Add support for GLM-OCR model

[msluszniak]

Problem description

HF repository: https://huggingface.co/zai-org/GLM-OCR

Proposed solution

Classic support of a model via RNE.

Alternative solutions

Not applicable.

Benefits to React Native ExecuTorch

Great addition to RNE ecosystem. Provide much better results than currently available OCR.

Additional context

No response

[msluszniak]

This model turns out to be way too slow aka 5-10s per image. For now, we don't progress with it until something will change this performance.