这是 ANCE FirstP Model 到 sentence-transformers 模型的移植：它能将句子和段落映射到 768 维的稠密向量空间，可用于聚类或语义搜索等任务。
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然后你可以这样使用该模型：
from openmind import AutoTokenizer, AutoModel, is_torch_npu_available
from openmind_hub import snapshot_download
import torch.nn.functional as F
import torch
import argparse
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument(
"--model_name_or_path",
type=str,
help="Path to model",
default="zhouhui/msmarco-roberta-base-ance-firstp",
)
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 = ['This is an example sentence', 'Each sentence is converted']
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()如需对该模型进行自动化评估，请参见“句子嵌入基准测试”：https://seb.sbert.net
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity'})
(3): LayerNorm(
(norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
)
)请查看：ANCE Model