Adding Evaluation Results

#33
Files changed (1) hide show
  1. README.md +14 -0
README.md CHANGED
@@ -113,3 +113,17 @@ Beluga is a new technology that carries risks with use. Testing conducted to dat
113
  primaryClass={cs.CL}
114
  }
115
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
113
  primaryClass={cs.CL}
114
  }
115
  ```
116
+
117
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
118
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_stabilityai__StableBeluga2)
119
+
120
+ | Metric | Value |
121
+ |-----------------------|---------------------------|
122
+ | Avg. | 64.97 |
123
+ | ARC (25-shot) | 71.08 |
124
+ | HellaSwag (10-shot) | 86.37 |
125
+ | MMLU (5-shot) | 68.79 |
126
+ | TruthfulQA (0-shot) | 59.44 |
127
+ | Winogrande (5-shot) | 82.95 |
128
+ | GSM8K (5-shot) | 35.86 |
129
+ | DROP (3-shot) | 50.28 |