enginex-mlu370-any2any/transformers/docs/source/en/model_doc/encoder-decoder.md

This model was released on 2017-06-12 and added to Hugging Face Transformers on 2020-11-16.

Encoder Decoder Models

EncoderDecoderModel initializes a sequence-to-sequence model with any pretrained autoencoder and pretrained autoregressive model. It is effective for sequence generation tasks as demonstrated in Text Summarization with Pretrained Encoders which uses [BertModel] as the encoder and decoder.

Tip

This model was contributed by thomwolf.

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

The example below demonstrates how to generate text with [Pipeline], [AutoModel], and from the command line.

from transformers import pipeline

summarizer = pipeline(
    "summarization",
    model="patrickvonplaten/bert2bert-cnn_dailymail-fp16",
    device=0
)

text = "Plants create energy through a process known as photosynthesis. This involves capturing sunlight and converting carbon dioxide and water into glucose and oxygen."
print(summarizer(text))

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("patrickvonplaten/bert2bert-cnn_dailymail-fp16")
model = AutoModelForCausalLM.from_pretrained("patrickvonplaten/bert2bert-cnn_dailymail-fp16", dtype=torch.bfloat16, device_map="auto",attn_implementation="sdpa")

text = "Plants create energy through a process known as photosynthesis. This involves capturing sunlight and converting carbon dioxide and water into glucose and oxygen."

inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True).to(model.device)

summary = model.generate(**inputs, max_length=60, num_beams=4, early_stopping=True)
print(tokenizer.decode(summary[0], skip_special_tokens=True))

echo -e "Plants create energy through a process known as photosynthesis. This involves capturing sunlight and converting carbon dioxide and water into glucose and oxygen." | transformers run --task summarization --model "patrickvonplaten/bert2bert-cnn_dailymail-fp16" --device 0

Notes

• [EncoderDecoderModel] can be initialized using any pretrained encoder and decoder. But depending on the decoder architecture, the cross-attention layers may be randomly initialized.

These models require downstream fine-tuning, as discussed in this blog post. Use [~EncoderDecoderModel.from_encoder_decoder_pretrained] to combine encoder and decoder checkpoints.

from transformers import EncoderDecoderModel, BertTokenizer

tokenizer = BertTokenizer.from_pretrained("google-bert/bert-base-uncased")
model = EncoderDecoderModel.from_encoder_decoder_pretrained(
    "google-bert/bert-base-uncased",
    "google-bert/bert-base-uncased"
)

• Encoder Decoder models can be fine-tuned like BART, T5 or any other encoder-decoder model. Only 2 inputs are required to compute a loss, input_ids and labels. Refer to this notebook for a more detailed training example.

>>> from transformers import BertTokenizer, EncoderDecoderModel

>>> tokenizer = BertTokenizer.from_pretrained("google-bert/bert-base-uncased")
>>> model = EncoderDecoderModel.from_encoder_decoder_pretrained("google-bert/bert-base-uncased", "google-bert/bert-base-uncased")

>>> model.config.decoder_start_token_id = tokenizer.cls_token_id
>>> model.config.pad_token_id = tokenizer.pad_token_id

>>> input_ids = tokenizer(
...     "The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side.During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was  finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft).Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.",
...     return_tensors="pt",
... ).input_ids

>>> labels = tokenizer(
...     "the eiffel tower surpassed the washington monument to become the tallest structure in the world. it was the first structure to reach a height of 300 metres in paris in 1930. it is now taller than the chrysler building by 5. 2 metres ( 17 ft ) and is the second tallest free - standing structure in paris.",
...     return_tensors="pt",
... ).input_ids

>>> # the forward function automatically creates the correct decoder_input_ids
>>> loss = model(input_ids=input_ids, labels=labels).loss

• [EncoderDecoderModel] can be randomly initialized from an encoder and a decoder config as shown below.

>>> from transformers import BertConfig, EncoderDecoderConfig, EncoderDecoderModel

>>> config_encoder = BertConfig()
>>> config_decoder = BertConfig()

>>> config = EncoderDecoderConfig.from_encoder_decoder_configs(config_encoder, config_decoder)
>>> model = EncoderDecoderModel(config=config)

• The Encoder Decoder Model can also be used for translation as shown below.

from transformers import AutoTokenizer, EncoderDecoderModel

# Load a pre-trained translation model
model_name = "google/bert2bert_L-24_wmt_en_de"
tokenizer = AutoTokenizer.from_pretrained(model_name, pad_token="<pad>", eos_token="</s>", bos_token="<s>")
model = EncoderDecoderModel.from_pretrained(model_name)

# Input sentence to translate
input_text = "Plants create energy through a process known as"

# Encode the input text
inputs = tokenizer(input_text, return_tensors="pt", add_special_tokens=False).input_ids

# Generate the translated output
outputs = model.generate(inputs)[0]

# Decode the output tokens to get the translated sentence
translated_text = tokenizer.decode(outputs, skip_special_tokens=True)

print("Translated text:", translated_text)

EncoderDecoderConfig

autodoc EncoderDecoderConfig

EncoderDecoderModel

autodoc EncoderDecoderModel - forward - from_encoder_decoder_pretrained