Instructions to use DataHammer/scidpr-question-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DataHammer/scidpr-question-encoder with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("DataHammer/scidpr-question-encoder") model = AutoModel.from_pretrained("DataHammer/scidpr-question-encoder") - Notebooks
- Google Colab
- Kaggle
metadata
datasets:
- allenai/qasper
language:
- en
library_name: transformers
pipeline_tag: sentence-similarity
license: apache-2.0
SciDPR Question Encoder
Model Details
Model Description
Dense Passage Retrieval (DPR) is a set of tools and models for state-of-the-art open-domain Q&A research. scidpr-question-encoder is the Question Encoder trained using the Scientific Question Answer (QA) dataset (Pradeep et al., 2021).
- Developed by: See GitHub repo for model developers
- Model type: BERT-based encoder
- Language(s) (NLP): Apache 2.0
- License: English
Model Sources [optional]
- Repository: Github Repo
- Paper [optional]: Paper Repo