Back to all models

Unable to determine this model’s pipeline type. Check the docs .

Monthly model downloads

squeezebert/squeezebert-uncased squeezebert/squeezebert-uncased
last 30 days



Contributed by

squeezebert university
1 team member · 3 models

How to use this model directly from the 🤗/transformers library:

Copy to clipboard
from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("squeezebert/squeezebert-uncased") model = AutoModel.from_pretrained("squeezebert/squeezebert-uncased")

language: en license: bsd datasets:

  • bookcorpus
  • wikipedia

SqueezeBERT pretrained model

This model, squeezebert-uncased, is a pretrained model for the English language using a masked language modeling (MLM) and Sentence Order Prediction (SOP) objective. SqueezeBERT was introduced in this paper. This model is case-insensitive. The model architecture is similar to BERT-base, but with the pointwise fully-connected layers replaced with grouped convolutions. The authors found that SqueezeBERT is 4.3x faster than bert-base-uncased on a Google Pixel 3 smartphone.


Pretraining data

Pretraining procedure

The model is pretrained using the Masked Language Model (MLM) and Sentence Order Prediction (SOP) tasks. (Author's note: If you decide to pretrain your own model, and you prefer to train with MLM only, that should work too.)

The SqueezeBERT paper presents 2 approaches to finetuning the model:

We pretrain SqueezeBERT from scratch (without distillation) using the LAMB optimizer, and we employ the hyperparameters recommended by the LAMB authors: a global batch size of 8192, a learning rate of 2.5e-3, and a warmup proportion of 0.28. Following the LAMB paper's recommendations, we pretrain for 56k steps with a maximum sequence length of 128 and then for 6k steps with a maximum sequence length of 512.


The SqueezeBERT paper results from 2 approaches to finetuning the model:

  • "finetuning without bells and whistles" -- after pretraining the SqueezeBERT model, finetune it on each GLUE task
  • "finetuning with bells and whistles" -- after pretraining the SqueezeBERT model, finetune it on a MNLI with distillation from a teacher model. Then, use the MNLI-finetuned SqueezeBERT model as a student model to finetune on each of the other GLUE tasks (e.g. RTE, MRPC, …) with distillation from a task-specific teacher model.

A detailed discussion of the hyperparameters used for finetuning is provided in the appendix of the SqueezeBERT paper. Note that finetuning SqueezeBERT with distillation is not yet implemented in this repo. If the author (Forrest Iandola - gets enough encouragement from the user community, he will add example code to Transformers for finetuning SqueezeBERT with distillation.

This model, squeezebert/squeezebert-uncased, has been pretrained but not finetuned. For most text classification tasks, we recommend using squeezebert-mnli-headless as a starting point.

How to finetune

To try finetuning SqueezeBERT on the MRPC text classification task, you can run the following command:


python examples/text-classification/ \
    --model_name_or_path squeezebert-base-headless \
    --task_name mrpc \
    --data_dir ./glue_data/MRPC \
    --output_dir ./models/squeezebert_mrpc \
    --overwrite_output_dir \
    --do_train \
    --do_eval \
    --num_train_epochs 10 \
    --learning_rate 3e-05 \
    --per_device_train_batch_size 16 \
    --save_steps 20000

BibTeX entry and citation info

     author = {Forrest N. Iandola and Albert E. Shaw and Ravi Krishna and Kurt W. Keutzer},
     title = {{SqueezeBERT}: What can computer vision teach NLP about efficient neural networks?},
     journal = {arXiv:2006.11316},
     year = {2020}