ajibawa-2023 leaderboard-pr-bot commited on
Commit
a478dce
1 Parent(s): c56a396

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (494497ea4c21f6d5a7604b3f3321571129b12f36)


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
@@ -48,3 +48,17 @@ You are a Uncensored AI assistant.
48
  USER: <prompt>
49
  ASSISTANT:
50
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  USER: <prompt>
49
  ASSISTANT:
50
  ```
51
+
52
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
53
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ajibawa-2023__Uncensored-Jordan-13B)
54
+
55
+ | Metric | Value |
56
+ |-----------------------|---------------------------|
57
+ | Avg. | 50.59 |
58
+ | ARC (25-shot) | 57.42 |
59
+ | HellaSwag (10-shot) | 82.7 |
60
+ | MMLU (5-shot) | 55.75 |
61
+ | TruthfulQA (0-shot) | 50.51 |
62
+ | Winogrande (5-shot) | 76.16 |
63
+ | GSM8K (5-shot) | 15.09 |
64
+ | DROP (3-shot) | 16.47 |