Update app.py

app.py

@@ -13,8 +13,6 @@ import ollama
 # Model from run.sh
 AVAILABLE_MODELS = [
     'smollm2:360m-instruct-q5_K_M',
-    'hf.co/ggml-org/SmolLM3-3B-GGUF:Q4_K_M',
-    'hf.co/bartowski/nvidia_OpenReasoning-Nemotron-1.5B-GGUF:Q5_K_M',
     'hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M', # OK speed with CPU
     'hf.co/unsloth/gemma-3-4b-it-qat-GGUF:Q4_K_M', #Slow.
     'hf.co/bartowski/Qwen_Qwen3-1.7B-GGUF:Q5_K_M',
@@ -22,12 +20,17 @@ AVAILABLE_MODELS = [
     'granite3.3:2b'
 ]
 
+#---fail to run
+    #'hf.co/ggml-org/SmolLM3-3B-GGUF:Q4_K_M',
+    #'hf.co/bartowski/nvidia_OpenReasoning-Nemotron-1.5B-GGUF:Q5_K_M',
+
+
 # Default System Prompt
 DEFAULT_SYSTEM_PROMPT = "Answer everything in simple, smart, relevant and accurate style. No chatty!"
 
 # --- Gradio Interface ---
 with gr.Blocks(theme=gr.themes.Default(primary_hue="blue", secondary_hue="neutral")) as demo:
-    gr.Markdown(f"## LLM GGUF Chat with Ollama") # Changed title to be more generic
+    gr.Markdown(f"## Small Language Model (SLM) run with CPU") # Changed title to be more generic
     gr.Markdown(f"(Run-Location-As: `{check_ipinfo}`)")
     gr.Markdown("Chat with the model, customize its behavior with a system prompt, and toggle streaming output.")