Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
Paper • 2009.12756 • Published
Quick Links
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Multihop-Dense Retrieval (MDR)
Paper: Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval (Xiong, Wenhan, et al.)
Code and checkpoint from https://github.com/facebookresearch/multihop_dense_retrieval/
This is the checkpoint q_model from https://dl.fbaipublicfiles.com/mdpr/models/q_encoder.pt
License: https://github.com/facebookresearch/multihop_dense_retrieval/blob/main/LICENSE
- Downloads last month
- 3,053
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Load model directly from transformers import AutoTokenizer, MDREncoder tokenizer = AutoTokenizer.from_pretrained("deutschmann/mdr_roberta_q_encoder") model = MDREncoder.from_pretrained("deutschmann/mdr_roberta_q_encoder")