Issues about integrated inference

[mikecovlee]

Traceback

Traceback (most recent call last):
  File "/home/mikecovlee/work/multi-lora-fine-tune/mlora.py", line 175, in <module>
    inference(config, model, tokenizer)
  File "/home/mikecovlee/work/multi-lora-fine-tune/mlora.py", line 106, in inference
    input_data = mlora.MultiLoraBatchData(
TypeError: MultiLoraBatchData.__init__() got an unexpected keyword argument 'prompts_'

TODO

Improve inference functions. @mikecovlee