blair-johnson leaderboard-pr-bot commited on
Commit
ba5272b
1 Parent(s): d866b68

Adding Evaluation Results (#3)

Browse files

- Adding Evaluation Results (ebc47a36881407893501ad205dec8cf2c5da12cf)


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
@@ -167,4 +167,17 @@ The base model HF repo can be found [here.](https://huggingface.co/bigcode/starc
167
  archivePrefix={arXiv},
168
  primaryClass={cs.CL}
169
  }
170
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
167
  archivePrefix={arXiv},
168
  primaryClass={cs.CL}
169
  }
170
+ ```
171
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
172
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_GeorgiaTechResearchInstitute__starcoder-gpteacher-code-instruct)
173
+
174
+ | Metric | Value |
175
+ |-----------------------|---------------------------|
176
+ | Avg. | 32.57 |
177
+ | ARC (25-shot) | 32.68 |
178
+ | HellaSwag (10-shot) | 47.6 |
179
+ | MMLU (5-shot) | 28.63 |
180
+ | TruthfulQA (0-shot) | 40.41 |
181
+ | Winogrande (5-shot) | 55.56 |
182
+ | GSM8K (5-shot) | 0.0 |
183
+ | DROP (3-shot) | 23.11 |