Scholarbert

🚀 ScholarBERT_100 Model

ScholarBERT_100 is a variant of the ScholarBERT model family, pre - trained on a large scientific research corpus, offering case - sensitive text processing capabilities.

🚀 Quick Start

This is the ScholarBERT_100 variant of the ScholarBERT model family. It is pretrained on a large collection of scientific research articles (221B tokens). This is a cased (case - sensitive) model, and the tokenizer will not convert all inputs to lower - case by default. The model is based on the same architecture as [BERT - large](https://huggingface.co/bert - large - cased) and has a total of 340M parameters.

✨ Features

• Large - scale Pretraining: Trained on a vast collection of 221B tokens from scientific research articles.
• Case - sensitive: The cased model preserves the case information of the input text.
• Similar Architecture: Based on the architecture of [BERT - large](https://huggingface.co/bert - large - cased).

📚 Documentation

🔧 Model Architecture

📦 Training Dataset

The vocab and the model are pretrained on 100% of the PRD scientific literature dataset. The PRD dataset is provided by Public.Resource.Org, Inc. (“Public Resource”), a nonprofit organization based in California. This dataset was constructed from a corpus of journal article files, from which we successfully extracted text from 75,496,055 articles from 178,928 journals. The articles span across Arts & Humanities, Life Sciences & Biomedicine, Physical Sciences, Social Sciences, and Technology. The distribution of articles is shown below.

📄 License

This model is licensed under the Apache - 2.0 license.

📖 BibTeX entry and citation info

If using this model, please cite this paper:

@misc{hong2023diminishing,
      title={The Diminishing Returns of Masked Language Models to Science}, 
      author={Zhi Hong and Aswathy Ajith and Gregory Pauloski and Eamon Duede and Kyle Chard and Ian Foster},
      year={2023},
      eprint={2205.11342},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}