Our reranker achieves results close to BAAI/bge-reranker-v2.5-gemma2-lightweight on the PIRB benchmark, even outperforming it on some datasets. At the same time, it is over 21 times smaller — 435M vs. 9.24B parameters.

Usage (Huggingface Transformers)

The model can be used with Huggingface Transformers in the following way:

python

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import numpy as np

query = "Jak dożyć 100 lat?"
answers = [
    "Trzeba zdrowo się odżywiać i uprawiać sport.",
    "Trzeba pić alkohol, imprezować i jeździć szybkimi autami.",
    "Gdy trwała kampania politycy zapewniali, że rozprawią się z zakazem niedzielnego handlu."
]

model_name = "sdadas/polish-reranker-roberta-v2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(
    model_name,
    dtype=torch.bfloat16,
    device_map="cuda"
)
texts = [f"{query}</s></s>{answer}" for answer in answers]
tokens = tokenizer(texts, padding="longest", max_length=512, truncation=True, return_tensors="pt").to("cuda")
output = model(**tokens)
results = output.logits.detach().cpu().float().numpy()
results = np.squeeze(results)
print(results.tolist())

Evaluation Results

The model achieves NDCG@10 of 65.30 in the Rerankers category of the Polish Information Retrieval Benchmark. See PIRB Leaderboard for detailed results.

Citation

bibtex

@article{dadas2024assessing,
  title={Assessing generalization capability of text ranking models in Polish}, 
  author={Sławomir Dadas and Małgorzata Grębowiec},
  year={2024},
  eprint={2402.14318},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}