README.md

---
tags:
- mteb
model-index:
- name: qinglong-large-zh
  results:
  - task:
      type: Reranking
    dataset:
      type: C-MTEB/CMedQAv1-reranking
      name: MTEB CMedQAv1
      config: default
      split: test
      revision: None
    metrics:
    - type: map
      value: 82.32176162633382
    - type: mrr
      value: 84.91440476190478
  - task:
      type: Reranking
    dataset:
      type: C-MTEB/CMedQAv2-reranking
      name: MTEB CMedQAv2
      config: default
      split: test
      revision: None
    metrics:
    - type: map
      value: 84.08586457179406
    - type: mrr
      value: 86.9011507936508
  - task:
      type: Reranking
    dataset:
      type: C-MTEB/Mmarco-reranking
      name: MTEB MMarcoReranking
      config: default
      split: dev
      revision: None
    metrics:
    - type: map
      value: 35.497382125464284
    - type: mrr
      value: 35.29206349206349
  - task:
      type: Reranking
    dataset:
      type: C-MTEB/T2Reranking
      name: MTEB T2Reranking
      config: default
      split: dev
      revision: None
    metrics:
    - type: map
      value: 68.25849742148222
    - type: mrr
      value: 78.64202157956387
---

# alime-reranker-large-zh

The alime reranker model.

# Usage
```python

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

pairs = [["西湖在哪？", "西湖风景名胜区位于浙江省杭州市"],["今天天气不错","你吓死我了"]]

if torch.cuda.is_available():
    device = torch.device("cuda")
else:
    device = torch.device("cpu")

tokenizer = AutoTokenizer.from_pretrained("Pristinenlp/alime-reranker-large-zh")
model = AutoModelForSequenceClassification.from_pretrained("Pristinenlp/alime-reranker-large-zh").to(device)

inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512).to(device)
scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
print(scores.tolist())

```