epfml Goto Github PK

attention-cnn

Source code for "On the Relationship between Self-Attention and Convolutional Layers"

autotrain

Open Challenge - Automatic Training for Deep Learning

bi-sent2vec

Robust Cross-lingual Embeddings from Parallel Sentences

byzantine-robust-decentralized-optimizer

byzantine-robust-noniid-optimizer

byzantine-robust-optimizer

Learning from history for Byzantine Robustness

chocosgd

Decentralized SGD and Consensus with Communication Compression: https://arxiv.org/abs/1907.09356

cifar

MLO internal cifar 10 / 100 default implementation / reference implementation. single machine, variable batch sizes, allowing maybe gradient compression. need to have clear documentation to make it easy to use, and so that we don't loose time with looking for hyperparameters. we can later keep it in sync with mlbench too, but self-contained is even better

cola

CoLa - Decentralized Linear Learning: https://arxiv.org/abs/1808.04883

collaborative-attention

Code for Multi-Head Attention: Collaborate Instead of Concatenate

continuityplan

Continuity Plan in accordance with https://www.epfl.ch/campus/security-safety/en/health/coronavirus-covid19/

correlating-tweets

Correlating Twitter Language with Community-Level Health Outcomes: https://arxiv.org/abs/1906.06465

denseformer

disco

Decentralized & federated privacy-preserving ML training, using p2p networking, in JS

doge

Codebase for ICML submission "DOGE: Domain Reweighting with Generalization Estimation"

dynamic-sparse-flash-attention

easy-summary

difficulty-guided text summarization

epfml-utils

Tools for experimentation and using run:ai. The aim is for these to be small self-contained utilities that are used by multiple people.

error-feedback-sgd

SGD with compressed gradients and error-feedback: https://arxiv.org/abs/1901.09847

feai

Federated Learning with TensorFlow.js

federated-learning-public-code

getting-started

getting-started-lauzhack

ghost-noise

gradientalignment

interpret-lm-knowledge

Extracting knowledge graphs from language models as a diagnostic benchmark of model performance (NeurIPS XAI 2021).

kubernetes-setup

MLO group setup for kubernetes cluster

landmark-attention

Landmark Attention: Random-Access Infinite Context Length for Transformers

llm-baselines

localsgd-code