OptimalScale / OptimalScale/LMFlow
what's the difference between text_only and text2text data type?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.5k
- Forks
- 822
- PR merge metrics
- No merged PRs in 30d
Description
你们好，我自己有一份私有大模型，预训练的时候，输入和输出之间的分隔符是"[SEP]"，输出终止token是“<eod>”。现在我想借助lmflow进行微调。我注意到，数据格式只能是text_only 和text2text，请问text_only 和text2text 在使用上有什么区别？
我应该如何构造我的数据集，才能使用你们的微调和推理脚本呢？
比如，我的数据格式是：
问：能否帮我写一个python代码判断一个数字是否是偶数？答：is_even = lambda x: x % 2 == 0
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
No file or test is named. Review LMFlow's text_only and text2text dataset handling alongside the fine-tuning and inference scripts, including how the [SEP] delimiter and terminator fit the documented formats. Done means documenting the distinction and showing how to construct the example dataset.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100