Update README.md

README.md

@@ -56,7 +56,7 @@ encodeds = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
 model_inputs = encodeds.to('cuda')
 
 # Increase max_new_tokens if needed
-generated_ids = merged_model.generate(**model_inputs, max_new_tokens=1000, do_sample=False, pad_token_id=tokenizer.eos_token_id)
+generated_ids = model.generate(**model_inputs, max_new_tokens=1000, 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