Ko Reranker 8k

🚀 upskyy/ko-reranker-8k

ko-reranker-8k是在BAAI/bge-reranker-v2-m3模型的基础上，使用韩语数据进行微调得到的模型。

🚀 快速开始

📦 安装指南

使用FlagEmbedding

pip install -U FlagEmbedding

💻 使用示例

基础用法

使用FlagEmbedding获取相关性分数（分数越高表示相关性越强）：

from FlagEmbedding import FlagReranker


reranker = FlagReranker('upskyy/ko-reranker-8k', use_fp16=True) # 将use_fp16设置为True可以在略微降低性能的情况下加快计算速度

score = reranker.compute_score(['query', 'passage'])
print(score) # -8.3828125

# 你可以通过设置"normalize=True"将分数映射到0-1之间，这将对分数应用sigmoid函数
score = reranker.compute_score(['query', 'passage'], normalize=True)
print(score) # 0.000228713314721116

scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']])
print(scores) # [-11.2265625, 8.6875]

# 你可以通过设置"normalize=True"将分数映射到0-1之间，这将对分数应用sigmoid函数
scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']], normalize=True)
print(scores) # [1.3315579521758342e-05, 0.9998313472460109]

使用Huggingface transformers获取相关性分数（分数越高表示相关性越强）：

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer


tokenizer = AutoTokenizer.from_pretrained('upskyy/ko-reranker-8k')
model = AutoModelForSequenceClassification.from_pretrained('upskyy/ko-reranker-8k')
model.eval()

pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]
with torch.no_grad():
    inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
    scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
    print(scores)

📚 详细文档

引用

@misc{li2023making,
      title={Making Large Language Models A Better Foundation For Dense Retrieval}, 
      author={Chaofan Li and Zheng Liu and Shitao Xiao and Yingxia Shao},
      year={2023},
      eprint={2312.15503},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
@misc{chen2024bge,
      title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, 
      author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
      year={2024},
      eprint={2402.03216},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

参考资料

• Dongjin-kr/ko-reranker
• reranker-kr
• FlagEmbedding

📄 许可证

本项目采用Apache-2.0许可证。