feat(doc): add split_thinking docs (#2613) [skip ci]

* feat(doc): add split_thinking docs

* fix: link config.qmd to conversation.qmd for split_thinking example

* update thinking => reasoning_content in messages format

---------

Co-authored-by: Wing Lian <wing@axolotl.ai>
This commit is contained in:
NanoCode012
2025-05-07 07:05:32 +07:00
committed by Wing Lian
parent fed5ca8254
commit 680dcc5a4d
2 changed files with 30 additions and 2 deletions

View File

@@ -184,8 +184,8 @@ datasets:
# adding a system turn with empty content.
drop_system_message:
# Optional[bool]. Whether to split the assistant turn based on a reasoning trace inside delimited tags
# defaults to False
# Optional[bool]. (for Qwen3 template only) Whether to split the assistant content based on a reasoning trace inside delimited tags
# See example at `docs/dataset-formats/conversation.qmd`
split_thinking:
# IMPORTANT: The following fields determine which parts of the conversation to train on.