upskyy/ko-reranker-8k
ko-reranker-8k는 BAAI/bge-reranker-v2-m3 모델에 한국어 데이터를 finetuning 한 model 입니다.
Usage
Using FlagEmbedding
pip install -U FlagEmbedding
Get relevance scores (higher scores indicate more relevance):
from FlagEmbedding import FlagReranker
reranker = FlagReranker('upskyy/ko-reranker-8k', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
score = reranker.compute_score(['query', 'passage'])
print(score) # -8.3828125
# You can map the scores into 0-1 by set "normalize=True", which will apply sigmoid function to the score
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]
# You can map the scores into 0-1 by set "normalize=True", which will apply sigmoid function to the score
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]
Using Huggingface transformers
Get relevance scores (higher scores indicate more relevance):
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)
Citation
@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}
}