ehartford leaderboard-pr-bot commited on
Commit
c6ed3a9
1 Parent(s): 134cea1

Adding Evaluation Results (#6)

Browse files

- Adding Evaluation Results (b77c4347fc069fc445c493329f6637c1f58cf97e)


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

Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -21,4 +21,17 @@ You are a helpful AI assistant.
21
 
22
  USER: <prompt>
23
  ASSISTANT:
24
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
 
22
  USER: <prompt>
23
  ASSISTANT:
24
+ ```
25
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
26
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__WizardLM-1.0-Uncensored-Llama2-13b)
27
+
28
+ | Metric | Value |
29
+ |-----------------------|---------------------------|
30
+ | Avg. | 49.31 |
31
+ | ARC (25-shot) | 55.72 |
32
+ | HellaSwag (10-shot) | 80.34 |
33
+ | MMLU (5-shot) | 55.4 |
34
+ | TruthfulQA (0-shot) | 51.44 |
35
+ | Winogrande (5-shot) | 74.66 |
36
+ | GSM8K (5-shot) | 13.27 |
37
+ | DROP (3-shot) | 14.35 |