Update README.md
Browse files
README.md
CHANGED
|
@@ -19,3 +19,23 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 19 |
|
| 20 |
|
| 21 |
- PEFT 0.5.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
|
| 21 |
- PEFT 0.5.0
|
| 22 |
+
|
| 23 |
+
### Note on the version
|
| 24 |
+
- Train on Malay dataset using updated prompt
|
| 25 |
+
- Sample prompt as per follow
|
| 26 |
+
|
| 27 |
+
```
|
| 28 |
+
[INST] <<SYS>>
|
| 29 |
+
You as Malay language expert in text normalization.
|
| 30 |
+
Please normalize the following noisy Malay sentence into a standard Malay sentence.
|
| 31 |
+
Ensure proper grammar, punctuation, and spelling in the corrected version, and aim for a sentence of similar length.
|
| 32 |
+
<</SYS>>
|
| 33 |
+
|
| 34 |
+
### NOISY MALAY TEXT
|
| 35 |
+
terima kasih rakyat johor kerana bijak memilih untuk masa depan yang lebih baik. tahniah kenapa komponen parti #bn yang berkerja keras siang dan malam demi meraih kemenangan yang luar biasa. #johormemilih
|
| 36 |
+
|
| 37 |
+
### NORMALIZED MALAY TEXT [/INST]
|
| 38 |
+
terima kasih rakyat johor kerana bijak memilih untuk masa depan yang lebih baik. tahniah kepada komponen parti #bn yang berkerja keras siang dan malam demi meraih kemenangan yang luar biasa. #johormemilih
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
|