qwen3-4b-20260206_1340-exp07-LR2e-6

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_id = "Qwen/Qwen3-4B-Instruct-2507"
lora_repo_id = "tmiyamoto/qwen3-4b-20260206_1340-exp07-LR2e-6"

tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id, torch_dtype="auto", device_map="auto", trust_remote_code=True
)
model = PeftModel.from_pretrained(base_model, lora_repo_id)

messages = [
    {"role": "user", "content": "次のテキストからJSON形式で情報を抽出してください: ..."}
]
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)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))