19 lines
804 B
Markdown
19 lines
804 B
Markdown
---
|
|
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](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_beaugogh__Llama2-7b-openorca-mc-v2)
|
|
|
|
| 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 |
|