Curious & Problem Solver
Master-Thesis-Multilingual-Longformer. 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).
35Surmize. Web application for summarizing and asking questions on your own documents. Summarization and QA application in FastAPI, React and Transformers
8rejx. Deal with `.rej` files with reasonable pain
6xlm-roberta-longformer-base-4096.
3Pytorch_Examples.
2doom-emacs-for-writers. Doom Emacs config for non-programmers. Just make smart notes with Org and Org-Roam
2SML_Project. Classifier of songs to predict good songs
2cosFormer. Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention
1datacards. Append missing model cards to datasets
1docs. A collaborative note taking, wiki and documentation platform that scales. Built with Django and React. Opensource alternative to Notion or Outline.
1sidekick. Sidekick code for the platform
1lm-evaluation-harness. A framework for few-shot evaluation of autoregressive language models.
1calibration. Code and datasets for the EMNLP 2020 paper "Calibration of Pre-trained Transformers"
1comcrawl. A python utility for downloading Common Crawl data
1mmf. A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
1Awesome-Multimodal-Research. A curated list of Multimodal Related Research.
1docarray. The data structure for unstructured data
1NN_calibration. Calibration of Convolutional Neural Networks
1TextGAIL. Python
1TranslateAlignRetrieve. Python-based implementation of the Translate-Align-Retrieve method to automatically translate the SQuAD Dataset to Spanish.
1CV. Information and collection about repos, reports and more used for CVs and Personal letters
1example_cml. Python
1budibase. Budibase is an open-source low-code platform for creating internal apps in minutes. Supports PostgreSQL, MySQL, MSSQL, MongoDB, Rest API, Docker, K8s 🚀
1sucx3_ner. Python
1pytorch-adapt. Domain adaptation made easy. Fully featured, modular, and customizable. Written in PyTorch.
1papers-search. Neural search engine for AI papers
1examples. Jina examples and demos to help you get started
1MAT. The official implementation of the Molecule Attention Transformer.
1Tatoeba-Challenge. Makefile
1tensorflow-tabnet. Improved TabNet for TensorFlow
1ScandEval. Evaluation of language models on mono- or multilingual Scandinavian language tasks.
1community-code. Shared code for data transforms, calling your model or just having fun with deep learning
1sms-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
1NERDA. Framework for fine-tuning pretrained transformers for Named-Entity Recognition (NER) tasks
1jiant. jiant is an nlp toolkit
1automated-string-cleaning. Repository for my master thesis on automated string handling
1protein_search. The neural search engine for proteins.
1T5-QA. Python
1pygaggle. a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini
1quality.
1MLOps-Basics. Jupyter Notebook
1GAN-for-tabular-data. We well know GANs for success in the realistic image generation. However, they can be applied in tabular data generation. We will review and examine some recent papers about tabular GANs in action.
1sms-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
1HM-Fashion-image-neural-search. H&M Fashion Image similarity search with Weaviate and DocArray
1chemicalx. A PyTorch and TorchDrug based deep learning library for drug pair scoring.
1ai_nlp_transformer_models_benchmarking. Investigates what impacts the GPU allocation, inference and training time for different Transformer based models
1keras-io-transformers. Jupyter Notebook
1pyserini. Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
1RATransformers. 🐭RATransformers - Make your transformer (like BERT, RoBERTa, GPT-2 and T5) Relation Aware!
1stockpredictor-streamlit. Simple demo for predicting sample stock prices with streamlit and prothet
1mltoolskit. Toolkit for ML or DS projects to reduce the number of repetitions made between projects
1hoot-ot. Smart notifier for all your shopping or curiosity needs
1sveltekit-tailwind-typescript-jit-template. CSS
1huggingface-models-overview. Recommendation on the available deep learning models - and where to find them. Use what for where?
1Transformers-LM-Benchmark. Benchmark training and inference time for Transformer models on Huggingface
1keras_classifier. JavaScript
1homepage. CSS
1MarkusSagen.github.io. CSS
1