Instructions to use patrickvonplaten/roberta_shared_bbc_xsum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use patrickvonplaten/roberta_shared_bbc_xsum 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="patrickvonplaten/roberta_shared_bbc_xsum")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("patrickvonplaten/roberta_shared_bbc_xsum") model = AutoModelForSeq2SeqLM.from_pretrained("patrickvonplaten/roberta_shared_bbc_xsum") - Notebooks
- Google Colab
- Kaggle
The link was for BERT2BERT warm start model, not the RoBERTaShared model
#3
by pyRis - opened
README.md
CHANGED
|
@@ -13,4 +13,4 @@ This model is a warm-started *RoBERTaShared* model fine-tuned on the *BBC XSum*
|
|
| 13 |
The model achieves a **16.89** ROUGE-2 score on *BBC XSUM*'s test dataset.
|
| 14 |
|
| 15 |
For more details on how the model was fine-tuned, please refer to
|
| 16 |
-
[this](https://colab.research.google.com/
|
|
|
|
| 13 |
The model achieves a **16.89** ROUGE-2 score on *BBC XSUM*'s test dataset.
|
| 14 |
|
| 15 |
For more details on how the model was fine-tuned, please refer to
|
| 16 |
+
[this](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/RoBERTaShared_for_BBC_XSum.ipynb) notebook.
|