MIM Solutions

bert_for_longer_texts

BERT classification model for processing texts longer than 512 tokens. Text is first divided into smaller chunks and after feeding them to BERT, intermediate results are pooled. The implementation allows fine-tuning.

deep-learning-template

robbytorch

Cool package for robust AI

MIM-OCR

mim_nlp

A Python package with ready-to-use models for various NLP tasks and text preprocessing utilities. The implementation allows fine-tuning.

java-ffm-predictor

Simple FFM predictor in Java

repository-template

A Cookiecutter repository template for an open-source project.

yolor

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)

donut

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

embedding-sum

google-research

Google Research

rouge_score

shap

A game theoretic approach to explain the output of any machine learning model.