Update app.py

app.py

@@ -5,7 +5,7 @@ from typing import Iterator
 import gradio as gr
 import spaces
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer, LlamaTokenizerFast
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
 DESCRIPTION = """\
 # Llama 3.2 3B Instruct
@@ -22,7 +22,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
 model_id = "ehristoforu/HappyLlama1"
-tokenizer = LlamaTokenizerFast.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",