Description
Describe the bug
What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程，最好有截图)
Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/swift/cli/pt.py", line 5, in
pt_main()
File "/usr/local/lib/python3.10/site-packages/swift/llm/train/pt.py", line 24, in pt_main
return SwiftPt(args).main()
File "/usr/local/lib/python3.10/site-packages/swift/llm/base.py", line 49, in main
result = self.run()
File "/usr/local/lib/python3.10/site-packages/swift/llm/train/sft.py", line 106, in run
self.model = self.prepare_model(self.args, self.model, template=self.template, train_dataset=train_dataset)
File "/usr/local/lib/python3.10/site-packages/swift/llm/train/tuner.py", line 363, in prepare_model
model = tuner.from_pretrained(model, args.resume_from_checkpoint, is_trainable=True, **kwargs)
File "/usr/local/lib/python3.10/site-packages/swift/tuners/base.py", line 926, in from_pretrained
return SwiftModel.from_pretrained(model, model_id, revision=revision, adapter_name=adapter_name, **kwargs)
File "/usr/local/lib/python3.10/site-packages/swift/tuners/base.py", line 350, in from_pretrained
raise ValueError('Mixed using with peft is not allowed now.')
ValueError: Mixed using with peft is not allowed now.
Your hardware and system info
Write your system info like CUDA version/system/GPU/torch version here(在这里给出硬件信息和系统信息，如CUDA版本，系统，GPU型号和torch版本等)
docker image：
modelscope -ubuntu22.04-cuda12.4.0-py310-torch2.6.0-vllm0.8.5.post1-modelscope1.27.1-swift3.5.3
Additional context
Add any other context about the problem here(在这里补充其他信息)
swift pt
--model /data/models/qwen2.5-3b
--train_type lora
--dataset './pt.jsonl'
--torch_dtype bfloat16
--num_train_epochs 5
--per_device_train_batch_size 12
--learning_rate 5e-5
--warmup_ratio 0.05
--split_dataset_ratio 0.2
--lora_rank 8
--lora_alpha 32
--use_chat_template false
--target_modules all-linear
--gradient_accumulation_steps 2
--eval_steps 100
--save_steps 100
--save_total_limit 5
--logging_steps 20
--max_length 2048
--output_dir ./output/qwen2.5-3b
--dataloader_num_workers 4
--model_author zfc
--model_name qwen2.5-3b-Lora
--dataset_num_proc 8
--resume_from_checkpoint ./output/qwen2.5-3b/v0-20250709-181326
--resume_only_model false
> "$LOG_FILE" 2>&1 &