Instructions to use praf-choub/bart-CaPE-cnn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use praf-choub/bart-CaPE-cnn 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="praf-choub/bart-CaPE-cnn")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("praf-choub/bart-CaPE-cnn") model = AutoModelForSeq2SeqLM.from_pretrained("praf-choub/bart-CaPE-cnn", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
0757e02
1
Parent(s): 7db28de
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,18 @@ tags:
|
|
| 5 |
license: bsd-3-clause
|
| 6 |
datasets:
|
| 7 |
- cnn_dailymail
|
| 8 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
license: bsd-3-clause
|
| 6 |
datasets:
|
| 7 |
- cnn_dailymail
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
Citation
|
| 11 |
+
```
|
| 12 |
+
@misc{https://doi.org/10.48550/arxiv.2110.07166,
|
| 13 |
+
doi = {10.48550/ARXIV.2110.07166},
|
| 14 |
+
url = {https://arxiv.org/abs/2110.07166},
|
| 15 |
+
author = {Choubey, Prafulla Kumar and Fabbri, Alexander R. and Vig, Jesse and Wu, Chien-Sheng and Liu, Wenhao and Rajani, Nazneen Fatema},
|
| 16 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
| 17 |
+
title = {CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization},
|
| 18 |
+
publisher = {arXiv},
|
| 19 |
+
year = {2021},
|
| 20 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
| 21 |
+
}
|
| 22 |
+
```
|