PSanni leaderboard-pr-bot commited on
Commit
0396a68
1 Parent(s): d28930e

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (2104ff7ef66a70e6d3aac24ab1daccb896835a64)


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
@@ -30,4 +30,17 @@ print(res[0]["generated_text"])
30
 
31
  ### Note:
32
 
33
- Kindly note that the model isn't attuned to human preferences and could generate unsuitable, unethical, biased, and toxic responses.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
 
31
  ### Note:
32
 
33
+ Kindly note that the model isn't attuned to human preferences and could generate unsuitable, unethical, biased, and toxic responses.
34
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
35
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PSanni__Deer-3b)
36
+
37
+ | Metric | Value |
38
+ |-----------------------|---------------------------|
39
+ | Avg. | 32.01 |
40
+ | ARC (25-shot) | 38.48 |
41
+ | HellaSwag (10-shot) | 57.41 |
42
+ | MMLU (5-shot) | 25.64 |
43
+ | TruthfulQA (0-shot) | 39.98 |
44
+ | Winogrande (5-shot) | 57.46 |
45
+ | GSM8K (5-shot) | 0.3 |
46
+ | DROP (3-shot) | 4.83 |