This repository is a chat example with LLaMA models running on a typical home PC. You will just need a NVIDIA video card and some RAM to chat with model. By using HF version you may fine-tune the model to any desired task.
System requirements: A modern enough CPU, NVIDIA graphics card (2 Gb of VRAM is ok); HF version is able to run on CPU, or mixed CPU/GPU, or pure GPU, 64 or better 128 Gb of RAM (192 would be perfect for 65B model).
Top, but for GPU processing on nVidia cards.
An AI assisted utility in which you scribble over something you want removed from an image, and it extrapolates and knits the surrounding background over it. CUDA enabled. Works with high resolution images just as well as boring ones. Multi-stroke support.
GPUtil is a Python module for getting the GPU status from NVIDA GPUs using nvidia-smi. GPUtil locates all GPUs on the computer, determines their availablity and returns a ordered list of available GPUs. Availablity is based upon the current memory consumption and load of each GPU. The module is written with GPU selection for Deep Learning in mind, but it is not task/library specific and it can be applied to any task, where it may be useful to identify available GPUs.
nvidia-smi aside, all of its dependencies are in the basic Python install.
In order to get maximum capability of these utilities, you should be running with a kernel that provides support of the GPUs you have installed. If using AMD GPUs, installing the latest amdgpu driver package or the latest ROCm release, may provide additional capabilities. If you have Nvidia GPUs installed, you should have nvidia-smi installed in order for the utility reading of the cards to be possible. Writing to GPUs is currently only possible for AMD GPUs.
A generative adversarial network that takes images and re-does them in various anime studios' styles. GPU enabled. Download the pre-trained model to get a jumpstart.
Nyuzi is an experimental GPGPU processor hardware design focused on compute intensive tasks. It is optimized for use cases like deep learning and image processing.
This project includes a synthesizable hardware design written in System Verilog, an instruction set emulator, an LLVM based C/C++ compiler, software libraries, and tests. It can be used to experiment with microarchitectural and instruction set design tradeoffs.
Broadcom opensourced the GPU drivers for the RaspberryPi under a three-clause BSD license. The code is fully functional, hasn't been reverse engineered, and can be compiled and used imediately on the RasPi.
Can be used with audio files and probably a hot mic to transcribe speech into text for later processing. Uses git Large File Storage for the neural network objects. GPU acceleration enabled. Includes trained models as well as source code. Available in PyPy as deepspeech and deepspeech-gpu. Supports the RasPi explicitly as a platform, interestingly.
Looking at the releases page is a good way to keep up with the project: https://github.com/mozilla/DeepSpeech/releases