aigc-apps / aigc-apps/VideoX-Fun
A question about the normalization approach in self-attention
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.3k
- Forks
- 188
- Avg merge
- 2d 22h
- Merged PRs (30d)
- 3
Description
In self-attention, are norm_q and norm_k specifically designed to perform normalization along the dim dimension? I’ve seen more cases where normalization is done along the head_dim dimension.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Begin by locating the self-attention implementation and the definitions or uses of norm_q and norm_k. Compare their normalization axis with head_dim, then use the findings to provide a documented answer or clarify the intended behavior in the issue.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100