RedHatAI
/

granite-3.1-8b-instruct-FP8-dynamic

Text Generation

compressed-tensors

Model card Files Files and versions

robgreenberg3 commited on 8 days ago

Commit

c450703

·

verified ·

1 Parent(s): 97ab42e

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -228,7 +228,7 @@ oc apply -f qwen-inferenceservice.yaml
 curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
         -H "Content-Type: application/json" \
         -d '{
-    "model": "Llama-4-Maverick-17B-128E-Instruct-FP8",
     "stream": true,
     "stream_options": {
         "include_usage": true

 curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
         -H "Content-Type: application/json" \
         -d '{
+    "model": "granite-3-1-8b-instruct-fp8-dynamic",
     "stream": true,
     "stream_options": {
         "include_usage": true