Safetensors
English
qwen2

Rank-K: Test-Time Reasoning for Listwise Reranking

Repo: https://github.com/hltcoe/rank-k

Paper: https://arxiv.org/abs/2505.14432

Script for running Rank-K is provided in the repo! If you have any questions, please raise an issue in our GitHub Repository

Reference

Please cite the following paper if you use the model.

@article{rank-k,
    title={Rank-K: Test-Time Reasoning for Listwise Reranking},
    author={Yang, Eugene and Yates, Andrew and Ricci, Kathryn and Weller, Orion and Chari, Vivek and Van Durme, Benjamin and Lawrie, Dawn},
    journal={arXiv preprint arXiv:2505.14432},
    year={2025}
}
Downloads last month
642
Safetensors
Model size
32.8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for hltcoe/Rank-K-32B

Base model

Qwen/Qwen2.5-32B
Finetuned
Qwen/QwQ-32B
Finetuned
(72)
this model
Quantizations
1 model

Dataset used to train hltcoe/Rank-K-32B