Adding Evaluation Results
#70
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -208,3 +208,17 @@ Please cite this model using the following format:
|
|
| 208 |
urldate = {2023-03-28} % change this date
|
| 209 |
}
|
| 210 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 208 |
urldate = {2023-03-28} % change this date
|
| 209 |
}
|
| 210 |
```
|
| 211 |
+
|
| 212 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 213 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mosaicml__mpt-7b-instruct)
|
| 214 |
+
|
| 215 |
+
| Metric | Value |
|
| 216 |
+
|-----------------------|---------------------------|
|
| 217 |
+
| Avg. | 42.62 |
|
| 218 |
+
| ARC (25-shot) | 50.34 |
|
| 219 |
+
| HellaSwag (10-shot) | 77.91 |
|
| 220 |
+
| MMLU (5-shot) | 32.35 |
|
| 221 |
+
| TruthfulQA (0-shot) | 35.08 |
|
| 222 |
+
| Winogrande (5-shot) | 70.48 |
|
| 223 |
+
| GSM8K (5-shot) | 2.81 |
|
| 224 |
+
| DROP (3-shot) | 29.4 |
|