removed quantization optimization

app.py

@@ -9,8 +9,10 @@ class Assistant:
     def __init__(self):
         model_name = "ruslanmv/Medical-Llama3-8B"
         device_map = 'auto'
-        bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4",bnb_4bit_compute_dtype=torch.float16,)
-        self.model = AutoModelForCausalLM.from_pretrained( model_name,quantization_config=bnb_config, trust_remote_code=True,use_cache=False,device_map=device_map)
+        # bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4",bnb_4bit_compute_dtype=torch.float16,)
+        # self.model = AutoModelForCausalLM.from_pretrained( model_name,quantization_config=bnb_config, trust_remote_code=True,use_cache=False,device_map=device_map)
+        self.model = AutoModelForCausalLM.from_pretrained( model_name, trust_remote_code=True,use_cache=False,device_map=device_map)
+        
         self.tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
         self.tokenizer.pad_token = self.tokenizer.eos_token