Commit 
							
							·
						
						f391c4c
	
1
								Parent(s):
							
							a1eeec4
								
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (51176d4de7584667e286f489fbbdd28fbc6564a7)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
    	
        README.md
    CHANGED
    
    | @@ -162,3 +162,17 @@ Quantized models: | |
| 162 |  | 
| 163 | 
             
            The work was supported by [#NASK](https://www.nask.pl/)
         | 
| 164 |  | 
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 162 |  | 
| 163 | 
             
            The work was supported by [#NASK](https://www.nask.pl/)
         | 
| 164 |  | 
| 165 | 
            +
             | 
| 166 | 
            +
            # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
         | 
| 167 | 
            +
            Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Voicelab__trurl-2-7b)
         | 
| 168 | 
            +
             | 
| 169 | 
            +
            | Metric                | Value                     |
         | 
| 170 | 
            +
            |-----------------------|---------------------------|
         | 
| 171 | 
            +
            | Avg.                  | 48.05   |
         | 
| 172 | 
            +
            | ARC (25-shot)         | 53.41          |
         | 
| 173 | 
            +
            | HellaSwag (10-shot)   | 75.29    |
         | 
| 174 | 
            +
            | MMLU (5-shot)         | 50.0         |
         | 
| 175 | 
            +
            | TruthfulQA (0-shot)   | 45.42   |
         | 
| 176 | 
            +
            | Winogrande (5-shot)   | 72.22   |
         | 
| 177 | 
            +
            | GSM8K (5-shot)        | 7.13        |
         | 
| 178 | 
            +
            | DROP (3-shot)         | 32.9         |
         | 

 
		