Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ Finetuned https://huggingface.co/mesolitica/nanot5-small-malaysian-cased using 2
|
|
| 13 |
- This model natively code switching.
|
| 14 |
- This model maintain `\n`, `\t`, `\r` as it is.
|
| 15 |
|
| 16 |
-
**Still in training session**, Wandb at https://wandb.ai/huseinzol05/nanot5-small-malaysian-cased-translation-v4
|
| 17 |
|
| 18 |
## Supported prefix
|
| 19 |
|
|
@@ -78,4 +78,8 @@ Output,
|
|
| 78 |
' Bayangkan PH dan menang PRU-14. Terdapat pelbagai pintu belakang. Akhirnya, Ismail Sabri naik. Itulah sebabnya saya tidak lagi bercakap tentang politik. Saya bersumpah sudah berputus asa.']
|
| 79 |
```
|
| 80 |
|
| 81 |
-
Input text can be any languages that speak in Malaysia, as long you use proper prefix, it should be able to translate to target language.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
- This model natively code switching.
|
| 14 |
- This model maintain `\n`, `\t`, `\r` as it is.
|
| 15 |
|
| 16 |
+
**Still in training session**, Wandb at https://wandb.ai/huseinzol05/nanot5-small-malaysian-cased-translation-v4-multipack/workspace
|
| 17 |
|
| 18 |
## Supported prefix
|
| 19 |
|
|
|
|
| 78 |
' Bayangkan PH dan menang PRU-14. Terdapat pelbagai pintu belakang. Akhirnya, Ismail Sabri naik. Itulah sebabnya saya tidak lagi bercakap tentang politik. Saya bersumpah sudah berputus asa.']
|
| 79 |
```
|
| 80 |
|
| 81 |
+
Input text can be any languages that speak in Malaysia, as long you use proper prefix, it should be able to translate to target language.
|
| 82 |
+
|
| 83 |
+
## how to finetune your own dataset?
|
| 84 |
+
|
| 85 |
+
We finetuned using T5 SDPA multipacking forked at https://github.com/mesolitica/t5-sdpa-multipack, super undocumented, but scripts from https://github.com/huggingface/transformers/tree/main/examples/pytorch/translation should work also.
|