modelscope / modelscope/ms-swift
基于sft后的lora进行gkd蒸馏
Open
Nobody has claimed this yet.
enhancement
stale
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
目前是否支持基于sft后的lora进行gkd蒸馏
Contributor guide
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 repository's GKD distillation entry point and the SFT/LoRA training and checkpoint-loading paths. Determine whether an SFT-produced LoRA can be used as the distillation input, then define support with a reproducible example or test and clear documentation of the result.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100