Upload README.md
Browse files
README.md
CHANGED
@@ -24,13 +24,24 @@ license: cc-by-nc-sa-4.0
|
|
24 |
- [kyujinpy/KOR-OpenOrca-Platypus-v3](https://huggingface.co/datasets/kyujinpy/KOR-OpenOrca-Platypus-v3).
|
25 |
|
26 |
---
|
27 |
-
# Model
|
28 |
> Ko-LLM leaderboard(11/23; [link](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard))
|
29 |
|
30 |
| Model | Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
|
31 |
| --- | --- | --- | --- | --- | --- | --- |
|
32 |
| **⭐My custom LLM 13B⭐** | 50.19 | 45.99 | 56.93 | 41.78 | 41.66 | **64.58** |
|
33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
# Implementation Code
|
35 |
```python
|
36 |
### KO-Platypus
|
|
|
24 |
- [kyujinpy/KOR-OpenOrca-Platypus-v3](https://huggingface.co/datasets/kyujinpy/KOR-OpenOrca-Platypus-v3).
|
25 |
|
26 |
---
|
27 |
+
# Model comparisons1
|
28 |
> Ko-LLM leaderboard(11/23; [link](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard))
|
29 |
|
30 |
| Model | Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
|
31 |
| --- | --- | --- | --- | --- | --- | --- |
|
32 |
| **⭐My custom LLM 13B⭐** | 50.19 | 45.99 | 56.93 | 41.78 | 41.66 | **64.58** |
|
33 |
|
34 |
+
---
|
35 |
+
# Model comparisons2
|
36 |
+
> AI-Harness evaluation; [link]()
|
37 |
+
|
38 |
+
| Model | Copa | Copa | HellaSwag | HellaSwag | BoolQ | BoolQ | Sentineg | Sentineg |
|
39 |
+
| | 0-shot | 5-shot | 0-shot | 5-shot | 0-shot | 5-shot | 0-shot | 5-shot |
|
40 |
+
| --- | --- | --- | --- | --- | --- | --- |
|
41 |
+
| **⭐My custom LLM 13B⭐** | NaN | 0.8269 | NaN | 0.5660 | NaN | 0.5060 | NaN | 0.9723 |
|
42 |
+
| [beomi/llama-2-koen-13b](https://huggingface.co/beomi/llama-2-koen-13b) | 0.7768 | 0.8128 | 0.4999 | 0.5127| 0.3988 | 0.7038 | 0.5870 | 0.9748 |
|
43 |
+
|
44 |
+
|
45 |
# Implementation Code
|
46 |
```python
|
47 |
### KO-Platypus
|