Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -108,3 +108,17 @@ The 42dot LLM-PLM is licensed under the Creative Commons Attribution-NonCommerci
|
|
| 108 |
version = {1.0.0},
|
| 109 |
}
|
| 110 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
version = {1.0.0},
|
| 109 |
}
|
| 110 |
```
|
| 111 |
+
|
| 112 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 113 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_42dot__42dot_LLM-PLM-1.3B)
|
| 114 |
+
|
| 115 |
+
| Metric | Value |
|
| 116 |
+
|-----------------------|---------------------------|
|
| 117 |
+
| Avg. | 31.26 |
|
| 118 |
+
| ARC (25-shot) | 32.42 |
|
| 119 |
+
| HellaSwag (10-shot) | 56.39 |
|
| 120 |
+
| MMLU (5-shot) | 27.09 |
|
| 121 |
+
| TruthfulQA (0-shot) | 38.68 |
|
| 122 |
+
| Winogrande (5-shot) | 58.88 |
|
| 123 |
+
| GSM8K (5-shot) | 0.76 |
|
| 124 |
+
| DROP (3-shot) | 4.59 |
|