mirror of
https://github.com/oobabooga/textgen.git
synced 2026-07-25 20:30:52 -05:00
Instead of two separate paths (format files vs Chat Template), all instruction training now uses apply_chat_template() with assistant-only label masking. Users pick a Jinja2 template from the dropdown or use the model's built-in chat template — both work identically.