diff --git a/config/manifests/inferencemodel.yaml b/config/manifests/inferencemodel.yaml index 94c36d845..12fb00b7d 100644 --- a/config/manifests/inferencemodel.yaml +++ b/config/manifests/inferencemodel.yaml @@ -10,3 +10,14 @@ spec: targetModels: - name: tweet-summary-1 weight: 100 + +--- +apiVersion: inference.networking.x-k8s.io/v1alpha2 +kind: InferenceModel +metadata: + name: inferencemodel-base-model +spec: + modelName: meta-llama/Llama-2-7b-hf + criticality: Critical + poolRef: + name: my-pool