Update README.md

README.md

@@ -65,12 +65,12 @@ prompt = prompt_template
 encodeds = tokenizer(prompt, return_tensors="pt", add_special_tokens=True).input_ids
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-merged_model.to(device)
+model.to(device)
 inputs = encodeds.to(device)
 
 
 # Increase max_new_tokens if needed
-generated_ids = merged_model.generate(inputs, max_new_tokens=250, do_sample=False, pad_token_id=tokenizer.eos_token_id)
+generated_ids = model.generate(inputs, max_new_tokens=250, do_sample=False, pad_token_id=tokenizer.eos_token_id)
 ans = ''
 for i in tokenizer.decode(generated_ids[0], skip_special_tokens=True).split('<end_of_turn>')[:2]:
     ans += i