Update app.py

app.py

@@ -1,16 +1,20 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import gradio as gr
 
 model_name = "microsoft/Phi-4-mini-instruct"
-model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Load model & tokenizer with optimizations
 tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
+
+# Create a pipeline for text generation (faster inference)
+chatbot = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=200)
 
 def chatbot_response(user_input):
-    inputs = tokenizer(user_input, return_tensors="pt")
-    output = model.generate(**inputs, max_length=200)
-    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    response = chatbot(user_input)[0]["generated_text"]
     return response
 
+# Gradio UI
 iface = gr.Interface(
     fn=chatbot_response,
     inputs="text",