Hugging Face's logo

lsmpp
/
qwenillustrious

Model card Files
xet
Community
qwenillustrious / transformers /docs /source /en /model_doc /albert.md
lsmpp's picture
lsmpp
Add files using upload-large-folder tool
4cef5ec verified
preview code
|
raw
history blame contribute delete
12 kB
PyTorch TensorFlow Flax SDPA

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.

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.

import torch
from transformers import pipeline

pipeline = pipeline(
    task="fill-mask",
    model="albert-base-v2",
    torch_dtype=torch.float16,
    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",
    torch_dtype=torch.float16,
    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])}")

echo -e "Plants create [MASK] through a process known as photosynthesis." | transformers run --task fill-mask --model albert-base-v2 --device 0

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.

Multiple choice

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

[[autodoc]] models.albert.modeling_tf_albert.TFAlbertForPreTrainingOutput

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

TFAlbertModel

[[autodoc]] TFAlbertModel - call

TFAlbertForPreTraining

[[autodoc]] TFAlbertForPreTraining - call

TFAlbertForMaskedLM

[[autodoc]] TFAlbertForMaskedLM - call

TFAlbertForSequenceClassification

[[autodoc]] TFAlbertForSequenceClassification - call

TFAlbertForMultipleChoice

[[autodoc]] TFAlbertForMultipleChoice - call

TFAlbertForTokenClassification

[[autodoc]] TFAlbertForTokenClassification - call

TFAlbertForQuestionAnswering

[[autodoc]] TFAlbertForQuestionAnswering - call

FlaxAlbertModel

[[autodoc]] FlaxAlbertModel - call

FlaxAlbertForPreTraining

[[autodoc]] FlaxAlbertForPreTraining - call

FlaxAlbertForMaskedLM

[[autodoc]] FlaxAlbertForMaskedLM - call

FlaxAlbertForSequenceClassification

[[autodoc]] FlaxAlbertForSequenceClassification - call

FlaxAlbertForMultipleChoice

[[autodoc]] FlaxAlbertForMultipleChoice - call

FlaxAlbertForTokenClassification

[[autodoc]] FlaxAlbertForTokenClassification - call

FlaxAlbertForQuestionAnswering

[[autodoc]] FlaxAlbertForQuestionAnswering - call