MobileBERT

This model was released on 2020-04-06 and added to Hugging Face Transformers on 2020-11-16.

MobileBERT

MobileBERT is a lightweight and efficient variant of BERT, specifically designed for resource-limited devices such as mobile phones. It retains BERT’s architecture but significantly reduces model size and inference latency while maintaining strong performance on NLP tasks. MobileBERT achieves this through a bottleneck structure and carefully balanced self-attention and feedforward networks. The model is trained by knowledge transfer from a large BERT model with an inverted bottleneck structure.

You can find the original MobileBERT checkpoint under the Google organization.

Tip

Click on the MobileBERT models in the right sidebar for more examples of how to apply MobileBERT to different language tasks.

The example below demonstrates how to predict the [MASK] token with Pipeline, AutoModel, and from the command line.

import torch
from transformers import pipeline

pipeline = pipeline(
    task="fill-mask",
    model="google/mobilebert-uncased",
    dtype=torch.float16,
    device=0
)
pipeline("The capital of France is [MASK].")

import torch
from transformers import AutoModelForMaskedLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "google/mobilebert-uncased",
)
model = AutoModelForMaskedLM.from_pretrained(
    "google/mobilebert-uncased",
    dtype=torch.float16,
    device_map="auto",
)
inputs = tokenizer("The capital of France is [MASK].", return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs)
    predictions = outputs.logits

masked_index = torch.where(inputs['input_ids'] == tokenizer.mask_token_id)[1]
predicted_token_id = predictions[0, masked_index].argmax(dim=-1)
predicted_token = tokenizer.decode(predicted_token_id)

print(f"The predicted token is: {predicted_token}")

echo -e "The capital of France is [MASK]." | transformers run --task fill-mask --model google/mobilebert-uncased --device 0

Notes

• Inputs should be padded on the right because BERT uses absolute position embeddings.

MobileBertConfig

[[autodoc]] MobileBertConfig

MobileBertTokenizer

[[autodoc]] MobileBertTokenizer

MobileBertTokenizerFast

[[autodoc]] MobileBertTokenizerFast

MobileBert specific outputs

[[autodoc]] models.mobilebert.modeling_mobilebert.MobileBertForPreTrainingOutput

MobileBertModel

[[autodoc]] MobileBertModel - forward

MobileBertForPreTraining

[[autodoc]] MobileBertForPreTraining - forward

MobileBertForMaskedLM

[[autodoc]] MobileBertForMaskedLM - forward

MobileBertForNextSentencePrediction

[[autodoc]] MobileBertForNextSentencePrediction - forward

MobileBertForSequenceClassification

[[autodoc]] MobileBertForSequenceClassification - forward

MobileBertForMultipleChoice

[[autodoc]] MobileBertForMultipleChoice - forward

MobileBertForTokenClassification

[[autodoc]] MobileBertForTokenClassification - forward

MobileBertForQuestionAnswering

[[autodoc]] MobileBertForQuestionAnswering - forward