Migrate model card from transformers-repo
Browse filesRead announcement at https://discuss.huggingface.co/t/announcement-all-model-cards-will-be-migrated-to-hf-co-model-repos/2755
Original file history: https://github.com/huggingface/transformers/commits/master/model_cards/yuvraj/xSumm/README.md
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: "en"
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- extreme summarization
|
| 6 |
+
---
|
| 7 |
+
​
|
| 8 |
+
## Model description
|
| 9 |
+
​
|
| 10 |
+
BartForConditionalGenerationModel for extreme summarization- creates a one line abstractive summary of a given article
|
| 11 |
+
​
|
| 12 |
+
## How to use
|
| 13 |
+
​
|
| 14 |
+
PyTorch model available
|
| 15 |
+
​
|
| 16 |
+
```python
|
| 17 |
+
from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline
|
| 18 |
+
​
|
| 19 |
+
tokenizer = AutoTokenizer.from_pretrained("yuvraj/xSumm")
|
| 20 |
+
model = AutoModelWithLMHead.from_pretrained("yuvraj/xSumm")
|
| 21 |
+
​
|
| 22 |
+
xsumm = pipeline('summarization', model=model, tokenizer=tokenizer)
|
| 23 |
+
xsumm("<text to be summarized>")
|
| 24 |
+
​
|
| 25 |
+
## Limitations and bias
|
| 26 |
+
Trained on a small fraction of the xsumm training dataset
|