Commit
•
91711b2
1
Parent(s):
aad13bc
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (fe95094d645b3acb794af7ea430d3aedb4ad7f85)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 3 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dhmeltzer__Llama-2-13b-hf-ds_eli5_1024_r_64_alpha_16_merged)
|
| 4 |
+
|
| 5 |
+
| Metric | Value |
|
| 6 |
+
|-----------------------|---------------------------|
|
| 7 |
+
| Avg. | 47.8 |
|
| 8 |
+
| ARC (25-shot) | 59.13 |
|
| 9 |
+
| HellaSwag (10-shot) | 82.13 |
|
| 10 |
+
| MMLU (5-shot) | 54.98 |
|
| 11 |
+
| TruthfulQA (0-shot) | 44.23 |
|
| 12 |
+
| Winogrande (5-shot) | 76.4 |
|
| 13 |
+
| GSM8K (5-shot) | 8.11 |
|
| 14 |
+
| DROP (3-shot) | 9.6 |
|