Commit
•
914052b
1
Parent(s):
ae7f22e
Adding Evaluation Results (#2)
Browse files- Adding Evaluation Results (31510fccf6b345ab471099406849c8de47b03832)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -81,4 +81,17 @@ function quicksort(array) {
|
|
| 81 |
if (left < right) {
|
| 82 |
quicksort(array, left, right);
|
| 83 |
}
|
| 84 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
if (left < right) {
|
| 82 |
quicksort(array, left, right);
|
| 83 |
}
|
| 84 |
+
```
|
| 85 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 86 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_lxe__Cerebras-GPT-2.7B-Alpaca-SP)
|
| 87 |
+
|
| 88 |
+
| Metric | Value |
|
| 89 |
+
|-----------------------|---------------------------|
|
| 90 |
+
| Avg. | 29.4 |
|
| 91 |
+
| ARC (25-shot) | 30.8 |
|
| 92 |
+
| HellaSwag (10-shot) | 48.88 |
|
| 93 |
+
| MMLU (5-shot) | 25.12 |
|
| 94 |
+
| TruthfulQA (0-shot) | 40.24 |
|
| 95 |
+
| Winogrande (5-shot) | 55.41 |
|
| 96 |
+
| GSM8K (5-shot) | 0.53 |
|
| 97 |
+
| DROP (3-shot) | 4.78 |
|