Add support for FLUX.2 Klein 9B and 4B in single_file_utils

[eliemichel]

What does this PR do?

It enables detection of FLUX.2 Klein models when loading transformers from single file, like in the following example:

import torch
from diffusers import Flux2KleinPipeline, Flux2Transformer2DModel, GGUFQuantizationConfig
dtype = torch.bfloat16

ckpt_path = "https://huggingface.co/unsloth/FLUX.2-klein-4B-GGUF/blob/main/flux-2-klein-4b-Q2_K.gguf"
transformer = Flux2Transformer2DModel.from_single_file(
    ckpt_path,
    quantization_config=GGUFQuantizationConfig(compute_dtype=dtype),
    torch_dtype=dtype,
)
pipe2 = Flux2KleinPipeline.from_pretrained(
    "black-forest-labs/FLUX.2-klein-4B",
    transformer=transformer,
    torch_dtype=dtype,
)
pipe2.enable_model_cpu_offload()

Before this PR, Klein models were detected as flux-2-dev, leading to wrong expected tensor sizes.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you read our philosophy doc (important for complex PRs)?
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

@sayakpaul @yiyixuxu @DN6

[vladmandic]

@yiyixuxu @sayakpaul @DN6 gentle ping?

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[DN6]

Thank you @eliemichel 👍🏽

[DN6]

@eliemichel Just checked against the unquantized versions of the Klein checkpoints and it looks like the proposed shape checks only work with GGUF checkpoints.

Proposed shape checks don't work with unquantized checkpoints.