deepseek微调模型无法转换为rkllm

[jianfeng-xiyue]

我用unsloth 微调了1.5B模型，生成的文件目录如下图，

将export_deepseek_1.5b_rkllm.py中mdol_lora改为了新路径，ret = llm.load_huggingface(model=modelpath, model_lora = modelpath, device='cpu')但转换时报错。

ython3 export_deepseek_1.5b_rkllm.py 
INFO: rkllm-toolkit version: 1.1.4
The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
Unused kwargs: ['_load_in_4bit', '_load_in_8bit', 'quant_method']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.
ERROR: Catch exception when loading model: bitsandbytes
Load model failed!

[waydong]

你好，方便提供下除权重以外的配置文件吗？

[jianfeng-xiyue]

deep-1.5B.zip
请查收附件

你好，方便提供下除权重以外的配置文件吗？

[waydong]

请先确认下huggingface模型能通过如下接口正常推理哈，model = AutoModelForCausalLM.from_pretrained(modelpath, trust_remote_code=True)，这边测试都加载不起来。