presentations from H2O meetups & conferences by the H2O.ai team

A curated list of research, applications and projects built using the H2O Machine Learning platform

reproducible benchmark of database-like ops

Open-Source Implementation of WizardLM to turn documents into Q:A pairs for LLM fine-tuning

No description.

Deep Learning in H2O using Native GPU Backends

Recipes for Driverless AI

Create apps 10x quicker, without Javascript/HTML/CSS.

Sample AI Apps built with H2O Wave.

Web based interactive computing environment for H2O

This is a repo for all the tutorials put out by H2O.ai. This includes learning paths for Driverless AI, H2O-3, Sparkling Water and more...

Client Code Examples, Use Cases and Benchmarks for Enterprise h2oGPTe RAG-Based GenAI Platform

H2O.ai fork of https://codeberg.org/jbruchon/jdupes

Large-language Model Evaluation framework with Elo Leaderboard and A-B testing

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Flink and DataFlow

training material

No description.

Templates for projects based on top of H2O.

H2OAI Driverless AI Code Samples and Tutorials

No description.

No description.

No description.

Domain name classifier looking for good vs. possibly malicious providers

A collection of data science examples implemented across a variety of languages and libraries.

AI-powered flood intelligence system featuring h2oGPTe Agent + NVIDIA NIM integration (A2A), NAT pipeline with Nemotron 49B, and real-time flood risk assessment. Part of NVIDIA–H2O.ai AI for Good Blueprint for disaster response and monitoring.

Experiment on QnA tabular data using LLMs and SQL

H2O Open Source Kubernetes operator and a command-line tool to ease deployment (and undeployment) of H2O open-source machine learning platform H2O-3 to Kubernetes.

Node.js bindings to H2O, the open-source prediction engine for big data science.

Wave App for H2O AutoML

GenAI apps from H2O made Wave

No description.

Performance Benchmarks

No description.

Python 2.7 & 3.5+ runtime type-checker

A collection of open-source GPU accelerated Python tools and examples for quantitative analyst tasks and leverages RAPIDS AI project, Numba, cuDF, and Dask.

Repository for SF QConf 2015 Workshop

A interactive playground to style and edit images, generate art and have fun.

No description.

Article for Special Edition of Information: Machine Learning with Python

Minimal graph-based issue tracker for long-horizon AI agent tasks

No description.

A Toolbox for Responsible Predictive and Generative AI.

Leland Wilkinson's engine for automatic visualizations of tabular datasets

No description.

H2O Cloud Discovery Client.

No description.

Examples for deploying Driverless AI (DAI) scorers.

Ask Craig application

AI code assistance for GitHub Actions on your infrastructure, powered by h2oGPTe.

Examples of techniques for training interpretable ML models, explaining ML models, and debugging ML models for accuracy, discrimination, and security.

Perrier - A blend of Spark & H2O <This is no longer a dependency for SparklingWater

No description.

A fast, distributed, high performance gradient boosting (GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks. It is under the umbrella of the DMTK(http://github.com/microsoft/dmtk) project of Microsoft.

Universal Token Provider

Java API for Google Analytics Measurement Protocol (part of Universal Analytics).

Guidelines for the responsible use of explainable AI and machine learning

Rapid application development for a more... civilized age.

No description.

H2O Model Validation Training

Computation using data flow graphs for scalable machine learning

Open Large Language Model Text Generation Inference - will remain Apache-2.0

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

Make websites accessible for AI agents

Repository for H2O.ai's Generative AI Training

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

dask-pytorch is a Python package that makes it easy to train PyTorch models on dask clusters using distributed data parallel.

CUDA Implementation for the H2O version of the LightGBM package

This package gives you the opportunity to use a Target mean Encoding.

Mirror of Apache Metron (Incubating)

This wave application is a R data.table tutorial and interactive learning environment developed using the wave library for R.

No description.

No description.

No description.

No description.

H2O Cloud code.

Bring Your Own Evals

SDK for text-2-everything

No description.

RAPIDS TPCx-BB

Specify what you want it to build, the AI asks for clarification, and then builds it.

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

The platform that powers Airbyte. Please file issues in https://github.com/airbytehq/airbyte

[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.

No description.

No description.

Dart/Flutter <-> Python transpiler

Python package repository

Wave Dashboard for the OpenML AutoML Benchmark

No description.

Modified version of https://github.com/camelot-dev/camelot

High performance, interactive statistical graphics engine for the web.

No description.

Main package repository for production Wolfi images

cuGraph - RAPIDS Graph Analytics Library

Spawn JupyterHub single-user servers with sudo

A game theoretic approach to explain the output of any machine learning model.

Multilingual Sentence & Image Embeddings with BERT

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

No description.

A simple RPC framework with protobuf service definitions

The official Python library for the OpenAI API

Bitnami container images

No description.

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

A high-throughput and memory-efficient inference and serving engine for LLMs

A high-throughput and memory-efficient inference and serving engine for LLMs

Process background jobs in Go

TypeScript Twirp client generator

A poor-man's hacky replacement for Anaconda Server. For small groups behind a firewall

UniLM - Unified Language Model Pre-training / Pre-training for NLP and Beyond

Generate TypeScript client for gRPC API exposed via grpc-gateway. Powered by protobuf-es framework and bun toolchain.

A Golang client for Druid

Python implementation of Benford's Law tests.

**This is a fork of reflections library to unblock our development with the newest version of this library. After official 0.9.11 release of the library, this repository should be deleted.**

goconfig uses a struct as input and populates the fields of this struct with parameters from command line, environment variables and configuration file.

No description.

No description.

No description.

No description.

Testing ground to ensure mojos backward compatibility

No description.

No description.

No description.

An initiate of H2O.ai to build AI apps to solve complex healthcare and life science problems

No description.

Yet another markdown-to-documentation generator

No description.

No description.

No description.

No description.

No description.

No description.

A conda-smithy repository for ucx-split.

Scale Optuna with Dask

Rapids Analytics Framework Toolset to share building blocks between cuGraph and cuML

RAPIDS - combined conda package & integration tests for all of RAPIDS libraries

Utilities for Dask and CUDA interactions

A collection of RAPIDS examples for security analysts, data scientists, and engineers to quickly get started applying RAPIDS and GPU acceleration to real-world cybersecurity use cases.

cuSignal - RAPIDS Signal Processing Library

Python bindings for UCX

cuML - RAPIDS Machine Learning Library

CUDA-accelerated GIS and spatiotemporal algorithms

cuDF - GPU DataFrame Library

RAPIDS Memory Manager

NumPy-like API accelerated with CUDA

A conda-smithy repository for ffmpeg.

A JupyterLab extension for displaying dashboards of GPU usage.

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

Third-party source packages that are modified for use in Triton.

The core library and APIs implementing the Triton Inference Server.

Instruct-tune LLaMA on consumer hardware

GenSON is a powerful, user-friendly JSON Schema generator built in Python.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

AWS Marketplace SaaS Build Tools

No description.

The missing bridge between Java and native C++

An Open Source Machine Learning Framework for Everyone

an ES2015 port of h2o-flow

Python module to read, parse and converting Microsoft Outlook MSG E-Mail files.

AI Verify

Jupyter magics and kernels for working with remote Spark clusters

protoc-gen-grpc-gateway-ts is a Typescript client generator for the grpc-gateway project. It generates idiomatic Typescript clients that connect the web frontend and golang backend fronted by grpc-gateway.

swagger-codegen contains a template-driven engine to generate documentation, API clients and server stubs in different languages by parsing your OpenAPI / Swagger definition.

Official implementation of Character Region Awareness for Text Detection (CRAFT)

Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.

DuckDB is an in-process SQL OLAP Database Management System

Use locally running LLMs directly from Siri 🦙🟣

Fast and memory-efficient exact attention

Java bytecode engineering toolkit

MCP Server for Snowflake including Cortex AI, object management, SQL orchestration, semantic view consumption, and more

No description.

No description.

No description.

No description.

No description.

A simple artifacts exchange.

Cypress.io test automation for Q

No description.

No description.

Documentation issues/request for engines, models, and applications in the H2O AI Cloud

No description.

No description.

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

Measure LLM summary quality using geometry and the Russian doll analogy — cosine and Geometric Algebra implementations

No description.

recipes for wildbook

No description.

On-demand self-hosted AWS EC2 runner for GitHub Actions