Upload README.md
Browse files
    	
        README.md
    CHANGED
    
    | 
         @@ -66,12 +66,12 @@ All evaluations were done using the [Pythia evaluation harness](https://github.c 
     | 
|
| 66 | 
         | 
| 67 | 
         
             
            ### Scores
         
     | 
| 68 | 
         | 
| 69 | 
         
            -
            | Model and Size            | ARC-easy   | ARC-challenge | HellaSwag  |  
     | 
| 70 | 
         
            -
            | ------------------------- | ---------- | ------------- | ---------- | ---------- | ---------- |  
     | 
| 71 | 
         
            -
            | EleutherAI/gpt-neo-125m   | 22.95%     | N/A           | 30.26%     | N/A        | N/A        | N/A 
     | 
| 72 | 
         
            -
            | HuggingFaceTB/SmolLM-135M | 43.99%     | N/A           | 42.30%     |  
     | 
| 73 | 
         
            -
            | OpenAI/GPT2-137M          | 31.09%     | N/A           | 29.76%     |  
     | 
| 74 | 
         
            -
            | **UNSAFE/Mixtress-135M**  | **29.21%** | **24.57%**    | **26.99%** | ** 
     | 
| 75 | 
         | 
| 76 | 
         
             
            ## Join Us
         
     | 
| 77 | 
         | 
| 
         | 
|
| 66 | 
         | 
| 67 | 
         
             
            ### Scores
         
     | 
| 68 | 
         | 
| 69 | 
         
            +
            | Model and Size            | ARC-easy   | ARC-challenge | HellaSwag  | PiQA       | TinyMMLU   | TriviaQA | Winogrande |
         
     | 
| 70 | 
         
            +
            | ------------------------- | ---------- | ------------- | ---------- | ---------- | ---------- | -------- | ---------- |
         
     | 
| 71 | 
         
            +
            | EleutherAI/gpt-neo-125m   | 22.95%     | N/A           | 30.26%     | N/A        | N/A        | N/A      | N/A        |
         
     | 
| 72 | 
         
            +
            | HuggingFaceTB/SmolLM-135M | 43.99%     | N/A           | 42.30%     | 69.60%     | 30.23%     | 4.11%    | 52.70%     |
         
     | 
| 73 | 
         
            +
            | OpenAI/GPT2-137M          | 31.09%     | N/A           | 29.76%     | 62.51%     | 26.29%     | 0.49%    | 49.72%     |
         
     | 
| 74 | 
         
            +
            | **UNSAFE/Mixtress-135M**  | **29.21%** | **24.57%**    | **26.99%** | **52.67%** | **31.71%** | **N/A**  | **50.91%** |
         
     | 
| 75 | 
         | 
| 76 | 
         
             
            ## Join Us
         
     | 
| 77 | 
         |