YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
SARA Cross-Encoder (sara_ce_cost-sensitive-opt/sara_ce_adrmse_relevance)
This model is a cross-encoder reranker trained on the SARA collection for Sensitivity-Aware Search (SAS).
Usage
from rankers import Cat
import pyterrier as pt
dataset = pt.get_dataset("irds:sara")
# Index the corpus
indexer = pt.IterDictIndexer('./indices/sara')
indexer.index(dataset.get_corpus_iter())
index_ref = pt.IndexRef.of('./indices/sara')
bm25 = pt.BatchRetrieve(index_ref, wmodel='BM25')
# Load the reranker
reranker = Cat.from_pretrained("cost-sensitive-opt/sara_ce_adrmse_relevance").to_pyterrier()
# Retrieval pipeline
pipeline = bm25 % 10 >> dataset.text_loader() >> reranker
pipeline.search("Your query goes here!")
| qid | docid | docno | score | query | text | rank |
|------:|--------:|:-------------------|---------:|:----------------------|:------------------------|-------:|
| 1 | 5496 | badly-star-bat | -5.61883 | Your query goes here! | <!DOCTYPE HTML PUBLI... | 0 |
| 1 | 126384 | wholly-proud-bison | -6.4882 | Your query goes here! | All - We have saved ... | 1 |
| 1 | 48895 | fully-pet-alpaca | -6.54544 | Your query goes here! | Anna, I just left yo... | 2 |
| 1 | 90929 | namely-clean-horse | -6.57092 | Your query goes here! | -----Original Messag... | 3 |
| 1 | 72466 | lately-joint-fawn | -6.91505 | Your query goes here! | David, Here's the in... | 4 |
| 1 | 114876 | safely-quick-gecko | -7.35775 | Your query goes here! | Casey, I ran curve q... | 5 |
| 1 | 108431 | poorly-trusty-dove | -7.42456 | Your query goes here! | I got the queries to... | 6 |
| 1 | 43652 | firmly-well-dassie | -7.48381 | Your query goes here! | My impression is tha... | 7 |
| 1 | 1998 | badly-big-pigeon | -7.52379 | Your query goes here! | Geoff, Attached is y... | 8 |
| 1 | 83963 | mainly-moving-ray | -7.81069 | Your query goes here! | -----Original Messag... | 9 |
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support