Transformers
Safetensors
English
bart
text2text-generation
text-summarization
cnn-dailymail
Eval Results (legacy)
Instructions to use phanerozoic/BART-Large-CNN-Scratch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use phanerozoic/BART-Large-CNN-Scratch with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("phanerozoic/BART-Large-CNN-Scratch") model = AutoModelForSeq2SeqLM.from_pretrained("phanerozoic/BART-Large-CNN-Scratch") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -103,7 +103,8 @@ The performance of BART-Large-CNN-scratch is compared against Facebook's base BA
|
|
| 103 |
- **Comparison**:
|
| 104 |
- Both summaries start with identical descriptions of the Eiffel Tower's height and base dimensions.
|
| 105 |
- The Facebook summary mentions the historical significance of the Eiffel Tower surpassing the Washington Monument.
|
| 106 |
-
- The scratch summary includes the detail of the
|
|
|
|
| 107 |
|
| 108 |
#### Paper Clip Article Summary Comparison
|
| 109 |
|
|
|
|
| 103 |
- **Comparison**:
|
| 104 |
- Both summaries start with identical descriptions of the Eiffel Tower's height and base dimensions.
|
| 105 |
- The Facebook summary mentions the historical significance of the Eiffel Tower surpassing the Washington Monument.
|
| 106 |
+
- The scratch summary includes the detail of the tower being the second tallest free-standing structure in France, providing a different historical context.
|
| 107 |
+
- The scratch summary omits the name of the tower, indicating our deficiency in attempting to perfectly replicate Facebook's performance.
|
| 108 |
|
| 109 |
#### Paper Clip Article Summary Comparison
|
| 110 |
|