aws-neuron
/

optimum-neuron-cache

dacorvo HF staff commited on 2 days ago

Commit

01e1fe9

verified ·

1 Parent(s): 7191bac

Update inference-cache-config/mistral.json

Files changed (1) hide show

inference-cache-config/mistral.json CHANGED Viewed

@@ -76,7 +76,8 @@
       "batch_size": 1,
       "sequence_length": 4096,
       "num_cores": 12,
-      "auto_cast_type": "bf16"
     }
   ],
   "mistralai/Mistral-Small-Instruct-2409": [
@@ -84,7 +85,8 @@
       "batch_size": 4,
       "sequence_length": 4096,
       "num_cores": 12,
-      "auto_cast_type": "bf16"
     }
   ]
 }

       "batch_size": 1,
       "sequence_length": 4096,
       "num_cores": 12,
+      "auto_cast_type": "bf16",
+      "task": "text-generation"
     }
   ],
   "mistralai/Mistral-Small-Instruct-2409": [
       "batch_size": 4,
       "sequence_length": 4096,
       "num_cores": 12,
+      "auto_cast_type": "bf16",
+      "task": "text-generation"
     }
   ]
 }