Update README.md
Browse files
README.md
CHANGED
@@ -417,9 +417,9 @@ apiVersion: serving.kserve.io/v1beta1
|
|
417 |
kind: InferenceService
|
418 |
metadata:
|
419 |
annotations:
|
420 |
-
openshift.io/display-name:
|
421 |
serving.kserve.io/deploymentMode: RawDeployment
|
422 |
-
name:
|
423 |
labels:
|
424 |
opendatahub.io/dashboard: 'true'
|
425 |
spec:
|
@@ -468,7 +468,7 @@ oc apply -f qwen-inferenceservice.yaml
|
|
468 |
curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
|
469 |
-H "Content-Type: application/json" \
|
470 |
-d '{
|
471 |
-
"model": "
|
472 |
"stream": true,
|
473 |
"stream_options": {
|
474 |
"include_usage": true
|
|
|
417 |
kind: InferenceService
|
418 |
metadata:
|
419 |
annotations:
|
420 |
+
openshift.io/display-name: llama-3-1-8b-instruct # OPTIONAL CHANGE
|
421 |
serving.kserve.io/deploymentMode: RawDeployment
|
422 |
+
name: llama-3-1-8b-instruct # specify model name. This value will be used to invoke the model in the payload
|
423 |
labels:
|
424 |
opendatahub.io/dashboard: 'true'
|
425 |
spec:
|
|
|
468 |
curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
|
469 |
-H "Content-Type: application/json" \
|
470 |
-d '{
|
471 |
+
"model": "llama-3-1-8b-instruct",
|
472 |
"stream": true,
|
473 |
"stream_options": {
|
474 |
"include_usage": true
|