Update README.md
Browse files
README.md
CHANGED
@@ -189,9 +189,9 @@ apiVersion: serving.kserve.io/v1beta1
|
|
189 |
kind: InferenceService
|
190 |
metadata:
|
191 |
annotations:
|
192 |
-
openshift.io/display-name:
|
193 |
serving.kserve.io/deploymentMode: RawDeployment
|
194 |
-
name:
|
195 |
labels:
|
196 |
opendatahub.io/dashboard: 'true'
|
197 |
spec:
|
@@ -240,7 +240,7 @@ oc apply -f qwen-inferenceservice.yaml
|
|
240 |
curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
|
241 |
-H "Content-Type: application/json" \
|
242 |
-d '{
|
243 |
-
"model": "
|
244 |
"stream": true,
|
245 |
"stream_options": {
|
246 |
"include_usage": true
|
|
|
189 |
kind: InferenceService
|
190 |
metadata:
|
191 |
annotations:
|
192 |
+
openshift.io/display-name: mistral-small-3-1-24b-instruct-2503-quantized-w4a16 # OPTIONAL CHANGE
|
193 |
serving.kserve.io/deploymentMode: RawDeployment
|
194 |
+
name: mistral-small-3-1-24b-instruct-2503-quantized-w4a16 # specify model name. This value will be used to invoke the model in the payload
|
195 |
labels:
|
196 |
opendatahub.io/dashboard: 'true'
|
197 |
spec:
|
|
|
240 |
curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
|
241 |
-H "Content-Type: application/json" \
|
242 |
-d '{
|
243 |
+
"model": "mistral-small-3-1-24b-instruct-2503-quantized-w4a16",
|
244 |
"stream": true,
|
245 |
"stream_options": {
|
246 |
"include_usage": true
|