Update README.md
Browse files
README.md
CHANGED
|
@@ -93,3 +93,7 @@ This model demonstrates that smaller models can still be productive models.
|
|
| 93 |
The hope is that this work opens the door to many in building small encoder models that pack a punch. Models can be trained in a matter of hours using consumer GPUs.
|
| 94 |
|
| 95 |
Imagine more specialized models like this for medical, legal, science and more.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
The hope is that this work opens the door to many in building small encoder models that pack a punch. Models can be trained in a matter of hours using consumer GPUs.
|
| 94 |
|
| 95 |
Imagine more specialized models like this for medical, legal, science and more.
|
| 96 |
+
|
| 97 |
+
## More Information
|
| 98 |
+
|
| 99 |
+
Read more about this model and how it was built in [this article](https://medium.com/neuml/training-tiny-language-models-with-token-hashing-b744aa7eb931).
|