Update README.md
Browse files
README.md
CHANGED
@@ -13,13 +13,7 @@ handling contradictory or incomplete supervision data. Overton automates the lif
|
|
13 |
In fact, using Overton, engineers can build deep-learning-based applications without writing any code in frameworks like TensorFlow. For over a year,
|
14 |
Overton has been used in production to support multiple applications in both near-real-time applications and back-of-house processing.
|
15 |
In that time, Overton-based applications have answered billions of queries in multiple languages and processed trillions of records reducing errors
|
16 |
-
1.7-2.9 times versus production systems
|
17 |
-
|
18 |
-
license: mit
|
19 |
-
---
|
20 |
-
|
21 |
-
# T5 One Line Summary
|
22 |
-
A T5 model trained on 370,000 research papers, to generate one line summary based on description/abstract of the papers. It is trained using [simpleT5] library - A python package built on top of pytorch lightning⚡️ & transformers🤗 to quickly train T5 models
|
23 |
|
24 |
## Usage:
|
25 |
```python
|
|
|
13 |
In fact, using Overton, engineers can build deep-learning-based applications without writing any code in frameworks like TensorFlow. For over a year,
|
14 |
Overton has been used in production to support multiple applications in both near-real-time applications and back-of-house processing.
|
15 |
In that time, Overton-based applications have answered billions of queries in multiple languages and processed trillions of records reducing errors
|
16 |
+
1.7-2.9 times versus production systems
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Usage:
|
19 |
```python
|