---
language:
- ko
license: other
license_name: tongyi-qianwen
---
### How to use

```python
prompt = '''너는 누구야?'''
messages = [
    {"role": "system", "content": "당신은 한국어 ai 모델입니다. 당신의 능력을 최대한 사용하여 답변해야 합니다."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt")

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=2048
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]