From c370d0795c8b166625486d1080eeff72201ce180 Mon Sep 17 00:00:00 2001 From: Wing Lian Date: Wed, 9 Jul 2025 14:52:44 -0400 Subject: [PATCH] [doc] Fix docs for text field mapping for completion datasets (#2890) * Fix docs for text field mapping for completion datasets * update another reference --- .runpod/src/config/config.yaml | 2 +- src/axolotl/utils/schemas/datasets.py | 13 ++++++------- 2 files changed, 7 insertions(+), 8 deletions(-) diff --git a/.runpod/src/config/config.yaml b/.runpod/src/config/config.yaml index 42c5978d5..2a89971fb 100644 --- a/.runpod/src/config/config.yaml +++ b/.runpod/src/config/config.yaml @@ -97,7 +97,7 @@ # # 'no_input_format' cannot include {input} # no_input_format: "{instruction} " -# # For `completion` datsets only, uses the provided field instead of `text` column +# # For `completion` datasets only, uses the provided field instead of `text` column # field: # # Axolotl attempts to save the dataset as an arrow after packing the data together so diff --git a/src/axolotl/utils/schemas/datasets.py b/src/axolotl/utils/schemas/datasets.py index db222ce1e..da8c545bc 100644 --- a/src/axolotl/utils/schemas/datasets.py +++ b/src/axolotl/utils/schemas/datasets.py @@ -34,12 +34,6 @@ class UserDefinedPrompterType(BaseModel): default=None, json_schema_extra={"description": "'no_input_format' cannot include {input}"}, ) - field: str | None = Field( - default=None, - json_schema_extra={ - "description": "For `completion` datsets only, uses the provided field instead of `text` column" - }, - ) class SFTDataset(BaseModel): @@ -104,7 +98,12 @@ class SFTDataset(BaseModel): default=None, json_schema_extra={"description": "defines the datatype when path is a file"}, ) - field: str | None = None + field: str | None = Field( + default=None, + json_schema_extra={ + "description": "For `completion` datasets only, uses the provided field instead of `text` column" + }, + ) field_human: str | None = None field_model: str | None = None field_messages: str | None = Field(