ehartford leaderboard-pr-bot commited on
Commit
979db8c
1 Parent(s): ad8892a

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (9c715720cdf836cfe91c5acc848876be1e8c6c7f)


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
@@ -33,4 +33,17 @@ ASSISTANT:
33
  ```
34
 
35
  Official character card: (thanks MortalWombat)
36
- ![](https://files.catbox.moe/zx9hfh.png)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  ```
34
 
35
  Official character card: (thanks MortalWombat)
36
+ ![](https://files.catbox.moe/zx9hfh.png)
37
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
38
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__samantha-1.1-llama-33b)
39
+
40
+ | Metric | Value |
41
+ |-----------------------|---------------------------|
42
+ | Avg. | 54.59 |
43
+ | ARC (25-shot) | 67.83 |
44
+ | HellaSwag (10-shot) | 85.55 |
45
+ | MMLU (5-shot) | 58.79 |
46
+ | TruthfulQA (0-shot) | 61.19 |
47
+ | Winogrande (5-shot) | 76.48 |
48
+ | GSM8K (5-shot) | 4.02 |
49
+ | DROP (3-shot) | 28.29 |