TypeError: dynamically_import_QuantLinear() got an unexpected keyword argument 'disable_exllamav2

hi，我在微调 qwen-vl-Chat-Int4的时候遇到了类似的问题。目前已经改了device_map，关闭了fp16，但是我有另外一个问题，不知道你是否遇到过呢？

device_map2:{'': 0}

Traceback (most recent call last):
  File "/data/zjj/Qwen/Qwen-VL/finetune.py", line 386, in <module>
    train()
  File "/data/zjj/Qwen/Qwen-VL/finetune.py", line 306, in train
    model = transformers.AutoModelForCausalLM.from_pretrained(
  File "/home/wz/anaconda3/envs/zjj_qwen/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 511, in from_pretrained
    return model_class.from_pretrained(
  File "/home/wz/anaconda3/envs/zjj_qwen/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2945, in from_pretrained
    model = quantizer.convert_model(model)
  File "/home/wz/anaconda3/envs/zjj_qwen/lib/python3.10/site-packages/optimum/gptq/quantizer.py", line 201, in convert_model
    self._replace_by_quant_layers(model, layers_to_be_replaced)
  File "/home/wz/anaconda3/envs/zjj_qwen/lib/python3.10/site-packages/optimum/gptq/quantizer.py", line 229, in _replace_by_quant_layers
    QuantLinear = dynamically_import_QuantLinear(
TypeError: dynamically_import_QuantLinear() got an unexpected keyword argument 'disable_exllamav2'

TypeError: dynamically_import_QuantLinear() got an unexpected keyword argument 'disable_exllamav2'

方便的话，可以提供一下optimum和transformers库的版本吗？谢谢～

Mingrui-Li / Qwen-VL-Lora-Model

TypeError: dynamically_import_QuantLinear() got an unexpected keyword argument 'disable_exllamav2 #2