Add another model - make modesl selectable ? - What wind.surf will do ?

app.py

@@ -2,23 +2,52 @@ import gradio as gr
 from llama_cpp import Llama
 import requests
 
-llm = Llama.from_pretrained(
-    repo_id="lmstudio-community/Llama-3.2-3B-Instruct-GGUF",
-    filename="*Q4_K_M.gguf",
-    verbose=True,
-    n_ctx=32768,
-    n_threads=2,
-    chat_format="chatml"
-)
+# Define available models
+MODELS = {
+    "Llama-3.2-3B": {
+        "repo_id": "lmstudio-community/Llama-3.2-3B-Instruct-GGUF",
+        "filename": "*Q4_K_M.gguf"
+    },
+    "Llama-3.2-1.5B": {
+        "repo_id": "lmstudio-community/Llama-3.2-1.5B-Instruct-GGUF",
+        "filename": "*Q4_K_M.gguf"
+    }
+}
+
+# Initialize with default model
+current_model = None
+
+def load_model(model_name):
+    global current_model
+    model_info = MODELS[model_name]
+    current_model = Llama.from_pretrained(
+        repo_id=model_info["repo_id"],
+        filename=model_info["filename"],
+        verbose=True,
+        n_ctx=32768,
+        n_threads=2,
+        chat_format="chatml"
+    )
+    return current_model
+
+# Initialize with first model
+current_model = load_model(list(MODELS.keys())[0])
 
 def respond(
     message,
     history: list[tuple[str, str]],
+    model_name,
     system_message,
     max_tokens,
     temperature,
     top_p,
 ):
+    global current_model
+    
+    # Load new model if changed
+    if current_model is None or model_name != current_model.model_path:
+        current_model = load_model(model_name)
+    
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -30,7 +59,7 @@ def respond(
     messages.append({"role": "user", "content": message})
 
     response = ""
-    response = llm.create_chat_completion(
+    response = current_model.create_chat_completion(
             messages=messages,
             stream=True,
             max_tokens=max_tokens,
@@ -43,14 +72,21 @@ def respond(
             message_repl = message_repl + \
                 chunk['choices'][0]["delta"]["content"]
         yield message_repl
+
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
     respond,
     title="GGUF is popular format on PC in LM Studio or on Tablet/Mobile in PocketPal APPs",
-    description="Try models locclay in: 🖥️ [LM Studio AI for PC](https://lmstudio.ai) | 📱 PocketPal AI ([Android](https://play.google.com/store/apps/details?id=com.pocketpalai) & [iOS](https://play.google.com/store/apps/details?id=com.pocketpalai))",
+    description="Try models locclay in: 🖥️ [LM Studio AI for PC](https://lmstudio.ai) | 📱 PocketPal AI ([Android](https://play.google.com/store/apps/details?id=com.pocketpalai) & [iOS](https://play.google.com/store/apps/details?id=com.pocketpalai)) on Tablet or Mobile",
+   
     additional_inputs=[
+        gr.Dropdown(
+            choices=list(MODELS.keys()),
+            value=list(MODELS.keys())[0],
+            label="Select Model"
+        ),
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),