Update README.md

examples/aws/llm/README.md

@@ -43,15 +43,15 @@ Create an instance YAML file with your desired configuration:
 apiVersion: kro.run/v1alpha1
 kind: OllamaDeployment
 metadata:
-  name: deepseek
+  name: phi
 spec:
-  name: deepseek         
+  name: phi         
   namespace: default
   values:
     storage: 50Gi        # Storage for model files
     model:
-      name: deepseek-r1  # Model name
-      size: 1.5b         # Model size variant
+      name: phi  # Model name
+      size: 2.7b         # Model size variant
     resources:
       requests:
         cpu: "2"
@@ -87,7 +87,7 @@ Access the model within the cluster using:
 curl http://<name>.<namespace>.svc.cluster.local/v1/completions \
   -H 'Content-Type: application/json' \
   -d '{ 
-    "model": "deepseek-r1:1.5b",
+    "model": "phi:2.7b",
     "prompt": "Hello, who are you?"
   }'
 ```
@@ -98,7 +98,7 @@ The service will be available at:
 curl http://<ALB-ADDRESS>/<name>/v1/completions \
   -H 'Content-Type: application/json' \
   -d '{ 
-    "model": "deepseek-r1:1.5b",
+    "model": "phi:2.7b",
     "prompt": "Hello, who are you?"
   }'
 ```
@@ -113,4 +113,4 @@ curl http://<ALB-ADDRESS>/<name>/v1/completions \
 ### Scaling Considerations
 - Increase storage for larger models
 - Adjust CPU/Memory based on load
-- Add GPUs for better inference performance
+- Add GPUs for better inference performance