Update app.py

app.py

@@ -13,14 +13,14 @@ import ollama
 
 # Model from run.sh
 MODEL_ID_MAP = {
+    "(IBM)Granite3.3-2B": 'granite3.3:2b',
+    "(Meta)Llama3.2-3B-Instruct": 'hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M', # OK speed with CPU
     "(阿里千問)Qwen3-4B-Instruct-2507": 'hf.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF:Q4_K_M',
     #"(阿里千問)Qwen3-4B-Thinking-2507": 'hf.co/bartowski/Qwen_Qwen3-4B-Thinking-2507-GGUF:Q4_K_M',
-    "(HuggingFace)SmolLM2-360M": 'smollm2:360m-instruct-q5_K_M',
-    "(Meta)Llama3.2-3B-Instruct": 'hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M', # OK speed with CPU
     #"(Google)Gemma3n-e2b-it": 'gemma3n:e2b-it-q4_K_M',
-    "(IBM)Granite3.3-2B": 'granite3.3:2b',
     #"(Tencent)混元-1.8B-Instruct":'hf.co/bartowski/tencent_Hunyuan-1.8B-Instruct-GGUF:Q4_K_M',
-    #"(Tencent)混元-4B-Instruct": 'hf.co/bartowski/tencent_Hunyuan-4B-Instruct-GGUF:Q4_K_M'
+    #"(Tencent)混元-4B-Instruct": 'hf.co/bartowski/tencent_Hunyuan-4B-Instruct-GGUF:Q4_K_M',
+    "(HuggingFace)SmolLM2-360M": 'smollm2:360m-instruct-q5_K_M'
 }
 
 
@@ -32,7 +32,7 @@ DEFAULT_SYSTEM_PROMPT = """Answer everything in simple, smart, relevant and accu
 
 # --- Gradio Interface ---
 with gr.Blocks(theme=gr.themes.Default(primary_hue="blue", secondary_hue="neutral")) as demo:
-    gr.Markdown(f"## LLM/SLM running with CPU") # Changed title to be more generic
+    gr.Markdown(f"## HH demo: LLM/SLM chatbot running with CPU only.") # 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.")