Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -142,3 +142,17 @@ The model will output something like:
|
|
| 142 |
## License
|
| 143 |
|
| 144 |
The `Aira-2-1B1` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 142 |
## License
|
| 143 |
|
| 144 |
The `Aira-2-1B1` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|
| 145 |
+
|
| 146 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 147 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nicholasKluge__Aira-2-1B1)
|
| 148 |
+
|
| 149 |
+
| Metric | Value |
|
| 150 |
+
|-----------------------|---------------------------|
|
| 151 |
+
| Avg. | 25.19 |
|
| 152 |
+
| ARC (25-shot) | 23.21 |
|
| 153 |
+
| HellaSwag (10-shot) | 26.97 |
|
| 154 |
+
| MMLU (5-shot) | 24.86 |
|
| 155 |
+
| TruthfulQA (0-shot) | 50.63 |
|
| 156 |
+
| Winogrande (5-shot) | 50.28 |
|
| 157 |
+
| GSM8K (5-shot) | 0.0 |
|
| 158 |
+
| DROP (3-shot) | 0.39 |
|