Mbart Large Cc25 Cnn Dailymail Xsum Nl

🚀 mbart-large-cc25-cnn-dailymail-xsum-nl

This is a fine - tuned version of mbart for Dutch news article summarization, with details shared in a related blog post.

🚀 Quick Start

This model is designed for summarizing Dutch news articles. Below is a Python code example demonstrating how to use it:

import transformers

undisputed_best_model = transformers.MBartForConditionalGeneration.from_pretrained(
    "ml6team/mbart-large-cc25-cnn-dailymail-xsum-nl"
)
tokenizer = transformers.MBartTokenizer.from_pretrained("facebook/mbart-large-cc25")
summarization_pipeline = transformers.pipeline(
    task="summarization",
    model=undisputed_best_model,
    tokenizer=tokenizer,
)
summarization_pipeline.model.config.decoder_start_token_id = tokenizer.lang_code_to_id[
    "nl_XX"
]

article = "Kan je dit even samenvatten alsjeblief."  # Dutch
summarization_pipeline(
    article,
    do_sample=True,
    top_p=0.75,
    top_k=50,
    min_length=50,
    early_stopping=True,
    truncation=True,
)[0]["summary_text"]

✨ Features

• Fine - tuned Model: It is a fine - tuned version of mbart, optimized for Dutch news article summarization.
• Blog Post: There is a related blog post about this model here.

📦 Installation

The code example above assumes you have the transformers library installed. You can install it using the following command:

pip install transformers

📚 Documentation

Model description

This is a fine - tuned version of mbart. You can find more information about this model in the blog post.

Training data

The model was fine - tuned using this dataset and this dataset.

Model Information Table