Update app.py

app.py

@@ -17,7 +17,7 @@ model_name = "unsloth.Q4_K_M.gguf"
 model_path = os.path.join(model_dir, model_name)
 
 hf_hub_download(
-    repo_id="vislupus/bulgarian-joke-master-gemma-2-2b-it-bnb-4bit-gguf",
+    repo_id="vislupus/bulgarian-joke-master-SmolLM2-135M-Instruct-bnb-4bit-gguf",
     filename=model_name,
     local_dir=model_dir
 )
@@ -36,32 +36,11 @@ def generate_response(prompt, temperature=0.7, top_p=1.0, max_tokens=256):
     except Exception as e:
         return f"Error generating response: {e}"
 
-with gr.Blocks() as demo:
-    gr.Markdown("# 🦙 Llama GGUF Model Chatbot")
-    gr.Markdown(description)
-
-    prompt_input = gr.Textbox(label="Your Prompt", placeholder="Type your message here...", lines=5)
-
-    with gr.Accordion("Advanced Settings", open=False):
-        temperature = gr.Slider(0.1, 2.0, value=0.7, step=0.1, label="Temperature")
-        top_p = gr.Slider(0.1, 1.0, value=1.0, step=0.01, label="Top-p")
-        max_tokens = gr.Slider(16, 512, value=256, step=16, label="Max Tokens")
-
-    response_output = gr.Textbox(label="Model Response", placeholder="The model's response will appear here...", lines=10)
-
-    generate_button = gr.Button("Generate Response")
-
-    generate_button.click(
+if __name__ == "__main__":
+    rag = gr.ChatInterface(
         generate_response,
-        inputs=[prompt_input, temperature, top_p, max_tokens],
-        outputs=[response_output]
+        title=title,
+        description=description,
     )
 
-if __name__ == "__main__":
-    demo.launch(share=True)
-
-    try:
-        if llm:
-            llm.close()
-    except Exception as e:
-        print(f"Error closing model: {e}")
+    rag.launch()