kyegomez / kyegomez/Blockwise-Parallel-Transformer

Explanation on the residual connection part?

Open
#2 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
51
Forks
1
PR merge metrics
No merged PRs in 30d

Description

image

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

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.