Adding Evaluation Results
#2
by
leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -199,3 +199,17 @@ https://github.com/databrickslabs/dolly
|
|
| 199 |
[More Information Needed]
|
| 200 |
|
| 201 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 199 |
[More Information Needed]
|
| 200 |
|
| 201 |
|
| 202 |
+
|
| 203 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 204 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Corianas__1.3b)
|
| 205 |
+
|
| 206 |
+
| Metric | Value |
|
| 207 |
+
|-----------------------|---------------------------|
|
| 208 |
+
| Avg. | 27.02 |
|
| 209 |
+
| ARC (25-shot) | 27.3 |
|
| 210 |
+
| HellaSwag (10-shot) | 38.3 |
|
| 211 |
+
| MMLU (5-shot) | 26.77 |
|
| 212 |
+
| TruthfulQA (0-shot) | 39.02 |
|
| 213 |
+
| Winogrande (5-shot) | 53.04 |
|
| 214 |
+
| GSM8K (5-shot) | 0.15 |
|
| 215 |
+
| DROP (3-shot) | 4.57 |
|