Update app.py

app.py

@@ -1,13 +1,12 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
+import torch
 from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM-135M-Instruct")
-
+model_name = 'HuggingFaceTB/SmolLM-135M-Instruct'
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
 
 def respond(
     message,