Stars
VTK-based Data Analysis and Visualization Application
🔭 Plugin allowing VisIt to read openPMD files
In Situ Animation of Accelerated Computations 🔬
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
unofficial implementation of the CoT-decoding method for extract cot paths in an unsupervised way
SGLang is a fast serving framework for large language models and vision language models.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
A library for mechanistic interpretability of GPT-style language models
Arena-Hard-Auto: An automatic LLM benchmark.
FastAPI framework, high performance, easy to learn, fast to code, ready for production
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Open source codebase powering the HuggingChat app
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
Generative AI extensions for onnxruntime
🛏 An HTML to Markdown converter written in JavaScript
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
Convert PDF to markdown + JSON quickly with high accuracy
Implementation of Nougat Neural Optical Understanding for Academic Documents
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.