[UNet_Spatio_Temporal_Condition] fix default num_attention_heads in unet_spatio_temporal_condition

[Wang-Xiaodong1899]

What does this PR do?

Since UNet_Spatio_Temporal_Condition file was designed for Stable Video Diffusion, the default parameter num_attention_heads should be [5, 10, 20, 20] as the SVD config shows. If people initialize the UNetSpatioTemporalConditionModel class by self.__init__() rather than loading by load_pretrained(config) using pretrained config file, they can not realize that they have initialized the different Attention Head, and also there is no warning or error when load pretrained weights into different Attention Head, causing the wrong attention output.

We should avoid the situation that will cause the wrong attention output. This PR does that.

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.

[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]

Good catch 👍🏽

[sayakpaul]

@DN6 good to merge?