Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -206,3 +206,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 206 |
[More Information Needed]
|
| 207 |
|
| 208 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
[More Information Needed]
|
| 207 |
|
| 208 |
|
| 209 |
+
|
| 210 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 211 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_kevinpro__Vicuna-13B-CoT)
|
| 212 |
+
|
| 213 |
+
| Metric | Value |
|
| 214 |
+
|-----------------------|---------------------------|
|
| 215 |
+
| Avg. | 47.0 |
|
| 216 |
+
| ARC (25-shot) | 52.73 |
|
| 217 |
+
| HellaSwag (10-shot) | 80.13 |
|
| 218 |
+
| MMLU (5-shot) | 51.94 |
|
| 219 |
+
| TruthfulQA (0-shot) | 52.08 |
|
| 220 |
+
| Winogrande (5-shot) | 74.19 |
|
| 221 |
+
| GSM8K (5-shot) | 8.64 |
|
| 222 |
+
| DROP (3-shot) | 9.31 |
|