ACL22 paper: Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost

BERT score for text generation

UmBERTo: an Italian Language Model trained with Whole Word Masking.

Deep learning models Serving with Python

Repository to experiment with the possibility of generating text with BERT models

Repository to develop great prompt engineering techniques for BERT models

Suite of tools for deploying and training deep learning models using the JVM. Highlights include model import for keras, tensorflow, and onnx/pytorch, a modular and tiny c++ library for running mat…

The repository for the code of the UltraFastBERT paper

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.