aws-neuron
/

optimum-neuron-cache

dacorvo HF Staff commited on Sep 27, 2024

Commit

8ea3b57

verified ·

1 Parent(s): b27749d

Update inference-cache-config/mistral.json

Files changed (1) hide show

inference-cache-config/mistral.json CHANGED Viewed

@@ -71,7 +71,7 @@
       "auto_cast_type": "bf16"
     }
   ],
-  "mistralai/Mistral-Small-Instruct-v2409": [
     {
       "batch_size": 1,
       "sequence_length": 4096,
@@ -79,7 +79,7 @@
       "auto_cast_type": "bf16"
     }
   ],
-  "mistralai/Mistral-Small-Instruct-v2409": [
     {
       "batch_size": 4,
       "sequence_length": 4096,

       "auto_cast_type": "bf16"
     }
   ],
+  "mistralai/Mistral-Small-Instruct-2409": [
     {
       "batch_size": 1,
       "sequence_length": 4096,
       "auto_cast_type": "bf16"
     }
   ],
+  "mistralai/Mistral-Small-Instruct-2409": [
     {
       "batch_size": 4,
       "sequence_length": 4096,