sent2vec
General purpose unsupervised sentence representationsML_course
EPFL Machine Learning Course, Fall 2023attention-cnn
Source code for "On the Relationship between Self-Attention and Convolutional Layers"OptML_course
EPFL Course - Optimization for Machine Learning - CS-439landmark-attention
Landmark Attention: Random-Access Infinite Context Length for Transformersfederated-learning-public-code
collaborative-attention
Code for Multi-Head Attention: Collaborate Instead of Concatenatepowersgd
Practical low-rank gradient compression for distributed optimization: https://arxiv.org/abs/1905.13727disco
Decentralized & federated privacy-preserving ML training, using p2p networking, in JSdynamic-sparse-flash-attention
DenseFormer
ChocoSGD
Decentralized SGD and Consensus with Communication Compression: https://arxiv.org/abs/1907.09356llm-baselines
sparsifiedSGD
Sparsified SGD with Memory: https://arxiv.org/abs/1809.07599optML-pku
summer school materialsLocalSGD-Code
error-feedback-SGD
SGD with compressed gradients and error-feedback: https://arxiv.org/abs/1901.09847Bi-Sent2Vec
Robust Cross-lingual Embeddings from Parallel Sentencesbyzantine-robust-optimizer
Learning from history for Byzantine Robustnessopt-summerschool
Short Course on Optimization for Machine Learning - Slides and Practical Labs - DS3 Data Science Summer School, June 24 to 28, 2019, Paris, Franceinterpret-lm-knowledge
Extracting knowledge graphs from language models as a diagnostic benchmark of model performance (NeurIPS XAI 2021).cola
CoLa - Decentralized Linear Learning: https://arxiv.org/abs/1808.04883opt-shortcourse
Short Course on Optimization for Machine Learning - Slides and Practical Lab - Pre-doc Summer School on Learning Systems, July 3 to 7, 2017, Zürich, Switzerlandbyzantine-robust-noniid-optimizer
X2Static
X2Static embeddingspowergossip
Code for "Practical Low-Rank Communication Compression in Decentralized Deep Learning"kubernetes-setup
MLO group setup for kubernetes clusterrelaysgd
Code for the paper “RelaySum for Decentralized Deep Learning on Heterogeneous Data”topology-in-decentralized-learning
Code related to ’Beyond spectral gap: The role of the topology in decentralized learning‘.quasi-global-momentum
piecewise-affine-multiplication
rotational-optimizers
byzantine-robust-decentralized-optimizer
uncertainity-estimation
Code for the paper “The Peril of Popular Deep Learning Uncertainty Estimation Methods”getting-started
text_to_image_generation
easy-summary
difficulty-guided text summarizationFeAI
Federated Learning with TensorFlow.jsautoTrain
Open Challenge - Automatic Training for Deep Learningghost-noise
pax
JAX-like API for PyTorchpersonalized-collaborative-llms
phantomedicus
MedSurge: medical survey generatorLove Open Source and this site? Check out how you can help us