Bert

tokenizersRust

Fast, state-of-the-art tokenizers for training and tokenization, optimized for both research and production.

rust-bertRust

A Rust-native port of Hugging Face Transformers providing ready-to-use NLP pipelines and transformer models like BERT, GPT2, and T5.

TexarPython

A modular toolkit for machine learning, natural language processing, and text generation with TensorFlow and PyTorch versions.

SciBERTPython

A BERT language model pre-trained on a large corpus of scientific papers for natural language processing tasks in scientific domains.

n2oErlang

Embeddable message protocol loop library for WebSocket, HTTP, MQTT, and TCP servers with unified API.

Awesome Vision + Language

A curated list of recent research papers and resources on Vision and Language Pre-trained Models (VL-PTMs).

BLEURT: a Transfer Learning-Based Metric for Natural Language GenerationPython

A transfer learning-based evaluation metric for Natural Language Generation that scores text fluency and meaning.

Question Answering

A curated list of resources for Question Answering (QA), covering machine learning, deep learning, datasets, and research.

BioBERT

Pre-trained biomedical language representation model for biomedical text mining tasks like named entity recognition and relation extraction.

BlueBERTPython

A BERT model pre-trained on PubMed abstracts and clinical notes for biomedical natural language processing tasks.

ChemBERTa-2Jupyter Notebook

A collection of BERT-like transformer models pre-trained on chemical SMILES data for drug design and property prediction.

Huang et al ClinicalBERTJupyter Notebook

A BERT-based language model pretrained on clinical notes for predicting hospital readmissions and analyzing medical text.

CybertronGo

A pure Go package for running inference with pre-trained Transformer models from Hugging Face, enabling NLP tasks without external languages.

BackpropPython

A Python library that simplifies using, finetuning, and deploying state-of-the-art machine learning models for various AI tasks.

Norwegian NLP resources

A curated collection of open-source libraries, models, datasets, and tools for Natural Language Processing (NLP) in Norwegian.

dbmdz BERT models

A collection of pre-trained BERT, DistilBERT, ELECTRA, GPT-2, and ConvBERT models for multiple languages, including German, Italian, Turkish, and historic texts.