bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization

Model overview

The model is published by mrm8488 as a summarization checkpoint. The captured configuration identifies EncoderDecoderModel with model type encoder-decoder, and Safetensors metadata reports 23,427,898 parameters. According to the model card, it was fine-tuned on the CNN/DailyMail summarization dataset.

Recorded capabilities

Use cases in the source record

• English news-style summarization following the documented CNN/DailyMail fine-tuning and 512-token tokenizer truncation.

Limitations and unknowns

• The 16.51 ROUGE-2 figure is a publisher-reported result and was not independently verified.
• No context-window value beyond the card's 512-token usage truncation was extracted as structured data.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization

Captured: Unknown. Processed: 2026-09-07T19:34:52.613194+00:00.

Bert-mini2Bert-mini Summarization with 🤗EncoderDecoder Framework This model is a warm-started BERT2BERT ( mini ) 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 notebook. Results on test set 📝 Metric # Value ROUGE-2 16.51 Model in Action 🚀 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…