mindnlp0.4版本不支持保存和加载PeftModel的adapter weights为safetensors

[xing-yiren]

Describe the bug/ 问题描述 (Mandatory / 必填) A clear and concise description of what the bug is.

mindnlp0.4版本不支持保存和加载PeftModel的adapter weights为safetensors，仅能保存为ckpt，这个导致在训练过程中通过save_pretrained保存下来的adapter weights，在香橙派上通过PeftModel.from_pretrained进行加载时报错（_parse_ckpt_proto无法识别tensor_type，必须为Float16，然后香橙派上保存下来的tensor_dtype为mindspore.float16）

• Hardware Environment(Ascend/GPU/CPU) / 硬件环境:

Please delete the backend not involved / 请删除不涉及的后端: /device ascend

• Software Environment / 软件环境 (Mandatory / 必填): -- MindSpore version (e.g., 1.7.0.Bxxx) : 2.5.0 -- Python version (e.g., Python 3.7.5) : 3.9 -- OS platform and distribution (e.g., Linux Ubuntu 16.04): Ubuntu -- GCC/Compiler version (if compiled from source):

• Excute Mode / 执行模式 (Mandatory / 必填)(PyNative/Graph):

Please delete the mode not involved / 请删除不涉及的模式: /mode pynative

To Reproduce / 重现步骤 (Mandatory / 必填) Steps to reproduce the behavior:

model_id = "MindSpore-Lab/DeepSeek-R1-Distill-Qwen-1.5B"

base_model = AutoModelForCausalLM.from_pretrained("/home/HwHiAiUser/xing-yiren/DeepSeek_half", ms_dtype=mindspore.float16)
base_model.generation_config = GenerationConfig.from_pretrained("/home/HwHiAiUser/xing-yiren/DeepSeek_half")

base_model.generation_config.pad_token_id = base_model.generation_config.eos_token_id


config = LoraConfig(
    task_type=TaskType.CAUSAL_LM, 
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
    inference_mode=False, # 训练模式
    r=8, # Lora 秩
    lora_alpha=32, # Lora alaph，具体作用参见 Lora 原理
    lora_dropout=0.1# Dropout 比例
)

# 实例化LoRA模型
model = get_peft_model(base_model, config)

# 保存LoRA权重
model.save_pretrained(peft_model_path)

# 加载LoRA权重
model = PeftModel.from_pretrained(base_model, peft_model_path)

Expected behavior / 预期结果 (Mandatory / 必填) A clear and concise description of what you expected to happen.

将adapter保存为safetensors并成功加载

Screenshots/ 日志 / 截图 (Mandatory / 必填) If applicable, add screenshots to help explain your problem.

Additional context / 备注 (Optional / 选填) Add any other context about the problem here.