microsoft / microsoft/TransformerCompression

Convert Layernorm to RMSnorm

Open
#110 6 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
460
Forks
58
Avg merge
8h 40m
Merged PRs (30d)
1

Description

Hello, I have read your paper "SliceGPT: Compress Large Language Models by Deleting Rows and Columns". In section 3.2, I noticed that you convert LayerNorm into RMSNorm and merged two parts through linear projection. However, I would like to ask how the conversion process ensures that the output remains unchanged without any additional processing of the residual connections.

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

Start by reading section 3.2 of the SliceGPT paper and locating the repository's LayerNorm-to-RMSNorm conversion implementation. Trace how the linear projection and residual connections are handled, then document how output equivalence is maintained or identify what remains unexplained.

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.