请问有没有办法在您的checkpoint基础上fine-tune？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 5k
- Forks
- 499
- PR merge metrics
- No merged PRs in 30d
Description
我在您的展示网页上看到可以继续fine-tune，但直接从您给的checkpoint开始加入新的处理好的数据的话，似乎会遇到vocab_size大小对不上的问题，这个有什么解决方法吗？
另外，我看到您在代码里筛选了4/4拍的midi，由于我的数据集里有很多三拍子，可以注释掉之后正常训练吗？
麻烦您了！
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 checkpoint-loading and MIDI preprocessing code referenced in the issue. Check how vocab_size is derived for the provided checkpoint and new processed data, and inspect the 4/4 filtering condition. Done means documenting or implementing a supported fine-tuning path and establishing whether three-beat MIDI can train correctly.
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
- 15/100