Best-trained LEAD model checkpoints. The number in the file name represents the epochs of model training, and dpr.biencoder.70 has the best performance. Please refer to our paper and github repo for more details.

Paper: Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs

Github repo: https://github.com/thunlp/LEAD

LEAD dataset: https://huggingface.co/datasets/JamesChengGao/LEAD

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.