ajibawa-2023 leaderboard-pr-bot commited on
Commit
ba2e72d
1 Parent(s): 96a9fbe

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (3fb8d4c44e985f48926be7f3dc55ad83d00d2ceb)


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

Files changed (1) hide show
  1. README.md +14 -0
README.md CHANGED
@@ -49,3 +49,17 @@ You are a Uncensored AI assistant.
49
  USER: <prompt>
50
  ASSISTANT:
51
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  USER: <prompt>
50
  ASSISTANT:
51
  ```
52
+
53
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
54
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ajibawa-2023__Uncensored-Jordan-7B)
55
+
56
+ | Metric | Value |
57
+ |-----------------------|---------------------------|
58
+ | Avg. | 46.88 |
59
+ | ARC (25-shot) | 51.28 |
60
+ | HellaSwag (10-shot) | 77.37 |
61
+ | MMLU (5-shot) | 45.69 |
62
+ | TruthfulQA (0-shot) | 47.5 |
63
+ | Winogrande (5-shot) | 71.11 |
64
+ | GSM8K (5-shot) | 6.75 |
65
+ | DROP (3-shot) | 28.46 |