Bug in Paligemma usage docs for v4.50.3

[EricCousineau-TRI]

The following doc version has a minor bug in its usage:
https://github.com/huggingface/transformers/blob/v4.50.3/docs/source/en/model_doc/paligemma.md#single-image-inference
At the time of writing, this is the default version of the docs people come across via
https://huggingface.co/docs/transformers/en/model_doc/paligemma

This has bug where it's using the tokenized input length:

print(processor.decode(output[0], skip_special_tokens=True)[inputs.input_ids.shape[1]: ])

but it should actually be the text input length:

print(processor.decode(output[0], skip_special_tokens=True)[len(prompt): ])

Found this out by cross-referencing the HF spaces example:
https://huggingface.co/spaces/big-vision/paligemma-hf/blob/d914d44/app.py#L38

Note sure if it's worth patching the existing docs, having a new minor release, or just closing this out as a note for others.

[zucchini-nlp]

@EricCousineau-TRI feel free to open a PR. We won't do patch, but it will included be in the next release

[EricCousineau-TRI]

PR'd against 4.50 release branch: #37212

[EricCousineau-TRI]

The Paligemma docs changed a bit in #36469, hence targeting release branch.

If the patch isn't useful, I can close it out. Thanks!

[zucchini-nlp]

Ah oke. We are doing release tomorrow anyway, so no big difference :)

[EricCousineau-TRI]

Cool, I'll go ahead and close this issue + the PR. Thanks!