maximzubkov

fft-scan

Efficient PScan implementation in PyTorch

cnn-distillation

Pytorch-lightning framework for knowledge distillation experiments with CNN

lin-transformer-kd

Distillation of knowledge into a Linear Transformer

LinBERT

maximzubkov

opt-project

Project on the stability of GANs training

astminer

A library for mining of path-based representations of code (and more)

barrel-rec-pytorch

BLINK

Entity Linker solution

code-transformer

Implementation of the paper "Language-agnostic representation learning of source code from structure and context".

CodeGen

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.

codeprep

A toolkit for pre-processing large source code corpora

CV

CV in Russian and English languages

deeptype

Code for the paper "DeepType: Multilingual Entity Linking by Neural Type System Evolution"

Diffusion-LM

Diffusion-LM

epfl-nlp.github.io

EPFL's NLP lab website

lightning-bolts

Toolbox of models, callbacks, and datasets for AI/ML researchers.

long-range-arena

Long Range Arena for Benchmarking Efficient Transformers

minimal-text-diffusion

A minimal implementation of diffusion models for text generation

ML_course

EPFL Machine Learning Course, Fall 2021

pix2struct

Pix2Struct wrapped into Docker, configured for GPU training and enhanced with Flesh Attention

positional-bias

Python_Project

Python Project

qagnn

[NAACL 2021] QA-GNN: Question Answering using Language Models and Knowledge Graphs

sasha

spe

Relative Positional Encoding for Transformers with Linear Complexity

Transformer-XH

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

wikidump

Framework for the extraction of features from Wikipedia XML dumps.

YouTokenToMe

Unsupervised text tokenizer focused on computational efficiency