transformers/docs/source/en/model_doc/albert.md

This model was published in HF papers on 2019-09-26 and contributed to Hugging Face Transformers on 2020-11-16.

ALBERT

ALBERT is designed to address memory limitations of scaling and training of BERT. It adds two parameter reduction techniques. The first, factorized embedding parametrization, splits the larger vocabulary embedding matrix into two smaller matrices so you can grow the hidden size without adding a lot more parameters. The second, cross-layer parameter sharing, allows layer to share parameters which keeps the number of learnable parameters lower.

ALBERT was created to address problems like -- GPU/TPU memory limitations, longer training times, and unexpected model degradation in BERT. ALBERT uses two parameter-reduction techniques to lower memory consumption and increase the training speed of BERT:

• Factorized embedding parameterization: The large vocabulary embedding matrix is decomposed into two smaller matrices, reducing memory consumption.
• Cross-layer parameter sharing: Instead of learning separate parameters for each transformer layer, ALBERT shares parameters across layers, further reducing the number of learnable weights.

ALBERT uses absolute position embeddings (like BERT) so padding is applied at right. Size of embeddings is 128 While BERT uses 768. ALBERT can processes maximum 512 token at a time.

You can find all the original ALBERT checkpoints under the ALBERT community organization.

Tip

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

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

from transformers import pipeline


pipeline = pipeline(
    task="fill-mask",
    model="albert-base-v2",
    device=0
)
pipeline("Plants create [MASK] through a process known as photosynthesis.", top_k=5)

import torch

from transformers import AutoModelForMaskedLM, AutoTokenizer


tokenizer = AutoTokenizer.from_pretrained("albert/albert-base-v2")
model = AutoModelForMaskedLM.from_pretrained(
    "albert/albert-base-v2",
    attn_implementation="sdpa",
    device_map="auto"
)

prompt = "Plants create energy through a process known as [MASK]."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs)
    mask_token_index = torch.where(inputs["input_ids"] == tokenizer.mask_token_id)[1]
    predictions = outputs.logits[0, mask_token_index]

top_k = torch.topk(predictions, k=5).indices.tolist()
for token_id in top_k[0]:
    print(f"Prediction: {tokenizer.decode([token_id])}")

Notes

• Inputs should be padded on the right because BERT uses absolute position embeddings.
• The embedding size E is different from the hidden size H because the embeddings are context independent (one embedding vector represents one token) and the hidden states are context dependent (one hidden state represents a sequence of tokens). The embedding matrix is also larger because V x E where V is the vocabulary size. As a result, it's more logical if H >> E. If E < H, the model has less parameters.

Resources

The resources provided in the following sections consist of a list of official Hugging Face and community (indicated by 🌎) resources to help you get started with AlBERT. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

• [AlbertForSequenceClassification] is supported by this example script.

• Check the Text classification task guide on how to use the model.

• [AlbertForTokenClassification] is supported by this example script.

• Token classification chapter of the 🤗 Hugging Face Course.

• Check the Token classification task guide on how to use the model.

• [AlbertForMaskedLM] is supported by this example script and notebook.
• Masked language modeling chapter of the 🤗 Hugging Face Course.
• Check the Masked language modeling task guide on how to use the model.

• [AlbertForQuestionAnswering] is supported by this example script and notebook.
• Question answering chapter of the 🤗 Hugging Face Course.
• Check the Question answering task guide on how to use the model.

Multiple choice

• [AlbertForMultipleChoice] is supported by this example script and notebook.
• Check the Multiple choice task guide on how to use the model.

AlbertConfig

autodoc AlbertConfig

AlbertTokenizer

autodoc AlbertTokenizer - build_inputs_with_special_tokens - get_special_tokens_mask - create_token_type_ids_from_sequences - save_vocabulary

AlbertTokenizerFast

autodoc AlbertTokenizerFast

Albert specific outputs

autodoc models.albert.modeling_albert.AlbertForPreTrainingOutput

AlbertModel

autodoc AlbertModel - forward

AlbertForPreTraining

autodoc AlbertForPreTraining - forward

AlbertForMaskedLM

autodoc AlbertForMaskedLM - forward

AlbertForSequenceClassification

autodoc AlbertForSequenceClassification - forward

AlbertForMultipleChoice

autodoc AlbertForMultipleChoice

AlbertForTokenClassification

autodoc AlbertForTokenClassification - forward

AlbertForQuestionAnswering

autodoc AlbertForQuestionAnswering - forward