Commit
c292233
1 Parent(s): 9369f14

Adding Evaluation Results (#25)

Browse files

- Adding Evaluation Results (06a9a55b604dd7612a24362ce85bc13ee7c1a8b6)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -180,4 +180,17 @@ To cite the GPT-NeoX-20B paper:
180
 
181
  copyright = {Creative Commons Attribution 4.0 International}
182
  }
183
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
180
 
181
  copyright = {Creative Commons Attribution 4.0 International}
182
  }
183
+ ```
184
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
185
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_EleutherAI__gpt-neox-20b)
186
+
187
+ | Metric | Value |
188
+ |-----------------------|---------------------------|
189
+ | Avg. | 36.02 |
190
+ | ARC (25-shot) | 45.73 |
191
+ | HellaSwag (10-shot) | 73.45 |
192
+ | MMLU (5-shot) | 25.0 |
193
+ | TruthfulQA (0-shot) | 31.61 |
194
+ | Winogrande (5-shot) | 68.9 |
195
+ | GSM8K (5-shot) | 2.43 |
196
+ | DROP (3-shot) | 5.04 |