diff --git a/charts/azimuth-chat/ci/ui-only-values.yaml b/charts/azimuth-chat/ci/ui-only-values.yaml
deleted file mode 100644
index b66347d..0000000
--- a/charts/azimuth-chat/ci/ui-only-values.yaml
+++ /dev/null
@@ -1,16 +0,0 @@
-azimuth-llm:
-  api:
-    enabled: false
-  ui:
-    service:
-      zenith:
-        enabled: false
-    appSettings:
-      # Verify that we can set non-standard LLM params
-      llm_params:
-        max_tokens: 101
-        temperature: 0.1
-        top_p: 0.15
-        top_k: 1
-        presence_penalty: 0.9
-        frequency_penalty: 1
diff --git a/charts/azimuth-llm/values.yaml b/charts/azimuth-llm/values.yaml
index 29879d4..cd483c1 100644
--- a/charts/azimuth-llm/values.yaml
+++ b/charts/azimuth-llm/values.yaml
@@ -56,8 +56,7 @@ api:
     hostPath:
       path: /tmp/llm/huggingface-cache
   # Number of gpus to requests for each api pod instance
-  # NOTE: This must be in the range 1 <= value <= N, where
-  # 'N' is the number of GPUs available in a single
+  # NOTE: This must be less than the number of GPUs available in a single
   # worker node on the target Kubernetes cluster.
   # NOTE: According to the vLLM docs found here
   # https://docs.vllm.ai/en/latest/serving/distributed_serving.html
diff --git a/web-apps/chat/defaults.yml b/web-apps/chat/defaults.yml
index b0260a9..b9ce61f 100644
--- a/web-apps/chat/defaults.yml
+++ b/web-apps/chat/defaults.yml
@@ -1,9 +1,3 @@
-
-# Default target is a local ollama instance
-# running inside the same docker network
-model_name: smollm2:135m
-backend_url: http://ollama:11434
-
 host_address: 0.0.0.0
 
 model_instruction: "You are a helpful and cheerful AI assistant. Please respond appropriately."