Update README.md
Browse files
README.md
CHANGED
|
@@ -6,11 +6,12 @@ This model is the result of a new approach called **QuaLA-MiniLM**, which combin
|
|
| 6 |
|
| 7 |
|
| 8 |
### QuaLA-MiniLM training process
|
| 9 |
-
Figure showing QuaLA-MiniLM training process. To run the model with the best accuracy-efficiency tradeoff per a specific computational budget, we set the length configuration to the best setting found by an evolutionary search to match our computational constraint.
|
| 10 |
-
[ArchitecureQuaLA-MiniLM.jpg](ArchitecureQuaLA-MiniLM.jpg)
|
| 11 |
|
| 12 |
-
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
| Model Detail | Description |
|
| 16 |
| ---- | --- |
|
|
|
|
| 6 |
|
| 7 |
|
| 8 |
### QuaLA-MiniLM training process
|
|
|
|
|
|
|
| 9 |
|
| 10 |
+
<!-- : # Figure showing QuaLA-MiniLM training process. 
|
| 11 |
+
-->
|
| 12 |
+
|
| 13 |
+
To run the model with the best accuracy-efficiency tradeoff per a specific computational budget, we set the length configuration to the best setting found by an evolutionary search to match our computational constraint.
|
| 14 |
+
|
| 15 |
|
| 16 |
| Model Detail | Description |
|
| 17 |
| ---- | --- |
|