Update README.md

README.md

@@ -37,22 +37,20 @@ lora_r = 8
 
 ```python
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-from peft import PeftModel,PeftConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 
-finetune_model_path="stuser2023/Llama2-7b-finetuned"  
-config = PeftConfig.from_pretrained(finetune_model_path)
+model_name = "stuser2023/Llama2-7b-finetuned"
+
+quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 
 model = AutoModelForCausalLM.from_pretrained(
-    config.base_model_name_or_path,
-    load_in_8bit=True,
+    model_name,
+    quantization_config=quantization_config,
     device_map={'': 0},  # 設定使用的設備，此處指定為 GPU 0
     trust_remote_code=True,
 )
 model.config.use_cache = False
-
-model = PeftModel.from_pretrained(model, finetune_model_path, device_map={"": 0})
-model =model.eval()
+model=model.eval() #把Dropout功能關掉
 ```
 
 **3.進行推論(文字生成)**