[bug] pissa init脚本报错

[letterk]

Reminder

• [X] I have read the README and searched the existing issues.

System Info

• llamafactory version: 0.8.3.dev0
• Platform: Linux-5.15.146.1-microsoft-standard-WSL2-x86_64-with-glibc2.35
• Python version: 3.11.9
• PyTorch version: 2.3.0+cu121 (GPU)
• Transformers version: 4.41.2
• Datasets version: 2.20.0
• Accelerate version: 0.31.0
• PEFT version: 0.11.1
• TRL version: 0.8.6
• GPU type: NVIDIA GeForce RTX 4060 Ti
• Bitsandbytes version: 0.43.1

Reproduction

python pissa_init.py ~/WORKDIR/hf/Qwen2-7B-Instruct ~/WORKDIR/saves/Qwen2-7B/pissa/sft -p 16 --lora_rank 32 --lora_target 'k_proj,o_proj,q_proj,v_proj,down_proj,gate_proj,up_proj'

Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
`low_cpu_mem_usage` was None, now set to True since model is quantized.
Traceback (most recent call last):
  File "/home/kissoul/WORKDIR/LLaMA-Factory/scripts/pissa_init.py", line 83, in <module>
    fire.Fire(quantize_pissa)
  File "/home/kissoul/miniconda3/envs/lf/lib/python3.11/site-packages/fire/core.py", line 143, in Fire
    component_trace = _Fire(component, args, parsed_flag_args, context, name)
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kissoul/miniconda3/envs/lf/lib/python3.11/site-packages/fire/core.py", line 477, in _Fire
    component, remaining_args = _CallAndUpdateTrace(
                                ^^^^^^^^^^^^^^^^^^^^
  File "/home/kissoul/miniconda3/envs/lf/lib/python3.11/site-packages/fire/core.py", line 693, in _CallAndUpdateTrace
    component = fn(*varargs, **kwargs)
                ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kissoul/WORKDIR/LLaMA-Factory/scripts/pissa_init.py", line 53, in quantize_pissa
    target_modules=[name.strip() for name in lora_target.split(",")],
                                             ^^^^^^^^^^^^^^^^^
AttributeError: 'tuple' object has no attribute 'split'

打印出来确实传递成元组了 lora_target value before function call: ('k_proj', 'o_proj', 'q_proj', 'v_proj', 'down_proj', 'gate_proj', 'up_proj'), type: <class 'tuple'>

Expected behavior

No response

Others

No response

[hiyouga]

--lora_target '"k_proj,o_proj,q_proj,v_proj,down_proj,gate_proj,up_proj"'