kyegomez / kyegomez/Blockwise-Parallel-Transformer
Explanation on the residual connection part?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 51
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
Hi, thanks for the good work! In your paper you described the residual connection design as the figure above. I am wondering what is the reason of the residual connection of "Q_i" within the FFN and "Attention(Q_i, K, V ) + Q_i" outside the FFN? Is this borrowed from some other researches?
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
Use the residual-connection figure included in the issue and the paper's description as the starting points. Provide a clear explanation of the two Q_i residual paths and identify whether the design is borrowed from prior research, with supporting references.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100