Update README.md
Browse files
README.md
CHANGED
@@ -147,9 +147,9 @@ apiVersion: serving.kserve.io/v1beta1
|
|
147 |
kind: InferenceService
|
148 |
metadata:
|
149 |
annotations:
|
150 |
-
openshift.io/display-name:
|
151 |
serving.kserve.io/deploymentMode: RawDeployment
|
152 |
-
name:
|
153 |
labels:
|
154 |
opendatahub.io/dashboard: 'true'
|
155 |
spec:
|
@@ -198,7 +198,7 @@ oc apply -f qwen-inferenceservice.yaml
|
|
198 |
curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
|
199 |
-H "Content-Type: application/json" \
|
200 |
-d '{
|
201 |
-
"model": "
|
202 |
"stream": true,
|
203 |
"stream_options": {
|
204 |
"include_usage": true
|
|
|
147 |
kind: InferenceService
|
148 |
metadata:
|
149 |
annotations:
|
150 |
+
openshift.io/display-name: mistral-small-3-1-24b-instruct-2503 # OPTIONAL CHANGE
|
151 |
serving.kserve.io/deploymentMode: RawDeployment
|
152 |
+
name: mistral-small-3-1-24b-instruct-2503 # specify model name. This value will be used to invoke the model in the payload
|
153 |
labels:
|
154 |
opendatahub.io/dashboard: 'true'
|
155 |
spec:
|
|
|
198 |
curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
|
199 |
-H "Content-Type: application/json" \
|
200 |
-d '{
|
201 |
+
"model": "mistral-small-3-1-24b-instruct-2503",
|
202 |
"stream": true,
|
203 |
"stream_options": {
|
204 |
"include_usage": true
|