Update README.md

README.md

@@ -36,17 +36,17 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 
-# Load the merged model and tokenizer
-merged_model = AutoModelForCausalLM.from_pretrained("./model", torch_dtype=torch.float16, device_map="auto")
+
+model = AutoModelForCausalLM.from_pretrained("./model", torch_dtype=torch.float16, device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained("./model")
 ```
 
 
 ```python
 prompt = "Your_question_here"
-inputs = tokenizer(prompt, return_tensors="pt").to(merged_model.device)
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 max_new_tokens = 2000  # Set the maximum number of tokens in the response
-outputs = merged_model.generate(**inputs, max_new_tokens=max_new_tokens)
+outputs = model.generate(**inputs, max_new_tokens=max_new_tokens)
 response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 print(response)
 ```