Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -85,4 +85,17 @@ OpenThaiGPT Volunteers, Artificial Intelligence Entrepreneur Association of Thai
|
|
| 85 |
* Kriangkrai Saetan (kraitan.ss21@gmail.com)
|
| 86 |
* Pitikorn Khlaisamniang (pitikorn32@gmail.com)
|
| 87 |
|
| 88 |
-
<i>Disclaimer: Provided responses are not guaranteed.</i>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
* Kriangkrai Saetan (kraitan.ss21@gmail.com)
|
| 86 |
* Pitikorn Khlaisamniang (pitikorn32@gmail.com)
|
| 87 |
|
| 88 |
+
<i>Disclaimer: Provided responses are not guaranteed.</i>
|
| 89 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 90 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_openthaigpt__openthaigpt-1.0.0-alpha-7b-chat-ckpt-hf)
|
| 91 |
+
|
| 92 |
+
| Metric | Value |
|
| 93 |
+
|-----------------------|---------------------------|
|
| 94 |
+
| Avg. | 42.05 |
|
| 95 |
+
| ARC (25-shot) | 50.85 |
|
| 96 |
+
| HellaSwag (10-shot) | 74.89 |
|
| 97 |
+
| MMLU (5-shot) | 40.02 |
|
| 98 |
+
| TruthfulQA (0-shot) | 47.23 |
|
| 99 |
+
| Winogrande (5-shot) | 69.06 |
|
| 100 |
+
| GSM8K (5-shot) | 3.87 |
|
| 101 |
+
| DROP (3-shot) | 8.42 |
|