Ko Reranker 8k

🚀 upskyy/ko-reranker-8k

ko-reranker-8k是在BAAI/bge-reranker-v2-m3模型的基礎上，使用韓語數據進行微調得到的模型。

🚀 快速開始

📦 安裝指南

使用FlagEmbedding

pip install -U FlagEmbedding

💻 使用示例

基礎用法

使用FlagEmbedding獲取相關性分數（分數越高表示相關性越強）：

from FlagEmbedding import FlagReranker


reranker = FlagReranker('upskyy/ko-reranker-8k', use_fp16=True) # 將use_fp16設置為True可以在略微降低性能的情況下加快計算速度

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

# 你可以通過設置"normalize=True"將分數映射到0-1之間，這將對分數應用sigmoid函數
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]

# 你可以通過設置"normalize=True"將分數映射到0-1之間，這將對分數應用sigmoid函數
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獲取相關性分數（分數越高表示相關性越強）：

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)

📚 詳細文檔

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}
}

參考資料

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

📄 許可證

本項目採用Apache-2.0許可證。