qwen2.5-7b-construction-translation-ko-lora

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct", torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, "madokalif/qwen2.5-7b-construction-translation-ko-lora")

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")

messages = [
    {"role": "system", "content": "다음 건설장비 클레임 정보를 한국어로 번역하세요."},
    {"role": "user", "content": "결함 원인: Poor material / 현상: LEAK(OIL) in HYDRAULIC/ATTACHMENT..."}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.3, top_p=0.9, do_sample=True)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))