Stars
Tiny-FSDP, a minimalistic re-implementation of the PyTorch FSDP
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
llama3 implementation one matrix multiplication at a time
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
Run Mixtral-8x7B models in Colab or consumer desktops
An open source implementation of CLIP.
JanusGraph: an open-source, distributed graph database
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
A library for Multilingual Unsupervised or Supervised word Embeddings
Productive, portable, and performant GPU programming in Python.
Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"
Portfolio and risk analytics in Python
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.
A simple implementation of Microsoft's AdPredictor (http://bit.ly/SFgcq8) in Python
A very simple framework for state-of-the-art Natural Language Processing (NLP)
A Flexible and Powerful Parameter Server for large-scale machine learning
The Noise Contrastive Estimation for softmax output written in Pytorch
Character-aware Neural Language Model implemented by PyTorch
Work in Australia as a Developer / 程序员如何申请到澳洲工作