Update app.py

app.py

@@ -1,14 +1,14 @@
 import gradio as gr
 import subprocess
 
-MODEL_PATH = "/app/model/model.gguf"
+MODEL_PATH = "/app/model/qwen2.5-coder-1.5b-instruct-q4_k_m.gguf"
 
 def query_model(prompt):
     cmd = [
-        "/llama.cpp/main", "-m", MODEL_PATH,
-        "-t", "4",            # threads
+        "/llama.cpp/build/main", "-m", MODEL_PATH,
+        "-t", "4",              # threads
         "--prompt", prompt,
-        "--n_predict", "128"  # tokens to generate
+        "--n_predict", "256"    # increase tokens for coding
     ]
     result = subprocess.run(cmd, capture_output=True, text=True)
     return result.stdout
@@ -17,7 +17,7 @@ iface = gr.Interface(
     fn=query_model,
     inputs="text",
     outputs="text",
-    title="GGUF Docker Chatbot"
+    title="Qwen2.5-Coder GGUF Chatbot"
 )
 
 iface.launch(server_name="0.0.0.0", server_port=7860)