add quantization in qwen pipelines and relevant unittests

Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13499600

* add quant features

* resolve import

* resolve format

* fix save vocab

examples/pytorch/llm/llm_sft.py

@@ -13,9 +13,7 @@ cd modelscope
 pip install -r requirements.txt
 pip install .
 """
-
 import os
-# os.environ['CUDA_VISIBLE_DEVICES'] = '0,1'
 from dataclasses import dataclass, field
 from functools import partial
 from types import MethodType