Quantize Q5_0 with llamafile-0.9.0
Browse files
    	
        Mistral-7B-Instruct-v0.3.Q5_0.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:f24b6bda776238a2a1a9628aed0cff9a4f0205ff8a7fb456ec4aab2a715bc85f
         
     | 
| 3 | 
         
            +
            size 5245325620
         
     |