diff --git a/README.md b/README.md index 2c38968e7..72ffd0954 100644 --- a/README.md +++ b/README.md @@ -50,7 +50,7 @@ kind: Workspace metadata: name: workspace-phi-3-5-mini resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC6s_v3" labelSelector: matchLabels: apps: phi-3-5 @@ -66,7 +66,7 @@ The workspace status can be tracked by running the following command. When the W ```sh $ kubectl get workspace workspace-phi-3-5-mini NAME INSTANCE RESOURCEREADY INFERENCEREADY JOBSTARTED WORKSPACESUCCEEDED AGE -workspace-phi-3-5-mini Standard_NC12s_v3 True True True 4h15m +workspace-phi-3-5-mini Standard_NC6s_v3 True True True 4h15m ``` Next, one can find the inference service's cluster ip and use a temporal `curl` pod to test the service endpoint in the cluster. diff --git a/examples/inference/kaito_workspace_phi_3.5-instruct.yaml b/examples/inference/kaito_workspace_phi_3.5-instruct.yaml index 294f89819..4c2497fe3 100644 --- a/examples/inference/kaito_workspace_phi_3.5-instruct.yaml +++ b/examples/inference/kaito_workspace_phi_3.5-instruct.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-phi-3-5-mini resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC6s_v3" labelSelector: matchLabels: apps: phi-3-5