pankajmathur leaderboard-pr-bot commited on
Commit
7b2f814
1 Parent(s): f9849ea

Adding Evaluation Results (#5)

Browse files

- Adding Evaluation Results (2d3bbba235e155309c4b1c55494f86958cd3c9bc)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -159,4 +159,17 @@ Please kindly cite using the following BibTeX:
159
  journal={arXiv preprint arXiv:2302.13971},
160
  year={2023}
161
  }
162
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
159
  journal={arXiv preprint arXiv:2302.13971},
160
  year={2023}
161
  }
162
+ ```
163
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
164
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psmathur__orca_mini_v3_7b)
165
+
166
+ | Metric | Value |
167
+ |-----------------------|---------------------------|
168
+ | Avg. | 47.98 |
169
+ | ARC (25-shot) | 56.91 |
170
+ | HellaSwag (10-shot) | 79.64 |
171
+ | MMLU (5-shot) | 52.37 |
172
+ | TruthfulQA (0-shot) | 50.51 |
173
+ | Winogrande (5-shot) | 74.27 |
174
+ | GSM8K (5-shot) | 7.13 |
175
+ | DROP (3-shot) | 15.06 |