Summarization
Transformers
PyTorch
TensorFlow
German
mt5
text2text-generation
arxiv:2005.00661
arxiv:2111.09525
arxiv:2112.08542
arxiv:2109.09209
Instructions to use aiautomationlab/german-news-title-gen-mt5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aiautomationlab/german-news-title-gen-mt5 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("summarization", model="aiautomationlab/german-news-title-gen-mt5")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("aiautomationlab/german-news-title-gen-mt5") model = AutoModelForSeq2SeqLM.from_pretrained("aiautomationlab/german-news-title-gen-mt5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
is the dataset this was trained on publicly available?
#1
by pete-rrr - opened
is the dataset this was trained on publicly available? if so could I please get a link to it?
Hi pete-rrr, we trained the model on articles which were written by journalists from Bayerischer Rundfunk. We can't publish the dataset because the authors still hold the rights on their articles.
I apologize for the inconvenience.
redadmiral changed discussion status to closed
thank you the reply. It sounds a bit weird to me that the br would not have the permission to republish the articles in a slightly different format when the same articles were already published on the website