Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
Paper • 2007.00808 • Published
How to use castorini/ance-dpr-context-multi with Transformers:
# Load model directly
from transformers import AutoTokenizer, DPRContextEncoder
tokenizer = AutoTokenizer.from_pretrained("castorini/ance-dpr-context-multi")
model = DPRContextEncoder.from_pretrained("castorini/ance-dpr-context-multi")YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This model is converted from the original ANCE repo and fitted into Pyserini:
Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, Arnold Overwijk. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
For more details on how to use it, check our experiments in Pyserini
# Load model directly from transformers import AutoTokenizer, DPRContextEncoder tokenizer = AutoTokenizer.from_pretrained("castorini/ance-dpr-context-multi") model = DPRContextEncoder.from_pretrained("castorini/ance-dpr-context-multi")