Commit
•
12a1ef6
1
Parent(s):
de6402a
Update README.md
Browse files
README.md
CHANGED
|
@@ -65,4 +65,9 @@ num_train_epochs=4,
|
|
| 65 |
predict_with_generate=True,
|
| 66 |
fp16=True,
|
| 67 |
report_to="none"
|
| 68 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
predict_with_generate=True,
|
| 66 |
fp16=True,
|
| 67 |
report_to="none"
|
| 68 |
+
```
|
| 69 |
+
|
| 70 |
+
## Reference
|
| 71 |
+
This model is based on the original <b>BART</b> architecture, as detailed in:
|
| 72 |
+
|
| 73 |
+
Lewis et al. (2019). BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. [arXiv:1910.13461](https://arxiv.org/abs/1910.13461)
|