Update app.py

app.py

@@ -9,12 +9,13 @@ access_token = os.environ["GATED_ACCESS_TOKEN"]
 # Load the tokenizer and model
 model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
 tokenizer = AutoTokenizer.from_pretrained(model_id, token=access_token)
-model = AutoModelForCausalLM.from_pretrained(model_id, token=access_token)
+model = AutoModelForCausalLM.from_pretrained(model_id, token=access_token, load_in_4bit=True)
+#model = AutoModelForCausalLM.from_pretrained(model_id, token=access_token)
 # Initialize the quantizer
-quantizer = bnb.GemmQuantizer(act_bits=8, weight_bits=8)
+#quantizer = bnb.GemmQuantizer(act_bits=8, weight_bits=8)
 
 # Quantize the model
-model = quantizer(model)
+#model = quantizer(model)
 
 # Function to generate text using the model
 def generate_text(prompt):