Sao10K leaderboard-pr-bot commited on
Commit
d70bd3a
1 Parent(s): 679aae3

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (ba9d2a7d54638a563f281f6cae1b2af680329278)


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
@@ -36,4 +36,17 @@ For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply
36
  ```
37
 
38
 
39
- Support me [here](https://ko-fi.com/sao10k) :)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  ```
37
 
38
 
39
+ Support me [here](https://ko-fi.com/sao10k) :)
40
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
41
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Sao10K__Zephyrus-L1-33B)
42
+
43
+ | Metric | Value |
44
+ |-----------------------|---------------------------|
45
+ | Avg. | 55.79 |
46
+ | ARC (25-shot) | 64.51 |
47
+ | HellaSwag (10-shot) | 84.15 |
48
+ | MMLU (5-shot) | 57.37 |
49
+ | TruthfulQA (0-shot) | 53.87 |
50
+ | Winogrande (5-shot) | 80.19 |
51
+ | GSM8K (5-shot) | 23.58 |
52
+ | DROP (3-shot) | 26.89 |