RedHatAI
/

whisper-large-v3-turbo-quantized.w4a16

Automatic Speech Recognition

compressed-tensors

text-generation-inference

Model card Files Files and versions

robgreenberg3 commited on Oct 13

Commit

7342059

·

verified ·

1 Parent(s): 8eefd46

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -181,7 +181,7 @@ spec:
           memory: 4Gi
           nvidia.com/gpu: '1'
       runtime: vllm-cuda-runtime	# must match the ServingRuntime name above
-      storageUri: registry.redhat.io/rhelai1/modelcar-whisper-large-v3-turbo-quantized-w4a16:1.5
     tolerations:
     - effect: NoSchedule
       key: nvidia.com/gpu

           memory: 4Gi
           nvidia.com/gpu: '1'
       runtime: vllm-cuda-runtime	# must match the ServingRuntime name above
+      storageUri: oci://registry.redhat.io/rhelai1/modelcar-whisper-large-v3-turbo-quantized-w4a16:1.5
     tolerations:
     - effect: NoSchedule
       key: nvidia.com/gpu