Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -152,4 +152,17 @@ The model will output something like:
|
|
152 |
|
153 |
## License
|
154 |
|
155 |
-
The `Aira-2-355M` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
152 |
|
153 |
## License
|
154 |
|
155 |
+
The `Aira-2-355M` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|
156 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
157 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nicholasKluge__Aira-2-355M)
|
158 |
+
|
159 |
+
| Metric | Value |
|
160 |
+
|-----------------------|---------------------------|
|
161 |
+
| Avg. | 27.0 |
|
162 |
+
| ARC (25-shot) | 27.56 |
|
163 |
+
| HellaSwag (10-shot) | 38.92 |
|
164 |
+
| MMLU (5-shot) | 27.26 |
|
165 |
+
| TruthfulQA (0-shot) | 38.53 |
|
166 |
+
| Winogrande (5-shot) | 53.75 |
|
167 |
+
| GSM8K (5-shot) | 0.0 |
|
168 |
+
| DROP (3-shot) | 2.99 |
|