dtflow 0.5.4__py3-none-any.whl → 0.5.5__py3-none-any.whl

dtflow/__init__.py

@@ -60,7 +60,7 @@ from .tokenizers import (
     token_stats,
 )
 
-__version__ = "0.5.4"
+__version__ = "0.5.5"
 
 __all__ = [
     # core

dtflow/__main__.py

@@ -60,7 +60,7 @@ def sample(
     filename: str = typer.Argument(..., help="输入文件路径"),
     num_arg: Optional[int] = typer.Argument(None, help="采样数量", metavar="NUM"),
     num: int = typer.Option(10, "--num", "-n", help="采样数量", show_default=True),
-    type: str = typer.Option("head", "--type", "-t", help="采样方式: random/head/tail"),
+    type: str = typer.Option("random", "--type", "-t", help="采样方式: random/head/tail"),
     output: Optional[str] = typer.Option(None, "--output", "-o", help="输出文件路径"),
     seed: Optional[int] = typer.Option(None, "--seed", help="随机种子"),
     by: Optional[str] = typer.Option(None, "--by", help="分层采样字段"),
@@ -223,9 +223,7 @@ def validate(
         None, "--preset", "-p", help="预设 Schema: openai_chat, alpaca, dpo, sharegpt"
     ),
     output: Optional[str] = typer.Option(None, "--output", "-o", help="输出有效数据的文件路径"),
-    filter: bool = typer.Option(
-        False, "--filter", "-f", help="过滤无效数据并保存"
-    ),
+    filter: bool = typer.Option(False, "--filter", "-f", help="过滤无效数据并保存"),
     max_errors: int = typer.Option(20, "--max-errors", help="最多显示的错误数量"),
     verbose: bool = typer.Option(False, "--verbose", "-v", help="显示详细信息"),
 ):

dtflow/cli/sample.py

@@ -20,7 +20,7 @@ from .common import (
 def sample(
     filename: str,
     num: int = 10,
-    type: Literal["random", "head", "tail"] = "head",
+    type: Literal["random", "head", "tail"] = "random",
     output: Optional[str] = None,
     seed: Optional[int] = None,
     by: Optional[str] = None,
@@ -37,7 +37,7 @@ def sample(
             - num > 0: 采样指定数量
             - num = 0: 采样所有数据
             - num < 0: Python 切片风格（如 -1 表示最后 1 条，-10 表示最后 10 条）
-        type: 采样方式，可选 random/head/tail，默认 head
+        type: 采样方式，可选 random/head/tail，默认 random
         output: 输出文件路径，不指定则打印到控制台
         seed: 随机种子（仅在 type=random 时有效）
         by: 分层采样字段名，按该字段的值分组采样

{dtflow-0.5.4.dist-info → dtflow-0.5.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dtflow
-Version: 0.5.4
+Version: 0.5.5
 Summary: A flexible data transformation tool for ML training formats (SFT, RLHF, Pretrain)
 Project-URL: Homepage, https://github.com/yourusername/DataTransformer
 Project-URL: Documentation, https://github.com/yourusername/DataTransformer#readme

{dtflow-0.5.4.dist-info → dtflow-0.5.5.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dtflow/__init__.py,sha256=yUwvKuVAmhDnp-1tYhZGlZcTdiEnZ3Jh-IJymgMIUhA,3031
-dtflow/__main__.py,sha256=ySpqvEn7k-vsrYFPx-8O6p-yx_24KccgnOSPd2XybhM,12572
+dtflow/__init__.py,sha256=6vE7u7NxILhzgsAoQzel0huISJhLLGgqVW2obUMz1xM,3031
+dtflow/__main__.py,sha256=htJk04NOEZbDoZILnwCMKjG--NPWuwv-2ZbFXlk7jjM,12558
 dtflow/converters.py,sha256=X3qeFD7FCOMnfiP3MicL5MXimOm4XUYBs5pczIkudU0,22331
 dtflow/core.py,sha256=qMo6B3LK--TWRK7ZBKObGcs3pKFnd0NPoaM0T8JC7Jw,38135
 dtflow/framework.py,sha256=jyICi_RWHjX7WfsXdSbWmP1SL7y1OWSPyd5G5Y-lvg4,17578
@@ -16,7 +16,7 @@ dtflow/cli/common.py,sha256=gCwnF5Sw2ploqfZJO_z3Ms9mR1HNT7Lj6ydHn0uVaIw,13817
 dtflow/cli/io_ops.py,sha256=BMDisP6dxzzmSjYwmeFwaHmpHHPqirmXAWeNTD-9MQM,13254
 dtflow/cli/lineage.py,sha256=_lNh35nF9AA0Zy6FyZ4g8IzrXH2ZQnp3inF-o2Hs1pw,1383
 dtflow/cli/pipeline.py,sha256=QNEo-BJlaC1CVnVeRZr7TwfuZYloJ4TebIzJ5ALzry0,1426
-dtflow/cli/sample.py,sha256=LRCkpFi9t0CI2QjRKADmvwWMdGfLriqdNkoFG6_wQkY,10497
+dtflow/cli/sample.py,sha256=y_yRG2vBr300HZD4MosHZ4uAYhiTSqDxVN-ZMWTURog,10501
 dtflow/cli/stats.py,sha256=u4ehCfgw1X8WuOyAjrApMRgcIO3BVmINbsTjxEscQro,24086
 dtflow/cli/transform.py,sha256=w6xqMOxPxQvL2u_BPCfpDHuPSC9gmcqMPVN8s-B6bbY,15052
 dtflow/cli/validate.py,sha256=65aGVlMS_Rq0Ch0YQ-TclVJ03RQP4CnG137wthzb8Ao,4384
@@ -31,7 +31,7 @@ dtflow/utils/__init__.py,sha256=Pn-ltwV04fBQmeZG7FxInDQmzH29LYOi90LgeLMEuQk,506
 dtflow/utils/display.py,sha256=OeOdTh6mbDwSkDWlmkjfpTjy2QG8ZUaYU0NpHUWkpEQ,5881
 dtflow/utils/field_path.py,sha256=K8nU196RxTSJ1OoieTWGcYOWl9KjGq2iSxCAkfjECuM,7621
 dtflow/utils/helpers.py,sha256=JXN176_B2pm53GLVyZ1wj3wrmBJG52Tkw6AMQSdj7M8,791
-dtflow-0.5.4.dist-info/METADATA,sha256=mQIIV3B-6VBOuNSRiPQjqOwdLTs6Nir6to1_FIER3d0,22544
-dtflow-0.5.4.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-dtflow-0.5.4.dist-info/entry_points.txt,sha256=dadIDOK7Iu9pMxnMPBfpb4aAPe4hQbBOshpQYjVYpGc,44
-dtflow-0.5.4.dist-info/RECORD,,
+dtflow-0.5.5.dist-info/METADATA,sha256=SzaIuZqLFK-Ncnim1NmBUs7bdnqIJiGtPikbnrM-gsA,22544
+dtflow-0.5.5.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+dtflow-0.5.5.dist-info/entry_points.txt,sha256=dadIDOK7Iu9pMxnMPBfpb4aAPe4hQbBOshpQYjVYpGc,44
+dtflow-0.5.5.dist-info/RECORD,,