如何从Huggingface中的FeatureExtractionPipeline访问返回的注意力掩码?
下面的代码采用嵌入模型,将其和 Huggingface 数据集分布在单个节点上的 8 个 GPU 上,并对输入执行推理。该代码需要用于均值池的注意掩码。
代码示例:
from accelerate import Accelerator
from accelerate.utils import tqdm
from transformers import AutoTokenizer, AutoModel
from optimum.bettertransformer import BetterTransformer
import torch
from datasets import load_dataset
from transformers import pipeline
accelerator = Accelerator()
model_name = "BAAI/bge-large-en-v1.5"
tokenizer = AutoTokenizer.from_pretrained(model_name,)
model = AutoModel.from_pretrained(model_name,)
pipe = pipeline(
"feature-extraction",
model=model,
tokenizer=tokenizer,
max_length=512,
truncation=True,
padding=True,
pad_to_max_length=True,
batch_size=256,
framework="pt",
return_tensors=True,
return_attention_mask=True,
device=(accelerator.device)
)
dataset = load_dataset(
"wikitext",
"wikitext-2-v1",
split="train",
)
#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)
# Assume 8 processes
with accelerator.split_between_processes(dataset["text"]) as data:
for out in pipe(data):
sentence_embeddings = mean_pooling(out, out["attention_mask"])
我需要管道中的注意力来用于均值池。
最好的,
恩里科
pipeline
库中的
transformers
对象为模型的快速推理提供了方便的抽象,但对于更多定制的解决方案,直接使用模型通常是一个好主意。例如:
text = 'This is a test.'
tokenized = tokenizer(
text,
max_length=512,
truncation=True,
padding=True,
return_attention_mask=True,
return_tensors='pt').to(accelerator.device)
out = model(**tokenized)
embeddings = out.last_hidden_state
attention_mask = tokenized['attention_mask']
然后您可以使用 embeddings
和
attention_mask
来计算均值池。您也可以考虑使用
out.pooler_output
而不是手动计算均值池,但是,我不确定在这种情况下如何计算
pooler_output
,所以要小心。