Update app.py

app.py

@@ -39,10 +39,11 @@ retriever = vectordb.as_retriever()
 #)
 
 from transformers import pipeline
-from transformers import AutoTokenizer, BitsAndBytesConfig
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+
 
 READER_MODEL = "HuggingFaceH4/zephyr-7b-beta"
-bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16)
+bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=bfloat16)
 model = AutoModelForCausalLM.from_pretrained(READER_MODEL, quantization_config=bnb_config)
 tokenizer = AutoTokenizer.from_pretrained(READER_MODEL)