bert2bert_L-24_wmt_de_en EncoderDecoder model

The model was introduced in this paper by Sascha Rothe, Shashi Narayan, Aliaksei Severyn and first released in this repository.

The model is an encoder-decoder model that was initialized on the bert-large checkpoints for both the encoder and decoder and fine-tuned on German to English translation on the WMT dataset, which is linked above.

Disclaimer: The model card has been written by the Hugging Face team.

How to use

You can use this model for translation, e.g.

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("google/bert2bert_L-24_wmt_de_en", pad_token="<pad>", eos_token="</s>", bos_token="<s>")
model = AutoModelForSeq2SeqLM.from_pretrained("google/bert2bert_L-24_wmt_de_en")

sentence = "Willst du einen Kaffee trinken gehen mit mir?"

input_ids = tokenizer(sentence, return_tensors="pt", add_special_tokens=False).input_ids
output_ids = model.generate(input_ids)[0]
print(tokenizer.decode(output_ids, skip_special_tokens=True))
# should output
# Want to drink a kaffee go with me? .
Downloads last month
746
Hosted inference API
Translation
This model can be loaded on the Inference API on-demand.