Update README.md
Browse files
README.md
CHANGED
@@ -20,10 +20,10 @@ This model is an improved version for Korean, based on the [Qwen2-72B-Instruct](
|
|
20 |
|
21 |
### KMMLU Benchmark
|
22 |
* [HAERAE-HUB/KMMLU](https://huggingface.co/datasets/HAERAE-HUB/KMMLU) benchmark accuracy score.
|
23 |
-
| Category |Qwen2-72B
|
24 |
-
|
25 |
-
| HUMSS | 0.63
|
26 |
-
| STEM | 0.59
|
27 |
-
| Applied Science | 0.56
|
28 |
-
| Other | 0.58
|
29 |
-
| Overall Accuracy| 0.58
|
|
|
20 |
|
21 |
### KMMLU Benchmark
|
22 |
* [HAERAE-HUB/KMMLU](https://huggingface.co/datasets/HAERAE-HUB/KMMLU) benchmark accuracy score.
|
23 |
+
| Category |Qwen2-72B-it-kor-dpo| Qwen2-72B-it | Mistral-Large-it-2407 | Questions |
|
24 |
+
|-----------------|--------------------|---------------|-----------------------|------------|
|
25 |
+
| HUMSS | 0.63 | 0.63 | 0.62 | 5130 |
|
26 |
+
| STEM | 0.59 | 0.59 | 0.57 | 9900 |
|
27 |
+
| Applied Science | 0.56 | 0.56 | 0.54 | 11600 |
|
28 |
+
| Other | 0.58 | 0.58 | 0.54 | 8400 |
|
29 |
+
| Overall Accuracy| 0.58 | 0.58 | 0.56 | 35030 |
|