OpenHermes-Gemma-2B
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 46.36 |
| AI2 Reasoning Challenge (25-Shot) | 49.32 |
| HellaSwag (10-Shot) | 72.26 |
| MMLU (5-Shot) | 37.67 |
| TruthfulQA (0-shot) | 41.69 |
| Winogrande (5-shot) | 65.11 |
| GSM8k (5-shot) | 12.13 |
- Downloads last month
- 2,213
Dataset used to train vicgalle/OpenHermes-Gemma-2B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard49.320
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard72.260
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard37.670
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard41.690
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard65.110
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard12.130