README.md

---
license: mit
language:
- zh
- en

tags:
- mteb
model-index:
- name: bge-reranker-large-1k
  results:
  - task:
      type: Reranking
    dataset:
      type: C-MTEB/CMedQAv1-reranking
      name: MTEB CMedQAv1
      config: default
      split: test
      revision: None
    metrics:
    - type: map
      value: 81.26301528052902
    - type: mrr
      value: 84.13043650793651
  - task:
      type: Reranking
    dataset:
      type: C-MTEB/CMedQAv2-reranking
      name: MTEB CMedQAv2
      config: default
      split: test
      revision: None
    metrics:
    - type: map
      value: 84.10748270282731
    - type: mrr
      value: 86.79376984126984
  - task:
      type: Reranking
    dataset:
      type: C-MTEB/Mmarco-reranking
      name: MTEB MMarcoReranking
      config: default
      split: dev
      revision: None
    metrics:
    - type: map
      value: 35.46065069588283
    - type: mrr
      value: 34.602380952380946
  - task:
      type: Reranking
    dataset:
      type: C-MTEB/T2Reranking
      name: MTEB T2Reranking
      config: default
      split: dev
      revision: None
    metrics:
    - type: map
      value: 67.25376077716552
    - type: mrr
      value: 77.1615431322608
---

本模型是在 [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) 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。