Update README.md
Browse files
README.md
CHANGED
|
@@ -12,5 +12,5 @@ Performance in terms of [sacrebleu](https://huggingface.co/docs/datasets/v1.5.0/
|
|
| 12 |
* num_train_epochs=1
|
| 13 |
|
| 14 |
# Thoughts
|
| 15 |
-
* Model `Helsinki-NLP/opus-mt-en-vi` is small (around 260MB), and can be easily deployed to a cheap server (e.g., EC2 t2.medium) without
|
| 16 |
* Easier and much faster to train compared to t5 or byt5.
|
|
|
|
| 12 |
* num_train_epochs=1
|
| 13 |
|
| 14 |
# Thoughts
|
| 15 |
+
* Model `Helsinki-NLP/opus-mt-en-vi` is small (around 260MB), and can be easily deployed to a cheap server (e.g., EC2 t2.medium) without a GPU
|
| 16 |
* Easier and much faster to train compared to t5 or byt5.
|