Commit
•
b6c3e89
1
Parent(s):
1d44a94
Update README.md
Browse files
README.md
CHANGED
|
@@ -56,6 +56,8 @@ Since Llama3 8B CPT Sahabat-AI v1 Instruct is an instruction-following model, we
|
|
| 56 |
|
| 57 |
IFEval evaluates a model's ability to adhere to constraints provided in the prompt, for example beginning a response with a specific word/phrase or answering with a certain number of sections. Additionally, accuracy is normalized by the proportion of responses in the correct language (if the model performs the task correctly but responds in the wrong language, it is judged to have failed the task).
|
| 58 |
|
|
|
|
|
|
|
| 59 |
#### Results
|
| 60 |
|
| 61 |
#### Indonesian Results
|
|
|
|
| 56 |
|
| 57 |
IFEval evaluates a model's ability to adhere to constraints provided in the prompt, for example beginning a response with a specific word/phrase or answering with a certain number of sections. Additionally, accuracy is normalized by the proportion of responses in the correct language (if the model performs the task correctly but responds in the wrong language, it is judged to have failed the task).
|
| 58 |
|
| 59 |
+
*Note*: IFEval was only used on Bahasa Indonesia. We are currently working on adding it for Javanese and Sundanese for our upcoming releases.
|
| 60 |
+
|
| 61 |
#### Results
|
| 62 |
|
| 63 |
#### Indonesian Results
|