Instructions to use SparseCL/BGE-SparseCL-arguana with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SparseCL/BGE-SparseCL-arguana with Transformers:
# Load model directly from transformers import AutoTokenizer, our_BertForCL tokenizer = AutoTokenizer.from_pretrained("SparseCL/BGE-SparseCL-arguana") model = our_BertForCL.from_pretrained("SparseCL/BGE-SparseCL-arguana", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| license: mit | |
| # BGE-SparseCL-Arguana | |
| This repository contains the SparseCL model based on `BAAI/bge-base-en-v1.5` and trained on the Arguana dataset. | |
| SparseCL is designed for contradiction and counterargument retrieval. | |
| For implementation and usage details, please see the [SparseCL repository](https://github.com/xuhaike/SparseCL). | |
| ## Citation | |
| Please cite our paper if you use this model: | |
| ```bibtex | |
| @inproceedings{xu2025contradiction, | |
| title={Contradiction Retrieval via Contrastive Learning with Sparsity}, | |
| author={Xu, Haike and Lin, Zongyu and Chang, Kai-Wei and Sun, Yizhou and Indyk, Piotr}, | |
| booktitle={International Conference on Machine Learning}, | |
| year={2025} | |
| } | |
| ``` | |
| ## License | |
| MIT License. |