RuntimeError: Input, output and indices must be on the current device. (fill_mask("Random text <mask>.")

Question

我收到“运行时错误：输入、输出和索引必须在当前设备上。” 当我运行这一行。 fill_mask("汽车.")

我运行在 Colab 上使用它。我的代码：

from transformers import BertTokenizer, BertForMaskedLM
from pathlib import Path
from tokenizers import ByteLevelBPETokenizer
from transformers import BertTokenizer, BertForMaskedLM


paths = [str(x) for x in Path(".").glob("**/*.txt")]
print(paths)

bert_tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

from transformers import BertModel, BertConfig

configuration = BertConfig()
model = BertModel(configuration)
configuration = model.config
print(configuration)

model = BertForMaskedLM.from_pretrained("bert-base-uncased")

from transformers import LineByLineTextDataset
dataset = LineByLineTextDataset(
    tokenizer=bert_tokenizer,
    file_path="./kant.txt",
    block_size=128,
)

from transformers import DataCollatorForLanguageModeling
data_collator = DataCollatorForLanguageModeling(
    tokenizer=bert_tokenizer, mlm=True, mlm_probability=0.15
)

from transformers import Trainer, TrainingArguments

training_args = TrainingArguments(
    output_dir="./KantaiBERT",
    overwrite_output_dir=True,
    num_train_epochs=1,
    per_device_train_batch_size=64,
    save_steps=10_000,
    save_total_limit=2,
    )

trainer = Trainer(
    model=model,
    args=training_args,
    data_collator=data_collator,
    train_dataset=dataset,
)

trainer.train()

from transformers import pipeline

fill_mask = pipeline(
    "fill-mask",
    model=model,
    tokenizer=bert_tokenizer
)

fill_mask("Auto Car <mask>.")

最后一行给我上面提到的错误。请让我知道我做错了什么或我必须做什么才能消除此错误。

Answer 1

训练器在 GPU (default value no_cuda=False) 上自动训练您的模型。您可以通过运行ning:

验证这一点

model.device

训练后。管道不会这样做，这会导致您看到错误（即您的模型在您的 GPU 上，但您的例句在您的 CPU 上）。您也可以通过运行支持 GPU 的管道来解决此问题：

fill_mask = pipeline(
    "fill-mask",
    model=model,
    tokenizer=bert_tokenizer,
    device=0,
)

或者在初始化管道之前将您的模型转移到 CPU：

model.to('cpu')

RuntimeError: Input, output and indices must be on the current device. (fill_mask("Random text <mask>.")

RuntimeError: Input, output and indices must be on the current device. (fill_mask("Random text <mask>.")

python

nlp

pytorch

bert-language-model

huggingface-transformers