leaderboard-pr-bot's picture
Adding Evaluation Results
fe408d3
|
raw
history blame
694 Bytes
---
license: llama2
---
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_maximuslee07__llama-2-7b-rockwell-final)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 44.77 |
| ARC (25-shot) | 52.73 |
| HellaSwag (10-shot) | 79.1 |
| MMLU (5-shot) | 47.88 |
| TruthfulQA (0-shot) | 47.21 |
| Winogrande (5-shot) | 68.43 |
| GSM8K (5-shot) | 7.96 |
| DROP (3-shot) | 10.06 |