Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -187,4 +187,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
187 |
|
188 |
## Model Card Contact
|
189 |
|
190 |
-
[More Information Needed]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
187 |
|
188 |
## Model Card Contact
|
189 |
|
190 |
+
[More Information Needed]
|
191 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
192 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Corianas__Quokka_590m)
|
193 |
+
|
194 |
+
| Metric | Value |
|
195 |
+
|-----------------------|---------------------------|
|
196 |
+
| Avg. | 25.02 |
|
197 |
+
| ARC (25-shot) | 24.4 |
|
198 |
+
| HellaSwag (10-shot) | 31.61 |
|
199 |
+
| MMLU (5-shot) | 25.36 |
|
200 |
+
| TruthfulQA (0-shot) | 39.59 |
|
201 |
+
| Winogrande (5-shot) | 50.2 |
|
202 |
+
| GSM8K (5-shot) | 0.0 |
|
203 |
+
| DROP (3-shot) | 3.96 |
|