e087a4a72b
The LLM was putting all columns in user_template (e.g. summarization dataset had both document AND summary as user input). Fixed by: - Reframed system message: explicitly states user=INPUT, assistant=OUTPUT - Added 4 concrete correct examples (summarization, NLI, translation, QA) showing exactly how to split columns - Added "NEVER put the output/target column in the user template" rule - Added sanity check: if assistant_template has no column placeholders, reject the result and fall back to simple classification |
||
|---|---|---|
| .. | ||
| assets | ||
| auth | ||
| core | ||
| loggers | ||
| models | ||
| plugins/data-designer-unstructured-seed | ||
| requirements | ||
| routes | ||
| state | ||
| tests | ||
| utils | ||
| colab.py | ||
| main.py | ||
| run.py | ||