update README.md to include data-centric approach for improving model performance
Browse files
README.md
CHANGED
|
@@ -1,13 +1,9 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
license: apache-2.0
|
| 11 |
-
---
|
| 12 |
-
|
| 13 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
| 1 |
+
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
Describe in your README.md program ways in which you can improve
|
| 5 |
+
model performance are using
|
| 6 |
+
|
| 7 |
+
### (b) data-centric approach
|
| 8 |
+
|
| 9 |
+
To get better results, on our domain task, gen Z slang, we can shift our focus from just tweaking the model's settings to actually improving the data it learns from. This is a datacentric aprotche. The problem right now is that standard models are trained on formal, static text, so they often just guess when they encounter real-world slang. By finding and feeding the model fresh, raw datasets that capture these more casual areas. This can help the model performance on this specific task.
|
|
|
|
|
|
|
|
|
|
|
|