Update app.py

app.py

@@ -6,15 +6,14 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 access_token = os.environ["GATED_ACCESS_TOKEN"]
 
-# specify how to quantize the model
 quantization_config = BitsAndBytesConfig(
         load_in_4bit=True,
         bnb_4bit_quant_type="nf4",
         bnb_4bit_compute_dtype="torch.float16",
 )
 
-model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-v0.1", quantization_config=True, device_map="auto")
-tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-v0.1")
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", quantization_config=True, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
 
 # Load the tokenizer and model
 #model_id = "mistralai/Mixtral-8x7B-v0.1"