Harel Gal's starred repositories

storybook

Storybook is the industry standard workshop for building, documenting, and testing UI components in isolation

Language:TypeScriptLicense:MITStargazers:83538Issues:940Issues:12594

floating-ui

A JavaScript library to position floating elements and create interactions for them.

Language:TypeScriptLicense:MITStargazers:29167Issues:257Issues:1331

pytorch-lightning

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

Language:PythonLicense:Apache-2.0Stargazers:27561Issues:247Issues:6973

mlc-llm

Universal LLM Deployment Engine with ML Compilation

Language:PythonLicense:Apache-2.0Stargazers:17857Issues:168Issues:1208

doris

Apache Doris is an easy-to-use, high performance and unified analytics database.

Language:JavaLicense:Apache-2.0Stargazers:11958Issues:284Issues:7036

web-llm

High-performance In-browser LLM Inference Engine

Language:TypeScriptLicense:Apache-2.0Stargazers:11832Issues:112Issues:263

fast

The adaptive interface system for modern web experiences.

Language:TypeScriptLicense:NOASSERTIONStargazers:9166Issues:123Issues:2670

llrt

LLRT (Low Latency Runtime) is an experimental, lightweight JavaScript runtime designed to address the growing demand for fast and efficient Serverless applications.

Language:JavaScriptLicense:Apache-2.0Stargazers:7810Issues:47Issues:119

mergekit

Tools for merging pretrained large language models.

Language:PythonLicense:LGPL-3.0Stargazers:4136Issues:46Issues:252

style-dictionary

A build system for creating cross-platform styles.

Language:JavaScriptLicense:Apache-2.0Stargazers:3766Issues:48Issues:581

openv0

AI generated UI components

Language:TypeScriptLicense:MITStargazers:3301Issues:37Issues:35

essentia

C++ library for audio and music analysis, description and synthesis, including Python bindings

Language:C++License:AGPL-3.0Stargazers:2766Issues:109Issues:1045

components

React components for Cloudscape Design System

Language:TypeScriptLicense:Apache-2.0Stargazers:2306Issues:29Issues:230

promptbench

A unified evaluation framework for large language models

Language:PythonLicense:MITStargazers:2287Issues:22Issues:45

checklist

Beyond Accuracy: Behavioral Testing of NLP models with CheckList

Language:Jupyter NotebookLicense:MITStargazers:1991Issues:29Issues:89

community-group

This is the official DTCG repository for the design tokens specification.

Language:HTMLLicense:NOASSERTIONStargazers:1491Issues:219Issues:139

madmom

Python audio and music signal processing library

Language:PythonLicense:NOASSERTIONStargazers:1280Issues:43Issues:264

amazon-bedrock-workshop

This is a workshop designed for Amazon Bedrock a foundational model service.

Language:Jupyter NotebookLicense:MIT-0Stargazers:1267Issues:36Issues:108

lm-format-enforcer

Enforce the output format (JSON Schema, Regex etc) of a language model

Language:PythonLicense:MITStargazers:1130Issues:11Issues:92

clipper.js

HTML to Markdown converter and crawler.

Language:TypeScriptLicense:Apache-2.0Stargazers:462Issues:4Issues:6

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

Language:PythonLicense:Apache-2.0Stargazers:418Issues:6Issues:24

genai-quickstart-pocs

This repository contains sample code demonstrating various use cases leveraging Amazon Bedrock and Generative AI. Each sample is a separate project with its own directory, and includes a basic Streamlit frontend to help users quickly set up a proof of concept.

Language:PythonLicense:MIT-0Stargazers:256Issues:10Issues:45

DecodingTrust

A Comprehensive Assessment of Trustworthiness in GPT Models

Language:PythonLicense:CC-BY-SA-4.0Stargazers:232Issues:6Issues:22

llm-comparator

LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.

Language:JavaScriptLicense:Apache-2.0Stargazers:228Issues:4Issues:0

fiddler-auditor

Fiddler Auditor is a tool to evaluate language models.

Language:PythonLicense:NOASSERTIONStargazers:159Issues:8Issues:18

CodeSage

CodeSage: Code Representation Learning At Scale (ICLR 2024)

Language:PythonLicense:Apache-2.0Stargazers:74Issues:6Issues:4

langchain-aws

Build LangChain Applications on AWS

Language:PythonLicense:MITStargazers:69Issues:10Issues:39

agent-evaluation

A generative AI-powered framework for testing virtual agents.

Language:PythonLicense:Apache-2.0Stargazers:64Issues:2Issues:25

fm-leaderboarder

FM-Leaderboard-er allows you to create leaderboard to find the best LLM/prompt for your own business use case based on your data, task, prompts

Language:PythonLicense:Apache-2.0Stargazers:14Issues:5Issues:10

k8s-operators-workshop

A Kubernetes Operators Workshop

Language:GoLicense:MITStargazers:2Issues:1Issues:2