Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
600
dacorvo HF Staff commited on
Commit
01e1fe9
·
verified ·
1 Parent(s): 7191bac

Update inference-cache-config/mistral.json

Browse files
Files changed (1) hide show
  1. inference-cache-config/mistral.json +4 -2
inference-cache-config/mistral.json CHANGED
@@ -76,7 +76,8 @@
76
  "batch_size": 1,
77
  "sequence_length": 4096,
78
  "num_cores": 12,
79
- "auto_cast_type": "bf16"
 
80
  }
81
  ],
82
  "mistralai/Mistral-Small-Instruct-2409": [
@@ -84,7 +85,8 @@
84
  "batch_size": 4,
85
  "sequence_length": 4096,
86
  "num_cores": 12,
87
- "auto_cast_type": "bf16"
 
88
  }
89
  ]
90
  }
 
76
  "batch_size": 1,
77
  "sequence_length": 4096,
78
  "num_cores": 12,
79
+ "auto_cast_type": "bf16",
80
+ "task": "text-generation"
81
  }
82
  ],
83
  "mistralai/Mistral-Small-Instruct-2409": [
 
85
  "batch_size": 4,
86
  "sequence_length": 4096,
87
  "num_cores": 12,
88
+ "auto_cast_type": "bf16",
89
+ "task": "text-generation"
90
  }
91
  ]
92
  }