Update README.md
Browse files
    	
        README.md
    CHANGED
    
    | @@ -19,11 +19,12 @@ tags: | |
| 19 | 
             
            - autoquant
         | 
| 20 | 
             
            - gptq
         | 
| 21 | 
             
            - 8 bit
         | 
| 22 | 
            -
             | 
| 23 | 
             
            widget:
         | 
| 24 | 
            -
             | 
| 25 | 
            -
             | 
| 26 | 
            -
             | 
|  | |
|  | |
| 27 | 
             
            ---
         | 
| 28 |  | 
| 29 | 
             
            This is 8-bit GPTQ  version of [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct).
         | 
| @@ -149,4 +150,4 @@ TODO: Study the impact of calibration data on Instruction-tuned models. | |
| 149 |  | 
| 150 | 
             
            ### Evaluations
         | 
| 151 |  | 
| 152 | 
            -
            TODO wrt 8-bit model
         | 
|  | |
| 19 | 
             
            - autoquant
         | 
| 20 | 
             
            - gptq
         | 
| 21 | 
             
            - 8 bit
         | 
|  | |
| 22 | 
             
            widget:
         | 
| 23 | 
            +
            - messages:
         | 
| 24 | 
            +
              - role: user
         | 
| 25 | 
            +
                content: Can you provide ways to eat combinations of bananas and dragonfruits?
         | 
| 26 | 
            +
            base_model:
         | 
| 27 | 
            +
            - meta-llama/Meta-Llama-3.1-8B-Instruct
         | 
| 28 | 
             
            ---
         | 
| 29 |  | 
| 30 | 
             
            This is 8-bit GPTQ  version of [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct).
         | 
|  | |
| 150 |  | 
| 151 | 
             
            ### Evaluations
         | 
| 152 |  | 
| 153 | 
            +
            TODO wrt 8-bit model
         |