JeongwonChoi
commited on
Commit
•
0f0e809
1
Parent(s):
fb6eea0
Update README.md
Browse files
README.md
CHANGED
@@ -55,18 +55,22 @@ text = """\
|
|
55 |
|
56 |
## **Model Benchmark**
|
57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
|
59 |
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
| DataVortexS-10.7B-v0.1 | 0 | 0 | 0 | 0 | 0 | 0 |
|
64 |
-
| **DataVortexS-10.7B-v0.2** | **43.6** | **38.74** | **50.74** | **38.98** | **44.7** | **44.86** |
|
65 |
-
| DataVortexS-10.7B-v0.3 | 0 | 0 | 0 | 0 | 0 | 0 |
|
66 |
-
| DataVortexS-10.7B-v0.4 | 0 | 0 | 0 | 0 | 0 | 0 |
|
67 |
-
| DataVortexS-10.7B-v1.0 | 0 | 0 | 0 | 0 | 0 | 0 |
|
68 |
-
| DataVortexTL-1.1B-v0.1 | 0 | 0 | 0 | 0 | 0 | 0 |
|
69 |
-
| DataVortexS-10.7B-dpo-v0.1 | 0 | 0 | 0 | 0 | 0 | 0 |
|
70 |
|
71 |
## **Implementation Code**
|
72 |
|
|
|
55 |
|
56 |
## **Model Benchmark**
|
57 |
|
58 |
+
### [Ko LM Eval Harnesss](https://github.com/Beomi/ko-lm-evaluation-harness)
|
59 |
+
|
60 |
+
On Benchmarking ...
|
61 |
+
|
62 |
+
| Task | 0-shot | 5-shot | 10-shot | 50-shot |
|
63 |
+
| :--------------- | -----: | -----: | ------: | ------: |
|
64 |
+
| kobest_boolq | 0.0 | 0.0 | 0.0 | 0.0 |
|
65 |
+
| kobest_copa | 0.0 | 0.0 | 0.0 | 0.0 |
|
66 |
+
| kobest_hellaswag | 0.0 | 0.0 | 0.0 | 0.0 |
|
67 |
+
| kobest_sentineg | 0.0 | 0.0 | 0.0 | 0.0 |
|
68 |
+
|
69 |
### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
|
70 |
|
71 |
+
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
|
72 |
+
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
|
73 |
+
| 43.6 | 38.74 | 50.74 | 38.98 | 44.7 | 44.86 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
|
75 |
## **Implementation Code**
|
76 |
|