gte-multilingual-reranker-base

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

model_name_or_path = "Alibaba-NLP/gte-multilingual-reranker-base"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForSequenceClassification.from_pretrained(
    model_name_or_path, trust_remote_code=True,
    torch_dtype=torch.float16
)
model.eval()

pairs = [["中国的首都在哪儿","北京"], ["what is the capital of China?", "北京"], ["how to implement quick sort in python?","Introduction of quick sort"]]
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)

# tensor([1.2315, 0.5923, 0.3041])

docker run --gpus all -v $PWD/data:/app/.cache -p "7997":"7997" \
michaelf34/infinity:0.0.68 \
v2 --model-id Alibaba-NLP/gte-multilingual-reranker-base --revision "main" --dtype bfloat16 --batch-size 32 --device cuda --engine torch --port 7997

docker run --platform linux/amd64 \
  -p 8080:80 \
  -v $PWD/data:/data \
  --pull always \
  ghcr.io/huggingface/text-embeddings-inference:cpu-1.7 \
  --model-id Alibaba-NLP/gte-multilingual-reranker-base

docker run --gpus all \
  -p 8080:80 \
  -v $PWD/data:/data \
  --pull always \
  ghcr.io/huggingface/text-embeddings-inference:1.7 \
  --model-id Alibaba-NLP/gte-multilingual-reranker-base

curl https://0.0.0.0:8080/rerank \
  -H "Content-Type: application/json" \
  -d '{
    "query": "中国的首都在哪儿",
    "raw_scores": false,
    "return_text": false,
    "texts": [ "北京" ],
    "truncate": true,
    "truncation_direction": "right"
  }'

@inproceedings{zhang2024mgte,
  title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
  author={Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and others},
  booktitle={Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track},
  pages={1393--1412},
  year={2024}
}