---
base_model: beomi/Llama-3-Open-Ko-8B-Instruct-preview
library_name: peft
license: llama3
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Base Model : beomi/Llama-3-Open-Ko-8B-Instruct-preview

Dataset = Bingsu/ko_alpaca_data

## Model inference

prompt template
```python
alpaca_prompt = """아래는 질문 instruction 과 추가정보를 나타내는 input 입니다. 적절한 response를 생성해주세요.

### Instruction:
{instruction}

### Input:
{input}

### Response:
{response}"""
```

inference code
```python

def generate_response(prompt, model):
    prompt = alpaca_prompt.format(instruction=prompt, input="", response="")
    messages = [
        {"role": "system", "content": "친절한 챗봇으로서 상대방의 요청에 최대한 자세하고 친절하게 답하자. 모든 대답은 한국어(Korean)으로 대답해줘."},
        {"role": "user", "content": f"{prompt}"},
    ]

    input_ids = tokenizer.apply_chat_template(
        messages,
        add_generation_prompt=True,
        return_tensors="pt"
    ).to(model.device)

    terminators = [
        tokenizer.eos_token_id,
        tokenizer.convert_tokens_to_ids("<|eot_id|>")
    ]

    outputs = model.generate(
        input_ids,
        max_new_tokens=512,
        eos_token_id=terminators,
        do_sample=True,
        temperature=0.1,
        top_p=0.9,
    )

    response = outputs[0][input_ids.shape[-1]:]
    return tokenizer.decode(response, skip_special_tokens=True)


instruction = "금리가 오르면 물가가 어떻게 돼?"

generate_response(instruction, model)
```