lars
93c4d6b74d
- Streaming pipeline: row-group-level parquet reading (PyArrow) so large files never fully land in RAM; Welford online algorithm for normalizer fitting; StreamingStepsDataset with shuffle buffer and multi-worker file striping; event-ID scan and vocab scan via cheap single-column reads - giant/cli.py: typer-based CLI with `giant train` subcommand, mirroring scripts/train.py; --shuffle-buffer flag for RAM control - pyproject.toml: add typer>=0.12 dependency and giant entry point - train.py: replace len(loader.dataset) with local counters (compatible with IterableDataset which has no __len__) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
29 lines
514 B
TOML
29 lines
514 B
TOML
[project]
|
|
name = "giant"
|
|
version = "0.1.0"
|
|
description = "Geant4 step-function surrogate via conditional flow matching"
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"torch>=2.3",
|
|
"numpy>=1.26",
|
|
"pandas>=2.2",
|
|
"pyarrow>=16",
|
|
"typer>=0.12",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=8",
|
|
]
|
|
|
|
[project.scripts]
|
|
giant = "giant.cli:app"
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["giant"]
|