import transformers
import torch

model_id = "VIRNECT/llama-3-Korean-8B-r-v1"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

pipeline.model.eval()

PROMPT = '''You are a helpful AI assistant. Please answer the user's questions kindly. 당신은 유능한 AI 어시스턴트 입니다. 사용자의 질문에 대해 친절하게 답변해주세요.'''
instruction = "화학공학이 다른 공학 분야와 어떻게 다른가요?"

messages = [
    {"role": "system", "content": f"{PROMPT}"},
    {"role": "user", "content": f"{instruction}"}
]

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)

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

outputs = pipeline(
    prompt,
    max_new_tokens=2048,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9
)

print(outputs[0]["generated_text"][len(prompt):])

RichardErkhov/VIRNECT_-_llama-3-Korean-8B-r-v1-8bits

Original model description:

Python code with Pipeline

RichardErkhov/
VIRNECT_-_llama-3-Korean-8B-r-v1-8bits