aigc-x/Qwen2.5-32B-novel-writting

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# 加载tokenizer
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-32B-Instruct", trust_remote_code=True)

# 加载基础模型
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct", trust_remote_code=True)

# 加载LoRA适配器
model = PeftModel.from_pretrained(base_model, "aigc-x/Qwen2.5-32B-novel-writting").merge_and_unload()

# 模型推理
prompt = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request."
messages = [
    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=4096
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]