from transformers import GPTNeoForCausalLM, GPT2Tokenizer
model = GPTNeoForCausalLM.from_pretrained("EleutherAI/gpt-neo-1.3B")
tokenizer = GPT2Tokenizer.from_pretrained("EleutherAI/gpt-neo-1.3B")

prompt = "In a shocking finding, scientists discovered a herd of unicorns living in a remote, " \
...          "previously unexplored valley, in the Andes Mountains. Even more surprising to the " \
...          "researchers was the fact that the unicorns spoke perfect English."

input_ids = tokenizer(prompt, return_tensors="pt").input_ids

gen_tokens = model.generate(input_ids, do_sample=True, temperature=0.9, max_length=100,)
gen_text = tokenizer.batch_decode(gen_tokens)[0]