本模型是在 BAAI/bge-reranker-large 上对模型的 model.base_model.embeddings.position_embeddings.weight 依赖经验值进行修改，来扩大模型输入长度，并没有进行任何继续supervised fined tuning，作为新手示例。
同时亦附上在C-MTEB的分数作为对比。
感谢原作者的工作。
- Downloads last month
- 288
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Space using neofung/bge-reranker-large-1k 1
Evaluation results
- map on MTEB CMedQAv1test set self-reported82.150
- mrr on MTEB CMedQAv1test set self-reported84.923
- map on MTEB CMedQAv2test set self-reported84.187
- mrr on MTEB CMedQAv2test set self-reported86.969
- map on MTEB MMarcoRerankingself-reported37.642
- mrr on MTEB MMarcoRerankingself-reported36.577
- map on MTEB T2Rerankingself-reported67.479
- mrr on MTEB T2Rerankingself-reported77.610