modelscope / modelscope/ms-swift
自定义模型最佳实践
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
Describe the feature
Please describe the feature requested here(请在这里描述需求)
希望能够看到如下最佳实践：
- 自定义一个文本模型且sft，例如为模型增加一个linear层
- 自定义一个多模态模型（魔改vit和魔改llm部分）且sft
多谢～
Paste any useful information
Paste any useful information, including papers, github links, etc.(请在这里描述其他有用的信息，比如相关的论文地址，github链接等)
Additional context
Add any other context or information here(其他信息可以写在这里)
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
The issue requests best-practice examples for custom text and multimodal models with SFT, but mentions no files, tests, or entry points. First clarify the expected scope and examples, then identify the existing model-customization and SFT documentation or examples to extend. Done should include usable guidance for both requested scenarios.
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
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100