ssgyejin/llama-3-Korean-Bllossom-8B-deobfuscation-KOTOX

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = "MLP-KTLim/llama-3-Korean-Bllossom-8B"
adapter = "ssgyejin/llama-3-Korean-Bllossom-8B-deobfuscation-KOTOX"

tokenizer = AutoTokenizer.from_pretrained(adapter, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base_model, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, adapter)  # LoRA 어댑터 결합
model.eval()

messages = [{"role": "user", "content": "여기에 난독화된 한국어 문장을 입력하세요"}]
inputs = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
out = model.generate(inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))