Add streaming data pipeline and giant CLI entry point
- 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>
This commit is contained in:
@@ -10,6 +10,15 @@ resolution-markers = [
|
||||
"python_full_version < '3.14' and sys_platform != 'emscripten' and sys_platform != 'win32'",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "annotated-doc"
|
||||
version = "0.0.4"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/57/ba/046ceea27344560984e26a590f90bc7f4a75b06701f653222458922b558c/annotated_doc-0.0.4.tar.gz", hash = "sha256:fbcda96e87e9c92ad167c2e53839e57503ecfda18804ea28102353485033faa4", size = 7288, upload-time = "2025-11-10T22:07:42.062Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/1e/d3/26bf1008eb3d2daa8ef4cacc7f3bfdc11818d111f7e2d0201bc6e3b49d45/annotated_doc-0.0.4-py3-none-any.whl", hash = "sha256:571ac1dc6991c450b25a9c2d84a3705e2ae7a53467b5d111c24fa8baabbed320", size = 5303, upload-time = "2025-11-10T22:07:40.673Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "colorama"
|
||||
version = "0.4.6"
|
||||
@@ -112,6 +121,7 @@ dependencies = [
|
||||
{ name = "pandas" },
|
||||
{ name = "pyarrow" },
|
||||
{ name = "torch" },
|
||||
{ name = "typer" },
|
||||
]
|
||||
|
||||
[package.optional-dependencies]
|
||||
@@ -126,6 +136,7 @@ requires-dist = [
|
||||
{ name = "pyarrow", specifier = ">=16" },
|
||||
{ name = "pytest", marker = "extra == 'dev'", specifier = ">=8" },
|
||||
{ name = "torch", specifier = ">=2.3" },
|
||||
{ name = "typer", specifier = ">=0.12" },
|
||||
]
|
||||
provides-extras = ["dev"]
|
||||
|
||||
@@ -150,6 +161,18 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/62/a1/3d680cbfd5f4b8f15abc1d571870c5fc3e594bb582bc3b64ea099db13e56/jinja2-3.1.6-py3-none-any.whl", hash = "sha256:85ece4451f492d0c13c5dd7c13a64681a86afae63a5f347908daf103ce6d2f67", size = 134899, upload-time = "2025-03-05T20:05:00.369Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "markdown-it-py"
|
||||
version = "4.2.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "mdurl" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/06/ff/7841249c247aa650a76b9ee4bbaeae59370dc8bfd2f6c01f3630c35eb134/markdown_it_py-4.2.0.tar.gz", hash = "sha256:04a21681d6fbb623de53f6f364d352309d4094dd4194040a10fd51833e418d49", size = 82454, upload-time = "2026-05-07T12:08:28.36Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/b3/81/4da04ced5a082363ecfa159c010d200ecbd959ae410c10c0264a38cac0f5/markdown_it_py-4.2.0-py3-none-any.whl", hash = "sha256:9f7ebbcd14fe59494226453aed97c1070d83f8d24b6fc3a3bcf9a38092641c4a", size = 91687, upload-time = "2026-05-07T12:08:27.182Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "markupsafe"
|
||||
version = "3.0.3"
|
||||
@@ -213,6 +236,15 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/70/bc/6f1c2f612465f5fa89b95bead1f44dcb607670fd42891d8fdcd5d039f4f4/markupsafe-3.0.3-cp314-cp314t-win_arm64.whl", hash = "sha256:32001d6a8fc98c8cb5c947787c5d08b0a50663d139f1305bac5885d98d9b40fa", size = 14146, upload-time = "2025-09-27T18:37:28.327Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "mdurl"
|
||||
version = "0.1.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/d6/54/cfe61301667036ec958cb99bd3efefba235e65cdeb9c84d24a8293ba1d90/mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba", size = 8729, upload-time = "2022-08-14T12:40:10.846Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/b3/38/89ba8ad64ae25be8de66a6d463314cf1eb366222074cfda9ee839c56a4b4/mdurl-0.1.2-py3-none-any.whl", hash = "sha256:84008a41e51615a49fc9966191ff91509e3c40b939176e643fd50a5c2196b8f8", size = 9979, upload-time = "2022-08-14T12:40:09.779Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "mpmath"
|
||||
version = "1.3.0"
|
||||
@@ -594,6 +626,19 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/ec/57/56b9bcc3c9c6a792fcbaf139543cee77261f3651ca9da0c93f5c1221264b/python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427", size = 229892, upload-time = "2024-03-01T18:36:18.57Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rich"
|
||||
version = "15.0.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "markdown-it-py" },
|
||||
{ name = "pygments" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/c0/8f/0722ca900cc807c13a6a0c696dacf35430f72e0ec571c4275d2371fca3e9/rich-15.0.0.tar.gz", hash = "sha256:edd07a4824c6b40189fb7ac9bc4c52536e9780fbbfbddf6f1e2502c31b068c36", size = 230680, upload-time = "2026-04-12T08:24:00.75Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/82/3b/64d4899d73f91ba49a8c18a8ff3f0ea8f1c1d75481760df8c68ef5235bf5/rich-15.0.0-py3-none-any.whl", hash = "sha256:33bd4ef74232fb73fe9279a257718407f169c09b78a87ad3d296f548e27de0bb", size = 310654, upload-time = "2026-04-12T08:24:02.83Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "setuptools"
|
||||
version = "81.0.0"
|
||||
@@ -603,6 +648,15 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/e1/e3/c164c88b2e5ce7b24d667b9bd83589cf4f3520d97cad01534cd3c4f55fdb/setuptools-81.0.0-py3-none-any.whl", hash = "sha256:fdd925d5c5d9f62e4b74b30d6dd7828ce236fd6ed998a08d81de62ce5a6310d6", size = 1062021, upload-time = "2026-02-06T21:10:37.175Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "shellingham"
|
||||
version = "1.5.4"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/58/15/8b3609fd3830ef7b27b655beb4b4e9c62313a4e8da8c676e142cc210d58e/shellingham-1.5.4.tar.gz", hash = "sha256:8dbca0739d487e5bd35ab3ca4b36e11c4078f3a234bfce294b0a0291363404de", size = 10310, upload-time = "2023-10-24T04:13:40.426Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/e0/f9/0595336914c5619e5f28a1fb793285925a8cd4b432c9da0a987836c7f822/shellingham-1.5.4-py2.py3-none-any.whl", hash = "sha256:7ecfff8f2fd72616f7481040475a65b2bf8af90a56c89140852d1120324e8686", size = 9755, upload-time = "2023-10-24T04:13:38.866Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "six"
|
||||
version = "1.17.0"
|
||||
@@ -685,6 +739,21 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/c1/68/fa86e5a39608000f645535b2c124920126327ab731f8c4fafd5b07ff8d4b/triton-3.7.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ce061073102714b725f3660ec6939d94a1da7984b3aa99c921417cae273672f5", size = 201546766, upload-time = "2026-05-07T18:46:42.088Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "typer"
|
||||
version = "0.26.7"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "annotated-doc" },
|
||||
{ name = "colorama", marker = "sys_platform == 'win32'" },
|
||||
{ name = "rich" },
|
||||
{ name = "shellingham" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/5e/ed/ef06584ccdd5c410df0837951ecd7e15d9a6144ea1bd4c73cecab1a89891/typer-0.26.7.tar.gz", hash = "sha256:e314a34c617e419c091b2830dda3ea1f257134ff593061a8f5b9717ab8dddb3a", size = 201709, upload-time = "2026-06-03T07:18:06.843Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/24/25/2201973529af2c954de0bb725323c3aaed6d7f0ceee8f550dec9185df013/typer-0.26.7-py3-none-any.whl", hash = "sha256:5c87cfbc5d34491c5346ebf49c23e18d56ccb863268d3a8d592b26087c2f5e58", size = 122456, upload-time = "2026-06-03T07:18:05.732Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "typing-extensions"
|
||||
version = "4.15.0"
|
||||
|
||||
Reference in New Issue
Block a user