Update app.py

app.py

@@ -2,13 +2,12 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Load the model and tokenizer
+from transformers import AutoModel, AutoTokenizer
+
 model_name = "Braszczynski/Llama-3.2-3B-Instruct-bnb-4bit-460steps"
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    load_in_4bit=True,  # Ensure this matches your model's quantization
-    device_map="auto"   # Automatically allocate model layers to GPUs
-)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name)
+
 
 def respond(
     message,