Update app.py

app.py

@@ -1,12 +1,17 @@
+from llama_cpp import Llama
 import gradio as gr
-from llama_cpp import Llama  # if using llama.cpp via GGUF
 
-# Load quantized model
-model = Llama(model_path="qwen2.5-1.5B-q4.gguf")
+# Load your quantized GGUF model
+llm = Llama(model_path="/app/models/qwen2.5-1.5B-q4.gguf")
 
-def generate(prompt):
-    output = model(prompt, max_tokens=100)
-    return output['text']
+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"
+)
 
-demo = gr.Interface(fn=generate, inputs="text", outputs="text")
 demo.launch()