diff --git a/llama_stack/templates/meta-reference-gpu/run.yaml b/llama_stack/templates/meta-reference-gpu/run.yaml
index 0763d0c36..c19066664 100644
--- a/llama_stack/templates/meta-reference-gpu/run.yaml
+++ b/llama_stack/templates/meta-reference-gpu/run.yaml
@@ -16,7 +16,7 @@ providers:
   - provider_id: meta-reference-inference
     provider_type: inline::meta-reference
     config:
-      model: ${env.INFERENCE_MODEL} # please make sure your inference model here is added as resource
+      model: ${env.INFERENCE_MODEL}
       max_seq_len: 4096
       checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
   - provider_id: sentence-transformers
diff --git a/llama_stack/templates/meta-reference-quantized-gpu/run.yaml b/llama_stack/templates/meta-reference-quantized-gpu/run.yaml
index ea34d3424..550170a00 100644
--- a/llama_stack/templates/meta-reference-quantized-gpu/run.yaml
+++ b/llama_stack/templates/meta-reference-quantized-gpu/run.yaml
@@ -16,7 +16,7 @@ providers:
   - provider_id: meta-reference-inference
     provider_type: inline::meta-reference-quantized
     config:
-      model: ${env.INFERENCE_MODEL} # please make sure your inference model here is added as resource
+      model: ${env.INFERENCE_MODEL}
       max_seq_len: 4096
       checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
       quantization: