gpustack / gte-multilingual-reranker-base-GGUF

gte-multilingual-reranker-base-GGUF

!!! Experimental supported by gpustack/llama-box v0.0.72+ only !!!

Model creator : Alibaba-NLP
Original model : gte-multilingual-reranker-base
GGUF quantization : based on llama.cpp f4d2b that patched by llama-box

gte-multilingual-reranker-base

The gte-multilingual-reranker-base model is the first reranker model in the GTE family of models, featuring several key attributes:

• High Performance : Achieves state-of-the-art (SOTA) results in multilingual retrieval tasks and multi-task representation model evaluations when compared to reranker models of similar size.
• Training Architecture : Trained using an encoder-only transformers architecture, resulting in a smaller model size. Unlike previous models based on decode-only LLM architecture (e.g., gte-qwen2-1.5b-instruct), this model has lower hardware requirements for inference, offering a 10x increase in inference speed.
• Long Context : Supports text lengths up to 8192 tokens.
• Multilingual Capability : Supports over 70 languages.

Model Information

• Model Size: 306M
• Max Input Tokens: 8192

Usage

• It is recommended to install xformers and enable unpadding for acceleration, refer to enable-unpadding-and-xformers .
• How to use it offline: new-impl/discussions/2

Using Huggingface transformers (transformers>=4.36.0)

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])

Evaluation

Results of reranking based on multiple text retreival datasets

More detailed experimental results can be found in the paper .

Cloud API Services

In addition to the open-source GTE series models, GTE series models are also available as commercial API services on Alibaba Cloud.

• Embedding Models : Rhree versions of the text embedding models are available: text-embedding-v1/v2/v3, with v3 being the latest API service.
• ReRank Models : The gte-rerank model service is available.

Note that the models behind the commercial APIs are not entirely identical to the open-source models.

Citation

If you find our paper or models helpful, please consider cite:

@misc{zhang2024mgtegeneralizedlongcontexttext,
      title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval}, 
      author={Xin Zhang and Yanzhao Zhang and Dingkun Long and Wen Xie and Ziqi Dai and Jialong Tang and Huan Lin and Baosong Yang and Pengjun Xie and Fei Huang and Meishan Zhang and Wenjie Li and Min Zhang},
      year={2024},
      eprint={2407.19669},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2407.19669}, 
}