inference-optimization
/

granite-4.0-h-tiny-quantized.w8a8

granitemoehybrid

8-bit precision

compressed-tensors

Model card Files Files and versions

krishnateja95 commited on 25 days ago

Commit

507095e

·

verified ·

1 Parent(s): 7902614

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -90,7 +90,7 @@
           "observer_kwargs": {},
           "strategy": "token",
           "symmetric": true,
-          "type": "int",
         },
         "output_activations": null,
         "targets": [

           "observer_kwargs": {},
           "strategy": "token",
           "symmetric": true,
+          "type": "int"
         },
         "output_activations": null,
         "targets": [