ehartford leaderboard-pr-bot commited on
Commit
03afa1b
1 Parent(s): 3eca9fd

Adding Evaluation Results (#4)

Browse files

- Adding Evaluation Results (0b0da72c460cf951e9ef500416c8ea1c859f7bd5)


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
@@ -23,4 +23,17 @@ USER: <prompt>
23
  ASSISTANT:
24
  ```
25
 
26
- Thank you [chirper.ai](https://chirper.ai) for sponsoring some of my compute!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  ASSISTANT:
24
  ```
25
 
26
+ Thank you [chirper.ai](https://chirper.ai) for sponsoring some of my compute!
27
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
28
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__WizardLM-33B-V1.0-Uncensored)
29
+
30
+ | Metric | Value |
31
+ |-----------------------|---------------------------|
32
+ | Avg. | 54.41 |
33
+ | ARC (25-shot) | 63.65 |
34
+ | HellaSwag (10-shot) | 83.84 |
35
+ | MMLU (5-shot) | 59.36 |
36
+ | TruthfulQA (0-shot) | 56.8 |
37
+ | Winogrande (5-shot) | 77.66 |
38
+ | GSM8K (5-shot) | 18.65 |
39
+ | DROP (3-shot) | 20.89 |