MarkusSagen/Master-Thesis-Multilingual-Longformer

Stars
27
Rank 905,827 (Top 18 %)
Language
Jupyter Notebook
License
MIT License
Created almost 4 years ago
Updated over 3 years ago

MarkusSagen/Master-Thesis-Multilingual-Longformer

MarkusSagen

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Master thesis with code investigating methods for incorporating long-context reasoning in low-resource languages, without the need to pre-train from scratch. We investigated if multilingual models could inherit these properties by making it an Efficient Transformer (s.a. the Longformer architecture).

Surmize

Web application for summarizing and asking questions on your own documents. Summarization and QA application in FastAPI, React and Transformers

doom-emacs-for-writers

Doom Emacs config for non-programmers. Just make smart notes with Org and Org-Roam

Pytorch_Examples

xlm-roberta-longformer-base-4096

CV

Information and collection about repos, reports and more used for CVs and Personal letters

SML_Project

Classifier of songs to predict good songs

Jupyter Notebook

rejx

Deal with `.rej` files with reasonable pain

Assignment2_Issue

mk3-spotify-backend

Backend server for testing the Spotify API with react

homepage

docker-training

Train using Docker and Kubernetes

Assignment_2

Assignment 2 for the course IOOPM HT 2018

School

First scool project in webprogramming - Burger shop

hoot-ot

Smart notifier for all your shopping or curiosity needs

Assignment_1

Inlämningsuppgift 1 IOOPM

MarkusSagen.github.io

sveltekit-tailwind-typescript-jit-template

Time_series_project

Jupyter Notebook

ai_nlp_transformer_models_benchmarking

Investigates what impacts the GPU allocation, inference and training time for different Transformer based models

Jupyter Notebook

Transformers-LM-Benchmark

Benchmark training and inference time for Transformer models on Huggingface

pytorch_lightning_al_comparisons

Active Learning in Pytroch

huggingface-models-overview

Recommendation on the available deep learning models - and where to find them. Use what for where?

mk3-spotify

Spotify API tester with react

keras_classifier

Arduino_Keyboard_Multiple_inputs

sms-explainable-antibiotics-VGR

Explainable Antibiotic Perscription for the Svensk Medicinskt Språkdatalabb Vinnova project (also known as MedBERT). A cooperation between Region Västra Götaland Folktandvården and Peltarion

Jupyter Notebook

stockpredictor-streamlit

Simple demo for predicting sample stock prices with streamlit and prothet

mltoolskit

Toolkit for ML or DS projects to reduce the number of repetitions made between projects

ACC-grp6

sms-fall-injury-prediction-RH

Fall injury prediction and identification from free text journal entries for the Svensk Medicinskt Språkdatalabb Vinnova project (also known as MedBERT). A cooperation between Region Halland, Peltarion, and RISE

Jupyter Notebook