[NPU] convert phi3 model met load tokenizer issue

[bopeng1234]

I am following https://docs.openvino.ai/2025/openvino-workflow-generative/inference-with-genai/inference-with-genai-on-npu.html to convert the phi3 model, my command

pip install  nncf==2.14.1 onnx==1.17.0 optimum-intel==1.21.0
pip install openvino==2025.0 openvino-tokenizers==2025.0 openvino-genai==2025.0
optimum-cli export openvino -m microsoft/Phi-3-mini-4k-instruct --weight-format int4 --sym --ratio 1.0 --group-size -1 ov_model\Phi-3-mini-4k-instruct-intel-opt-int4-sym-channelwised

when the quantization running, it shows warning Could not load tokenizer using specified model ID or path. OpenVINO tokenizer/detokenizer models won't be generated. Exception: Invalid version: '2025.0.0.0-476-2b2420220f9'

and after quantized, load the model with ov_genai.LLMPipeline(model_path, "CPU")

met issue:

  File "C:\Users\gta\Downloads\script\npu_workspace\official_npu_ov\run.py", line 6, in <module>
    pipe = ov_genai.LLMPipeline(model_path, "CPU")#, pipeline_config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Check 'ov_tokenizer || ov_detokenizer' failed at C:\Jenkins\workspace\private-ci\ie\build-windows-vs2022\b\repos\openvino.genai\src\cpp\src\tokenizer.cpp:196:
Neither tokenizer nor detokenzier models were provided

which step did I make a mistake?

[bopeng1234]

use 2024.6, the issue gone