thu-ml / thu-ml/TurboDiffusion
关于merge的一些疑问
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 277
- Avg merge
- 2h 57m
- Merged PRs (30d)
- 2
Description
源代码中的merge操作是将稀疏和蒸馏分别的训练变化权重直接相加，这样做为什么能够work呢？为何不考虑分两阶段训练策略呢？
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
Start by locating the source-code merge operation that adds the sparse and distillation training changes, then trace how each set of weights is produced and applied. Compare that flow with the proposed two-stage training approach. The issue does not name files, tests, or a concrete change, so done would first require a maintainer decision on whether an implementation or only an explanation is wanted.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Refactor
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100