Update app.py

app.py

@@ -1,17 +1,23 @@
 from llama_cpp import Llama
 import gradio as gr
 
-# Load your quantized GGUF model
-llm = Llama(model_path="/app/models/qwen2.5-1.5B-q4.gguf")
-
-def generate_text(prompt):
-    output = llm(prompt, max_tokens=200)
-    return output['choices'][0]['text']
-
-demo = gr.Interface(
-    fn=generate_text,
-    inputs=gr.Textbox(lines=2, placeholder="Type your prompt here..."),
-    outputs="text"
+model = Llama(
+    model_path="qwen2.5-1.5B-q4.gguf",
+    n_threads=4,
+    n_ctx=2048,
 )
 
-demo.launch()
+def chat(prompt):
+    out = model(
+        prompt,
+        max_tokens=256,
+        temperature=0.7,
+    )
+    return out["choices"][0]["text"]
+
+gr.Interface(
+    fn=chat,
+    inputs="text",
+    outputs="text",
+    title="Qwen2.5-1.5B Q4 Chatbot"
+).launch()