Instructions to use manueldeprada/FactCC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use manueldeprada/FactCC with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="manueldeprada/FactCC")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("manueldeprada/FactCC") model = AutoModelForSequenceClassification.from_pretrained("manueldeprada/FactCC") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit ·
c7b3148
1
Parent(s): 59a7949
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ metrics:
|
|
| 11 |
|
| 12 |
Original paper: [Evaluating the Factual Consistency of Abstractive Text Summarization](https://arxiv.org/abs/1910.12840)
|
| 13 |
|
|
|
|
|
|
|
| 14 |
This model is trained to predict whether a summary is factual with respect to the original text. Basic usage:
|
| 15 |
```
|
| 16 |
from transformers import BertForSequenceClassification, BertTokenizer
|
|
|
|
| 11 |
|
| 12 |
Original paper: [Evaluating the Factual Consistency of Abstractive Text Summarization](https://arxiv.org/abs/1910.12840)
|
| 13 |
|
| 14 |
+
This is a more modern implementation of the model and code from [the original github repo](https://github.com/salesforce/factCC)
|
| 15 |
+
|
| 16 |
This model is trained to predict whether a summary is factual with respect to the original text. Basic usage:
|
| 17 |
```
|
| 18 |
from transformers import BertForSequenceClassification, BertTokenizer
|