Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking
Paper • 2405.07920 • Published • 3
How to use webis/monoelectra-base with Lightning IR:
#install from https://github.com/webis-de/lightning-ir
from lightning_ir import CrossEncoderModule
model = CrossEncoderModule("webis/monoelectra-base")
model.score("query", ["doc1", "doc2", "doc3"])This model was introduced in the paper Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking.
For code, examples and more, please visit https://github.com/webis-de/msmarco-llm-distillation.
Base model
google/electra-base-discriminator