This PR fixes SQ accuracy lost after #6729.

The problem was with the calculation of the vector's offset value (what is the offset value for an SQ vector? You can find it here: https://qdrant.tech/articles/scalar-quantization/).

This value is different between vector and query. For query (in Dot metric) it's

values.iter().cloned().sum::<f32>()
    * self.metadata.alpha
    * self.metadata.offset

For the vector it's

dim as f32 * offset * offset + values.iter().cloned().sum::<f32>()
    * self.metadata.alpha
    * self.metadata.offset

This PR fixes difference in query internal method. Test included.

All Submissions:

• Contributions should target the dev branch. Did you create your branch from dev?
• Have you followed the guidelines in our Contributing document?
• Have you checked to ensure there aren't other open Pull Requests for the same update/change?

New Feature Submissions:

1. Does your submission pass tests?
2. Have you formatted your code locally using cargo +nightly fmt --all command prior to submission?
3. Have you checked your code using cargo clippy --all --all-features command?

Changes to Core Features:

• Have you added an explanation of what your changes do and why you'd like us to include them?
• Have you written new tests for your core changes, as applicable?
• Have you successfully ran tests with your changes locally?