Thomas Viehmann's Projects
Demonstration of using Caffe2 inside an Android application.
8-bit CUDA functions for PyTorch
Gaussian Processes in Pytorch
A library for benchmarking vulnerability to adversarial examples
The Python programming language
NumPy-like API accelerated with CUDA
The Natural Language Decathlon: A Multitask Challenge for NLP
Deep Learning Kurs
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
The fast.ai deep learning library, lessons, and tutorials
Estimate derivatives with finite differences
Submit stacked diffs to GitHub on the command line
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
repo for tvm
Economic models and things in Pytorch
Coalition agreement between the SPD, Green Party, and FDP as clean PDF file, .docx file, and .txt file
Open Source Differentiable Computer Vision Library for PyTorch
Toolbox of models, callbacks, and datasets for AI/ML researchers.
Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning.
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, quantization, LoRA fine-tuning, pre-training. Apache 2.0-licensed.
Lightning module for TorchDrift
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
PyTorch Tutorial at the LOD2021 conference
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
:ledger: Sphinx source parser for Jupyter notebooks
Acceleration package for neural networks on multi-core CPUs
Jupyter Interactive Notebook
A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")