CambridgeMolecularEngineering/MechBERT-uncased-squad2

Model Name

Description

This model is fine-tuned on the SQuAD v2 dataset for question answering tasks. It is based on the pre-trained MechBERT-uncased model, developed by Cambridge Molecular Engineering designed for superior performance on downstream domain-specific NLP tasks.

See the associated paper for more details.

Citation:

If you use this model, please cite:

@article{mechbert-kumar2025,
  title={MechBERT: Language Models for Extracting Chemical and Property Relationships about Mechanical Stress and Strain},
  author={Pankaj Kumar, Saurabh Kabra, Jacqueline M. Cole},
  journal={Journal of Chemical Information and Modelling},
  doi={10.1021/acs.jcim.4c00857},
  year={2025}
}