inference-optimization
/

granite-4.0-h-tiny-quantized.w4a16

granitemoehybrid

compressed-tensors

Model card Files Files and versions

krishnateja95 commited on 19 days ago

Commit

3b39735

·

verified ·

1 Parent(s): da46321

Update config.json

Files changed (1) hide show

config.json +1 -3

config.json CHANGED Viewed

@@ -93,11 +93,9 @@
           "num_bits": 4,
           "observer": "minmax",
           "observer_kwargs": {},
-          "scale_dtype": null,
           "strategy": "group",
           "symmetric": true,
-          "type": "int",
-          "zp_dtype": null
         }
       }
     },

           "num_bits": 4,
           "observer": "minmax",
           "observer_kwargs": {},
           "strategy": "group",
           "symmetric": true,
+          "type": "int"
         }
       }
     },