feat(doc): document drop_system_message and clarify limitation (#2381) [skip ci]

This commit is contained in:
NanoCode012
2025-03-05 22:01:16 +07:00
committed by GitHub
parent 05dddfc41d
commit 9ed4f6b3aa

View File

@@ -163,6 +163,12 @@ datasets:
system: ["system"]
tool: ["tool"]
# Optional[bool]. Whether to drop the system turn from the dataset. Only works with chat_template.
# This does not drop the default system message from chat_template if it exists. If you wish to,
# we recommend using a custom jinja template with the default system message removed or
# adding a system turn with empty content.
drop_system_message:
# IMPORTANT: The following fields determine which parts of the conversation to train on.
# Priority order: message_field_training > message_field_training_detail > train_on_inputs or role in roles_to_train
# See examples at `docs/dataset-formats/conversation.qmd`
@@ -222,8 +228,8 @@ process_reward_model:
chat_template: tokenizer_default
# custom jinja template for chat template. This will be only used if chat_template is set to `jinja` or `null` (in which case chat_template is automatically set to `jinja`). Default is null.
chat_template_jinja: null
# Changes the default system message
default_system_message: You are a helpful assistant. Please give a long and detailed answer. # Currently only supports chatml.
# Changes the default system message. Currently only supports chatml.
default_system_message: You are a helpful assistant. Please give a long and detailed answer.
# Axolotl attempts to save the dataset as an arrow after packing the data together so
# subsequent training attempts load faster, relative path
dataset_prepared_path: data/last_run_prepared