from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jinn33/kanana-1.5-8b-rlhf")
model = AutoModelForCausalLM.from_pretrained("jinn33/kanana-1.5-8b-rlhf")

prompt = "### 질문: 안녕하세요\n\n### 답변:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))