gte-micro-v3

这是 gte-tiny 的精简版本。

预期用途

本模型专为语义自动补全功能设计（点击此处查看演示）。

使用方法（Sentence-Transformers）（与 gte-tiny 相同）

当您安装了 sentence-transformers 后，使用此模型会变得非常简单：

pip install -U sentence-transformers

然后您可以像这样使用该模型：

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('Mihaiii/gte-micro-v3')
embeddings = model.encode(sentences)
print(embeddings)

使用方法（HuggingFace Transformers）（与 gte-tiny 相同）

如果不使用 sentence-transformers，您可以这样使用该模型：首先，将输入传递给 transformer 模型，然后必须在语境化词嵌入之上应用正确的池化操作。

from openmind import AutoModel, AutoTokenizer , is_torch_npu_available
from openmind_hub import snapshot_download
import torch
import argparse

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="jeffding/gte-micro-v3-openmind",
    )
    args = parser.parse_args()
    return args

#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

def main():
    args = parse_args()
    model_path = args.model_name_or_path

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
        
    # Sentences we want sentence embeddings for
    sentences = ['This is an example sentence', 'Each sentence is converted']

    # Load model from HuggingFace Hub
    tokenizer = AutoTokenizer.from_pretrained(model_path)
    model = AutoModel.from_pretrained(model_path)

    # Tokenize sentences
    encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

    # Compute token embeddings
    with torch.no_grad():
        model_output = model(**encoded_input)

    # Perform pooling. In this case, mean pooling.
    sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

    print("Sentence embeddings:")
    print(sentence_embeddings)
    
if __name__ == "__main__":
    main()

局限性（与 gte-small 相同）

该模型仅适用于英文文本，并且任何长文本都将被截断为最多 512 个 token。