Sandro Cavallari's repositories
compressor
Because we don't have enough time to read everything
expan
Open-source Python library for statistical analysis of randomised control trials (A/B tests)
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
graph-2-seq
implementing session based reccomadantion trpught gnn
Merlin
NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.
minimal
Minimal is a Jekyll theme for GitHub Pages
nvidia-merlin-redis
Three examples of recommendation system pipelines with NVIDIA Merlin and Redis
omnitext
Library for NLP
Optimus
Optimus: the first large-scale pre-trained VAE language model
ProG
All in One: Multi-task Prompting for Graph Neural Networks, KDD 2023.
pytorch-normalizing-flows
Normalizing flows in PyTorch. Current intended use is education not production.
quantifying-classification-uncertainty-in-deep-neural-networks
pytorch implementation on Uncertainty Estimation Using a Single Deep Deterministic Neural Network
rasa
rasa interviews
Reward-Optimizing-Reco
Materials for the "Reward Optimising Recommendation using Deep Learning and Fast Maximum Inner Product Search" tutorial delivered at the 28th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '22).
rust-arxiv-podcast
Arxiv podcast
SentenceMIM-demo
This repo contains code to reproduce some of the results presented in the paper "SentenceMIM: A Latent Variable Language Model"
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
systems
Merlin Systems provides tools for combining recommendation models with other elements of production recommender systems (like feature stores, nearest neighbor search, and exploration strategies) into end-to-end recommendation pipelines that can be served with Triton Inference Server.
TabFormer
Code & Data for "Tabular Transformers for Modeling Multivariate Time Series" (ICASSP, 2021)
the-art-of-debugging
The Art of Debugging
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
triton-client
Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.
ttt-lm-pytorch
Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States