Fixes # (issue)

RuntimeError: Error(s) in loading state_dict for LongCatAudioDiTTransformer:
        size mismatch for blocks.0.ffn.ff.0.weight: copying a param with shape torch.Size([9216, 2560]) from checkpoint, the shape in current model is torch.Size([10240, 2560]).

Root cause:
The ff_mult parameter was hardcoded to 4.0 in the transformer but the LongCat-AudioDiT-3.5B checkpoint uses ff_mult=3.6, causing FFN weight shape mismatch (9216 vs 10240).

Now reads dit_ff_mult from config.json, enabling conversion of models with non-default ff_mult (e.g., 3.5B model uses 3.6).

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?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.