From 66e9608bae7bfe713fa348445b9b3a4aa8160cc2 Mon Sep 17 00:00:00 2001 From: Manuel Romero Date: Thu, 26 Nov 2020 18:43:43 +0100 Subject: [PATCH] Create README.md (#8760) --- .../README.md | 52 +++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 model_cards/mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization/README.md diff --git a/model_cards/mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization/README.md b/model_cards/mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization/README.md new file mode 100644 index 0000000000..f5589cc1da --- /dev/null +++ b/model_cards/mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization/README.md @@ -0,0 +1,52 @@ +--- +language: en +license: apache-2.0 +datasets: +- cnn_dailymail +tags: +- summarization +--- + +# Bert-mini2Bert-mini Summarization with 🤗EncoderDecoder Framework + +This model is a warm-started *BERT2BERT* ([mini](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4)) model fine-tuned on the *CNN/Dailymail* summarization dataset. + +The model achieves a **16.51** ROUGE-2 score on *CNN/Dailymail*'s test dataset. + +For more details on how the model was fine-tuned, please refer to +[this](https://colab.research.google.com/drive/1Ekd5pUeCX7VOrMx94_czTkwNtLN32Uyu?usp=sharing) notebook. + +## Results on test set 📝 + +| Metric | # Value | +| ------ | --------- | +| **ROUGE-2** | **16.51** | + + + +## Model in Action 🚀 + +```python +from transformers import BertTokenizerFast, EncoderDecoderModel +import torch +device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') +tokenizer = BertTokenizerFast.from_pretrained('mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization') +model = EncoderDecoderModel.from_pretrained('mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization').to(device) + +def generate_summary(text): + # cut off at BERT max length 512 + inputs = tokenizer([text], padding="max_length", truncation=True, max_length=512, return_tensors="pt") + input_ids = inputs.input_ids.to(device) + attention_mask = inputs.attention_mask.to(device) + + output = model.generate(input_ids, attention_mask=attention_mask) + + return tokenizer.decode(output[0], skip_special_tokens=True) + +text = "your text to be summarized here..." +generate_summary(text) +``` + +> Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488) | [LinkedIn](https://www.linkedin.com/in/manuel-romero-cs/) + +> Made with ♥ in Spain