Update README.md

README.md

@@ -54,12 +54,12 @@ model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_c
 
 # Load weights
 peft_name = "AIgroup-CVM-utokyohospital/Llama-2-70b-chat-4bit-japanese"
-model_peft = PeftModel.from_pretrained(
+model = PeftModel.from_pretrained(
     model, 
     peft_name, 
     device_map="auto"
 )
-model_peft.eval()
+model.eval()
 
 device = "cuda:0"
 
@@ -70,10 +70,6 @@ with torch.no_grad():
             temperature=0.0,
             repetition_penalty=1.00)
   print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-  outputs = model_peft.generate(**inputs,
-            temperature=0.0,
-            repetition_penalty=1.00)
-  print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
 ## Sample Responses