ctu-aic/CE-fernet-c5-MRank256

This is fav-kky/FERNET-C5, fine-tuned with the Cross-Encoder architecture on DaReCzech dataset. The Cross-Encoder architecture processes both input text pieces simultaneously, enabling better accuracy.

The model can be used both for re-ranking.

Re-ranking task: Given a query, the model assesses all potential passages and ranks them in descending order of relevance.

from sentence_transformers import CrossEncoder

model = CrossEncoder('ctu-aic/CE-fernet-c5-MRank256', max_length=256)

query = "example query"

documents = [
    "Example document one.",
    "Example document two.",
    "Example document three."
]

top_k = 3
return_documents = True

results = model.rank(
    query=query,
    documents=documents,
    top_k=top_k,
    return_documents=return_documents
)

for i, res in enumerate(results):
    print(f"{i+1}. {res['text']}")