Stars
Fast GPU error-bounded lossy compressor for floating-point data.
Numerical weather prediction code from the WRF model, translated from Fortran to CUDA-C. Too fast.
A collection of diagnostic and interpolation routines for use with output from the Weather Research and Forecasting (WRF-ARW) Model.
【🔞🔞🔞 内含不适合未成年人阅读的图片】基于我擅长的编程、绘画、写作展开的 AI 探索和总结：StableDiffusion 是一种强大的图像生成模型，能够通过对一张图片进行演化来生成新的图片。ChatGPT 是一个基于 Transformer 的语言生成模型，它能够自动为输入的主题生成合适的文章。而 Github Copilot 是一个智能编程助手，能够加速日常编程活动。
An open-source solution that leverages machine learning to improve numerical weather predictions. Due to data corruption on my end, the model no longer functions.
Download numerical weather prediction datasets (HRRR, RAP, GFS, IFS, etc.) from NOMADS, NODD partners (Amazon, Google, Microsoft), ECMWF open data, and the University of Utah Pando Archive System.
A work in progress. Trying to write about all interesting or necessary pieces in the current development of LLMs and generative AI. Gradually adding more topics.
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
The "vicuna-installation-guide" provides step-by-step instructions for installing and configuring Vicuna 13 and 7B
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/
How you can fine-tune a GPT-3 model with Python with your own data
Interact with your documents using the power of GPT, 100% privately, no data leaks
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Lord of Large Language and Multi modal Systems Web User Interface
Instruct-tune LLaMA on consumer hardware
Node.js example app from the OpenAI API quickstart tutorial
Making large AI models cheaper, faster and more accessible
EdgeCloudSim: An Environment for Performance Evaluation of Edge Computing Systems
Architecture-level Fault Injection Tool for GPU Application Resilience Evaluation
CoLoRe - Cosmological Lofty Realizations
LCFI is an LLVM based lossy compression fault injection tool modified from LLFI.
Developed with the UROP, Detecting Deep Learning Software Defects (Spring 2019), HKUST
DLFuzz: An Efficient Fuzzing Testing Framework of Deep Learning Systems