model = InstructBlip的from_pretrained部分

[NaDongsfd]

Describe the bug/ 问题描述 (Mandatory / 必填)
A clear and concise description of what the bug is.
mindnlp/transformers/models/instructblip/processing_instructblip.py
由于 #@classmethod被注释，导致from_pretrained部分功能无法使用（cls被识别成需要输入的参数），

• Software Environment / 软件环境 (Mandatory / 必填):
  -- MindSpore version (e.g., 1.7.0.Bxxx) :2.4.1
  -- Python version (e.g., Python 3.7.5) :3.9
  -- OS platform and distribution (e.g., Linux Ubuntu 16.04):linux 86_64

To Reproduce / 重现步骤 (Mandatory / 必填)

1. 使用model = InstructBlipForConditionalGeneration.from_pretrained("Salesforce/instructblip-vicuna-7b")
   报错缺少参数“pretrained_model_name_or_path”
   定位到mindnlp/transformers/models/instructblip/processing_instructblip.py
   由于from_pretrained前 #@classmethod被注释，导致from_pretrained部分功能无法使用（cls被识别成需要输入的参数）
   取消注释的话，会缺参数qformer_tokenizer（没有继承这个参数）
   使用原注释代码qformer_tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path, subfolder="qformer_tokenizer")
   会报错

• Ascend Error Message:

---

EH9999: Inner Error!
rtStreamSynchronizeWithTimeout execute failed, reason=[aicore exception][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:53][THREAD:35095]
EH9999: 2025-01-23-20:26:37.502.940 synchronize stream failed, runtime result = 507015[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161][THREAD:35095]
TraceBack (most recent call last):
EH9999: Inner Error!未找到对应代号

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

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.

[lvyufeng]

fixed on 0.5