StaticLLMPipeline: Enable chat test

[TolyaTalamanov]

No description provided.

[TolyaTalamanov]

Thanks!

[ilya-lavrenov]

https://github.com/openvinotoolkit/openvino.genai/actions/runs/11627421408/job/32383657944?pr=1117#step:9:870

[TolyaTalamanov]

Any idea why did this happen?

RuntimeError: Exception from src\inference\src\cpp\core.cpp:85:
Check 'util::directory_exists(path) || util::file_exists(path)' failed at src\frontends\common\src\frontend.cpp:117:
FrontEnd API failed with GeneralFailure:
ir: Could not open the file: "Qwen2-0.5B-Instruct\openvino_tokenizer.xml"

[Wovchena]

I don't have a solution to ir: Could not open the file: "Qwen2-0.5B-Instruct\openvino_tokenizer.xml"

[ilya-lavrenov]

it's not a model path, it's a model_id. E.g. from CI error we can see:

model_path = WindowsPath('Qwen2-0.5B-Instruct'), device = 'CPU'

which means model is not even converted by Optimum

In other places, it's used like:

    pipe = read_model(get_models_list()[0])[4]

where read model converts model and created pipe on to top it.

So, the question is - have you run tests locally? do they even magically pass?