deepseek-ai / deepseek-ai/DeepSeek-Coder
What is the dataset format for fine-tuning the base model for code infilling purposes only (not instructions) ?
Open
- Dominant language
- Python
- Stars
- 24.3k
- Forks
- 2.9k
- PR merge metrics
- No merged PRs in 30d
Description
In the "How to Fine-tune DeepSeek-Coder" section, the format appears suitable for instruction code generation purposes. If I want to fine-tune it for **code infilling** purposes, what would be the data format for that?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.