Quantize Q2_K with llamafile-0.9.0
Browse files
    	
        Mistral-7B-Instruct-v0.3.Q2_K.llamafile
    CHANGED
    
    | 
         @@ -1,3 +1,3 @@ 
     | 
|
| 1 | 
         
             
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            -
            oid sha256: 
     | 
| 3 | 
         
            -
            size  
     | 
| 
         | 
|
| 1 | 
         
             
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:dbcf6d2562d648e92de2bc3a6b1a98c5a386e4aa7a156e9eb375b1cb8d8506b8
         
     | 
| 3 | 
         
            +
            size 2965721396
         
     |