metadata
license: apache-2.0
Llama2-7b finetuned on a 10k subset of OpenOrca focusing on multiple choice questions + 6k ShareGPT4 datasets.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 45.88 |
| ARC (25-shot) | 55.55 |
| HellaSwag (10-shot) | 81.26 |
| MMLU (5-shot) | 48.3 |
| TruthfulQA (0-shot) | 51.49 |
| Winogrande (5-shot) | 72.85 |
| GSM8K (5-shot) | 5.38 |
| DROP (3-shot) | 6.32 |