Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -94,3 +94,17 @@ Parent Models with this license:
|
|
94 |
<br>[lemonilia/limarp-llama2-v2](https://huggingface.co/lemonilia/limarp-llama2-v2)
|
95 |
|
96 |
Support me [here](https://ko-fi.com/sao10k) :)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
<br>[lemonilia/limarp-llama2-v2](https://huggingface.co/lemonilia/limarp-llama2-v2)
|
95 |
|
96 |
Support me [here](https://ko-fi.com/sao10k) :)
|
97 |
+
|
98 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
99 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Sao10K__Euryale-L2-70B)
|
100 |
+
|
101 |
+
| Metric | Value |
|
102 |
+
|-----------------------|---------------------------|
|
103 |
+
| Avg. | 56.39 |
|
104 |
+
| ARC (25-shot) | 68.94 |
|
105 |
+
| HellaSwag (10-shot) | 87.07 |
|
106 |
+
| MMLU (5-shot) | 68.84 |
|
107 |
+
| TruthfulQA (0-shot) | 54.49 |
|
108 |
+
| Winogrande (5-shot) | 82.08 |
|
109 |
+
| GSM8K (5-shot) | 26.54 |
|
110 |
+
| DROP (3-shot) | 6.75 |
|