Instructions to use debbiesoon/bart_large_summarise_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use debbiesoon/bart_large_summarise_v3 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("debbiesoon/bart_large_summarise_v3") model = AutoModelForSeq2SeqLM.from_pretrained("debbiesoon/bart_large_summarise_v3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
a9e0f71
1
Parent(s): 837eccb
Update README.md
Browse files
README.md
CHANGED
|
@@ -43,6 +43,10 @@ This model was created to generate summaries of news articles.
|
|
| 43 |
|
| 44 |
The model takes up to maximum article length of 1024 characters and generates a summary of maximum length of 512 characters.
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Training hyperparameters
|
| 47 |
|
| 48 |
The following hyperparameters were used during training:
|
|
|
|
| 43 |
|
| 44 |
The model takes up to maximum article length of 1024 characters and generates a summary of maximum length of 512 characters.
|
| 45 |
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
This model was trained on 1000 articles and summaries from the Multi-News dataset. https://arxiv.org/abs/1906.01749
|
| 49 |
+
|
| 50 |
### Training hyperparameters
|
| 51 |
|
| 52 |
The following hyperparameters were used during training:
|