from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("npvinHnivqn/phi-1_5-NRL", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("npvinHnivqn/phi-1_5-NRL", trust_remote_code=True)

inputs = tokenizer('''<|USER|> Write a paragragh about animal''', return_tensors="pt", return_attention_mask=False)

outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)