Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -61,3 +61,17 @@ Question: <Query>
|
|
| 61 |
|
| 62 |
Answer: <Response>
|
| 63 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
Answer: <Response>
|
| 63 |
```
|
| 64 |
+
|
| 65 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 66 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_kashif__stack-llama-2)
|
| 67 |
+
|
| 68 |
+
| Metric | Value |
|
| 69 |
+
|-----------------------|---------------------------|
|
| 70 |
+
| Avg. | 43.81 |
|
| 71 |
+
| ARC (25-shot) | 53.07 |
|
| 72 |
+
| HellaSwag (10-shot) | 78.57 |
|
| 73 |
+
| MMLU (5-shot) | 46.8 |
|
| 74 |
+
| TruthfulQA (0-shot) | 38.75 |
|
| 75 |
+
| Winogrande (5-shot) | 74.03 |
|
| 76 |
+
| GSM8K (5-shot) | 10.01 |
|
| 77 |
+
| DROP (3-shot) | 5.44 |
|