instructlab-training 0.0.2__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- instructlab_training-0.0.2/.github/dependabot.yml +21 -0
- instructlab_training-0.0.2/.github/workflows/actionlint.dockerfile +3 -0
- instructlab_training-0.0.2/.github/workflows/actionlint.yml +48 -0
- instructlab_training-0.0.2/.github/workflows/docs.yml +46 -0
- instructlab_training-0.0.2/.github/workflows/lint.yml +76 -0
- instructlab_training-0.0.2/.github/workflows/matchers/actionlint.json +17 -0
- instructlab_training-0.0.2/.github/workflows/matchers/pylint.json +32 -0
- instructlab_training-0.0.2/.github/workflows/pypi.yaml +131 -0
- instructlab_training-0.0.2/.github/workflows/spellcheck.yml +45 -0
- instructlab_training-0.0.2/.gitignore +173 -0
- instructlab_training-0.0.2/.isort.cfg +10 -0
- instructlab_training-0.0.2/.markdownlint-cli2.yaml +16 -0
- instructlab_training-0.0.2/.pre-commit-config.yaml +16 -0
- instructlab_training-0.0.2/.pylintrc +675 -0
- instructlab_training-0.0.2/.spellcheck-en-custom.txt +20 -0
- instructlab_training-0.0.2/.spellcheck.yml +28 -0
- instructlab_training-0.0.2/LICENSE +201 -0
- instructlab_training-0.0.2/Makefile +56 -0
- instructlab_training-0.0.2/PKG-INFO +280 -0
- instructlab_training-0.0.2/README.md +238 -0
- instructlab_training-0.0.2/pyproject.toml +104 -0
- instructlab_training-0.0.2/requirements-cuda.txt +1 -0
- instructlab_training-0.0.2/requirements-dev.txt +8 -0
- instructlab_training-0.0.2/requirements.txt +19 -0
- instructlab_training-0.0.2/sample-data/train_all_pruned_SDG.jsonl +24545 -0
- instructlab_training-0.0.2/scripts/ruff.sh +54 -0
- instructlab_training-0.0.2/setup.cfg +4 -0
- instructlab_training-0.0.2/src/instructlab/__init__.py +1 -0
- instructlab_training-0.0.2/src/instructlab/training/__init__.py +11 -0
- instructlab_training-0.0.2/src/instructlab/training/_version.py +16 -0
- instructlab_training-0.0.2/src/instructlab/training/async_logger.py +54 -0
- instructlab_training-0.0.2/src/instructlab/training/chat_templates/ibm_generic_tmpl.py +24 -0
- instructlab_training-0.0.2/src/instructlab/training/chat_templates/mistral_tmpl.py +22 -0
- instructlab_training-0.0.2/src/instructlab/training/config.py +142 -0
- instructlab_training-0.0.2/src/instructlab/training/data_process.py +326 -0
- instructlab_training-0.0.2/src/instructlab/training/ilab_to_sdg.py +59 -0
- instructlab_training-0.0.2/src/instructlab/training/main_ds.py +722 -0
- instructlab_training-0.0.2/src/instructlab/training/multipack_sampler.py +478 -0
- instructlab_training-0.0.2/src/instructlab/training/token_dataset.py +112 -0
- instructlab_training-0.0.2/src/instructlab/training/tokenizer_utils.py +57 -0
- instructlab_training-0.0.2/src/instructlab/training/utils.py +683 -0
- instructlab_training-0.0.2/src/instructlab_training.egg-info/PKG-INFO +280 -0
- instructlab_training-0.0.2/src/instructlab_training.egg-info/SOURCES.txt +45 -0
- instructlab_training-0.0.2/src/instructlab_training.egg-info/dependency_links.txt +1 -0
- instructlab_training-0.0.2/src/instructlab_training.egg-info/requires.txt +18 -0
- instructlab_training-0.0.2/src/instructlab_training.egg-info/top_level.txt +1 -0
- instructlab_training-0.0.2/tox.ini +63 -0
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
|
|
3
|
+
# GitHub Dependabot configuration file
|
|
4
|
+
version: 2
|
|
5
|
+
updates:
|
|
6
|
+
|
|
7
|
+
# Maintain dependencies for GitHub Actions
|
|
8
|
+
- package-ecosystem: "github-actions"
|
|
9
|
+
directory: "/"
|
|
10
|
+
schedule:
|
|
11
|
+
interval: "daily"
|
|
12
|
+
- package-ecosystem: "docker"
|
|
13
|
+
directory: "/.github/workflows"
|
|
14
|
+
schedule:
|
|
15
|
+
interval: "daily"
|
|
16
|
+
|
|
17
|
+
# Maintain dependencies for Python scripts
|
|
18
|
+
- package-ecosystem: "pip"
|
|
19
|
+
directory: "/"
|
|
20
|
+
schedule:
|
|
21
|
+
interval: "daily"
|
|
@@ -0,0 +1,48 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
|
|
3
|
+
name: Lint GitHub Actions workflows
|
|
4
|
+
on:
|
|
5
|
+
push:
|
|
6
|
+
branches:
|
|
7
|
+
- "main"
|
|
8
|
+
paths:
|
|
9
|
+
- '.github/workflows/*.ya?ml'
|
|
10
|
+
- '.github/workflows/actionlint.*' # This workflow
|
|
11
|
+
pull_request:
|
|
12
|
+
branches:
|
|
13
|
+
- "main"
|
|
14
|
+
paths:
|
|
15
|
+
- '.github/workflows/*.ya?ml'
|
|
16
|
+
- '.github/workflows/actionlint.*' # This workflow
|
|
17
|
+
|
|
18
|
+
env:
|
|
19
|
+
LC_ALL: en_US.UTF-8
|
|
20
|
+
|
|
21
|
+
defaults:
|
|
22
|
+
run:
|
|
23
|
+
shell: bash
|
|
24
|
+
|
|
25
|
+
permissions:
|
|
26
|
+
contents: read
|
|
27
|
+
|
|
28
|
+
jobs:
|
|
29
|
+
actionlint:
|
|
30
|
+
runs-on: ubuntu-latest
|
|
31
|
+
steps:
|
|
32
|
+
- name: "Harden Runner"
|
|
33
|
+
uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
|
|
34
|
+
with:
|
|
35
|
+
egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
|
|
36
|
+
|
|
37
|
+
- name: "Checkout"
|
|
38
|
+
uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
|
|
39
|
+
with:
|
|
40
|
+
fetch-depth: 0
|
|
41
|
+
|
|
42
|
+
- name: "Download actionlint"
|
|
43
|
+
run: |
|
|
44
|
+
docker build --tag actionlint - < .github/workflows/actionlint.dockerfile
|
|
45
|
+
- name: "Check workflow files"
|
|
46
|
+
run: |
|
|
47
|
+
echo "::add-matcher::.github/workflows/matchers/actionlint.json"
|
|
48
|
+
docker run --volume="${PWD}:/repo" --workdir=/repo actionlint -color
|
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
|
|
3
|
+
name: Lint Markdown documents
|
|
4
|
+
|
|
5
|
+
on:
|
|
6
|
+
push:
|
|
7
|
+
branches:
|
|
8
|
+
- "main"
|
|
9
|
+
paths:
|
|
10
|
+
- '**/*.md'
|
|
11
|
+
- '.markdownlint-cli2.yaml'
|
|
12
|
+
- '.github/workflows/docs.yml' # This workflow
|
|
13
|
+
pull_request:
|
|
14
|
+
branches:
|
|
15
|
+
- "main"
|
|
16
|
+
paths:
|
|
17
|
+
- '**/*.md'
|
|
18
|
+
- '.markdownlint-cli2.yaml'
|
|
19
|
+
- '.github/workflows/docs.yml' # This workflow
|
|
20
|
+
|
|
21
|
+
env:
|
|
22
|
+
LC_ALL: en_US.UTF-8
|
|
23
|
+
|
|
24
|
+
defaults:
|
|
25
|
+
run:
|
|
26
|
+
shell: bash
|
|
27
|
+
|
|
28
|
+
permissions:
|
|
29
|
+
contents: read
|
|
30
|
+
|
|
31
|
+
jobs:
|
|
32
|
+
markdown-lint:
|
|
33
|
+
runs-on: ubuntu-latest
|
|
34
|
+
steps:
|
|
35
|
+
- name: "Harden Runner"
|
|
36
|
+
uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
|
|
37
|
+
with:
|
|
38
|
+
egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
|
|
39
|
+
- name: "Checkout"
|
|
40
|
+
uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
|
|
41
|
+
with:
|
|
42
|
+
fetch-depth: 0
|
|
43
|
+
- name: "Check Markdown documents"
|
|
44
|
+
uses: DavidAnson/markdownlint-cli2-action@b4c9feab76d8025d1e83c653fa3990936df0e6c8 # v16.0.0
|
|
45
|
+
with:
|
|
46
|
+
globs: '**/*.md'
|
|
@@ -0,0 +1,76 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
|
|
3
|
+
name: Lint, Format, and MyPy
|
|
4
|
+
|
|
5
|
+
on:
|
|
6
|
+
push:
|
|
7
|
+
branches:
|
|
8
|
+
- "main"
|
|
9
|
+
- "release-**"
|
|
10
|
+
paths:
|
|
11
|
+
- '**.py'
|
|
12
|
+
- 'pyproject.toml'
|
|
13
|
+
- 'requirements*.txt'
|
|
14
|
+
- 'tox.ini'
|
|
15
|
+
- 'scripts/*.sh'
|
|
16
|
+
- '.github/**'
|
|
17
|
+
pull_request:
|
|
18
|
+
branches:
|
|
19
|
+
- "main"
|
|
20
|
+
- "release-**"
|
|
21
|
+
paths:
|
|
22
|
+
- '**.py'
|
|
23
|
+
- 'pyproject.toml'
|
|
24
|
+
- 'requirements*.txt'
|
|
25
|
+
- 'tox.ini'
|
|
26
|
+
- 'scripts/*.sh'
|
|
27
|
+
- '.github/**'
|
|
28
|
+
|
|
29
|
+
env:
|
|
30
|
+
PYTHON_VERSION: 3.11
|
|
31
|
+
|
|
32
|
+
jobs:
|
|
33
|
+
lint:
|
|
34
|
+
runs-on: ubuntu-latest
|
|
35
|
+
steps:
|
|
36
|
+
- name: "Harden Runner"
|
|
37
|
+
uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
|
|
38
|
+
with:
|
|
39
|
+
egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
|
|
40
|
+
|
|
41
|
+
- name: "Checkout"
|
|
42
|
+
uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
|
|
43
|
+
with:
|
|
44
|
+
# https://github.com/actions/checkout/issues/249
|
|
45
|
+
fetch-depth: 0
|
|
46
|
+
submodules: true
|
|
47
|
+
|
|
48
|
+
- name: Setup Python 3.11
|
|
49
|
+
uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
|
|
50
|
+
with:
|
|
51
|
+
python-version: 3.11
|
|
52
|
+
cache: pip
|
|
53
|
+
cache-dependency-path: |
|
|
54
|
+
**/pyproject.toml
|
|
55
|
+
**/requirements*.txt
|
|
56
|
+
|
|
57
|
+
- name: Install dependencies
|
|
58
|
+
id: deps
|
|
59
|
+
run: |
|
|
60
|
+
python -m pip install --upgrade pip
|
|
61
|
+
python -m pip install tox
|
|
62
|
+
|
|
63
|
+
- name: Run Ruff check
|
|
64
|
+
run: |
|
|
65
|
+
tox -e ruff -- check
|
|
66
|
+
|
|
67
|
+
- name: Run linting
|
|
68
|
+
if: ${{ !cancelled() && (steps.deps.outcome == 'success') }}
|
|
69
|
+
run: |
|
|
70
|
+
echo "::add-matcher::.github/workflows/matchers/pylint.json"
|
|
71
|
+
tox -e lint
|
|
72
|
+
|
|
73
|
+
- name: Run mypy type checks
|
|
74
|
+
if: ${{ !cancelled() && (steps.deps.outcome == 'success') }}
|
|
75
|
+
run: |
|
|
76
|
+
tox -e mypy
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
{
|
|
2
|
+
"problemMatcher": [
|
|
3
|
+
{
|
|
4
|
+
"owner": "actionlint",
|
|
5
|
+
"pattern": [
|
|
6
|
+
{
|
|
7
|
+
"regexp": "^(?:\\x1b\\[\\d+m)?(.+?)(?:\\x1b\\[\\d+m)*:(?:\\x1b\\[\\d+m)*(\\d+)(?:\\x1b\\[\\d+m)*:(?:\\x1b\\[\\d+m)*(\\d+)(?:\\x1b\\[\\d+m)*: (?:\\x1b\\[\\d+m)*(.+?)(?:\\x1b\\[\\d+m)* \\[(.+?)\\]$",
|
|
8
|
+
"file": 1,
|
|
9
|
+
"line": 2,
|
|
10
|
+
"column": 3,
|
|
11
|
+
"message": 4,
|
|
12
|
+
"code": 5
|
|
13
|
+
}
|
|
14
|
+
]
|
|
15
|
+
}
|
|
16
|
+
]
|
|
17
|
+
}
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
{
|
|
2
|
+
"problemMatcher": [
|
|
3
|
+
{
|
|
4
|
+
"owner": "pylint-error",
|
|
5
|
+
"severity": "error",
|
|
6
|
+
"pattern": [
|
|
7
|
+
{
|
|
8
|
+
"regexp": "^(.+):(\\d+):(\\d+):\\s(([EF]\\d{4}):\\s.+)$",
|
|
9
|
+
"file": 1,
|
|
10
|
+
"line": 2,
|
|
11
|
+
"column": 3,
|
|
12
|
+
"message": 4,
|
|
13
|
+
"code": 5
|
|
14
|
+
}
|
|
15
|
+
]
|
|
16
|
+
},
|
|
17
|
+
{
|
|
18
|
+
"owner": "pylint-warning",
|
|
19
|
+
"severity": "warning",
|
|
20
|
+
"pattern": [
|
|
21
|
+
{
|
|
22
|
+
"regexp": "^(.+):(\\d+):(\\d+):\\s(([CRW]\\d{4}):\\s.+)$",
|
|
23
|
+
"file": 1,
|
|
24
|
+
"line": 2,
|
|
25
|
+
"column": 3,
|
|
26
|
+
"message": 4,
|
|
27
|
+
"code": 5
|
|
28
|
+
}
|
|
29
|
+
]
|
|
30
|
+
}
|
|
31
|
+
]
|
|
32
|
+
}
|
|
@@ -0,0 +1,131 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
|
|
3
|
+
name: Build, test, and upload PyPI package
|
|
4
|
+
|
|
5
|
+
on:
|
|
6
|
+
push:
|
|
7
|
+
branches:
|
|
8
|
+
- "main"
|
|
9
|
+
- "release-**"
|
|
10
|
+
tags:
|
|
11
|
+
- "v*"
|
|
12
|
+
pull_request:
|
|
13
|
+
branches:
|
|
14
|
+
- "main"
|
|
15
|
+
- "release-**"
|
|
16
|
+
release:
|
|
17
|
+
types:
|
|
18
|
+
- published
|
|
19
|
+
|
|
20
|
+
env:
|
|
21
|
+
LC_ALL: en_US.UTF-8
|
|
22
|
+
|
|
23
|
+
defaults:
|
|
24
|
+
run:
|
|
25
|
+
shell: bash
|
|
26
|
+
|
|
27
|
+
permissions:
|
|
28
|
+
contents: read
|
|
29
|
+
|
|
30
|
+
jobs:
|
|
31
|
+
# Create and verify release artifacts
|
|
32
|
+
# - build source dist (tar ball) and wheel
|
|
33
|
+
# - validate artifacts with various tools
|
|
34
|
+
# - upload artifacts to GHA
|
|
35
|
+
build-package:
|
|
36
|
+
name: Build and check packages
|
|
37
|
+
runs-on: ubuntu-latest
|
|
38
|
+
steps:
|
|
39
|
+
- name: "Harden Runner"
|
|
40
|
+
uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
|
|
41
|
+
with:
|
|
42
|
+
egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
|
|
43
|
+
|
|
44
|
+
- name: "Checkout"
|
|
45
|
+
uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
|
|
46
|
+
with:
|
|
47
|
+
# for setuptools-scm
|
|
48
|
+
fetch-depth: 0
|
|
49
|
+
|
|
50
|
+
- name: "Build and Inspect"
|
|
51
|
+
uses: hynek/build-and-inspect-python-package@b4fc3f6ba2b3da04f09659be99e2a29fb6146a61 # v2.6.0
|
|
52
|
+
|
|
53
|
+
# push to Test PyPI on
|
|
54
|
+
# - a new GitHub release is published
|
|
55
|
+
# - a PR is merged into main branch
|
|
56
|
+
publish-test-pypi:
|
|
57
|
+
name: Publish packages to test.pypi.org
|
|
58
|
+
# environment: publish-test-pypi
|
|
59
|
+
if: ${{ (github.repository_owner == 'instructlab') && ((github.event.action == 'published') || ((github.event_name == 'push') && (github.ref == 'refs/heads/main'))) }}
|
|
60
|
+
permissions:
|
|
61
|
+
contents: read
|
|
62
|
+
# see https://docs.pypi.org/trusted-publishers/
|
|
63
|
+
id-token: write
|
|
64
|
+
runs-on: ubuntu-latest
|
|
65
|
+
needs: build-package
|
|
66
|
+
|
|
67
|
+
steps:
|
|
68
|
+
- name: "Harden Runner"
|
|
69
|
+
uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
|
|
70
|
+
with:
|
|
71
|
+
egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
|
|
72
|
+
|
|
73
|
+
- name: "Download build artifacts"
|
|
74
|
+
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
|
|
75
|
+
with:
|
|
76
|
+
name: Packages
|
|
77
|
+
path: dist
|
|
78
|
+
|
|
79
|
+
- name: "Upload to Test PyPI"
|
|
80
|
+
uses: pypa/gh-action-pypi-publish@ec4db0b4ddc65acdf4bff5fa45ac92d78b56bdf0 # v1.9.0
|
|
81
|
+
with:
|
|
82
|
+
repository-url: https://test.pypi.org/legacy/
|
|
83
|
+
|
|
84
|
+
# push to Production PyPI on
|
|
85
|
+
# - a new GitHub release is published
|
|
86
|
+
publish-pypi:
|
|
87
|
+
name: Publish release to pypi.org
|
|
88
|
+
# environment: publish-pypi
|
|
89
|
+
if: ${{ (github.repository_owner == 'instructlab') && (github.event.action == 'published') }}
|
|
90
|
+
permissions:
|
|
91
|
+
# see https://docs.pypi.org/trusted-publishers/
|
|
92
|
+
id-token: write
|
|
93
|
+
# allow gh release upload
|
|
94
|
+
contents: write
|
|
95
|
+
|
|
96
|
+
runs-on: ubuntu-latest
|
|
97
|
+
needs: build-package
|
|
98
|
+
|
|
99
|
+
steps:
|
|
100
|
+
- name: "Harden Runner"
|
|
101
|
+
uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
|
|
102
|
+
with:
|
|
103
|
+
egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
|
|
104
|
+
|
|
105
|
+
- name: "Download build artifacts"
|
|
106
|
+
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
|
|
107
|
+
with:
|
|
108
|
+
name: Packages
|
|
109
|
+
path: dist
|
|
110
|
+
|
|
111
|
+
- name: "Sigstore sign package"
|
|
112
|
+
uses: sigstore/gh-action-sigstore-python@61f6a500bbfdd9a2a339cf033e5421951fbc1cd2 # v2.1.1
|
|
113
|
+
with:
|
|
114
|
+
inputs: |
|
|
115
|
+
./dist/*.tar.gz
|
|
116
|
+
./dist/*.whl
|
|
117
|
+
|
|
118
|
+
- name: "Upload artifacts and signatures to GitHub release"
|
|
119
|
+
run: |
|
|
120
|
+
gh release upload '${{ github.ref_name }}' dist/* --repo '${{ github.repository }}'
|
|
121
|
+
env:
|
|
122
|
+
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
123
|
+
|
|
124
|
+
# PyPI does not accept .sigstore artifacts and
|
|
125
|
+
# gh-action-pypi-publish has no option to ignore them.
|
|
126
|
+
- name: "Remove sigstore signatures before uploading to PyPI"
|
|
127
|
+
run: |
|
|
128
|
+
rm ./dist/*.sigstore
|
|
129
|
+
|
|
130
|
+
- name: "Upload to PyPI"
|
|
131
|
+
uses: pypa/gh-action-pypi-publish@ec4db0b4ddc65acdf4bff5fa45ac92d78b56bdf0 # v1.9.0
|
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
|
|
3
|
+
name: Spellcheck
|
|
4
|
+
|
|
5
|
+
on:
|
|
6
|
+
push:
|
|
7
|
+
branches:
|
|
8
|
+
- "main"
|
|
9
|
+
paths:
|
|
10
|
+
- '**.md'
|
|
11
|
+
- '.github/workflows/spellcheck.yml' # This workflow
|
|
12
|
+
pull_request:
|
|
13
|
+
branches:
|
|
14
|
+
- "main"
|
|
15
|
+
paths:
|
|
16
|
+
- '**.md'
|
|
17
|
+
- '.github/workflows/spellcheck.yml' # This workflow
|
|
18
|
+
|
|
19
|
+
env:
|
|
20
|
+
LC_ALL: en_US.UTF-8
|
|
21
|
+
|
|
22
|
+
defaults:
|
|
23
|
+
run:
|
|
24
|
+
shell: bash
|
|
25
|
+
|
|
26
|
+
permissions:
|
|
27
|
+
contents: read
|
|
28
|
+
|
|
29
|
+
jobs:
|
|
30
|
+
spellcheck:
|
|
31
|
+
name: Spellcheck (en_US)
|
|
32
|
+
runs-on: ubuntu-latest
|
|
33
|
+
steps:
|
|
34
|
+
- name: "Harden Runner"
|
|
35
|
+
uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
|
|
36
|
+
with:
|
|
37
|
+
egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
|
|
38
|
+
|
|
39
|
+
- name: "Checkout"
|
|
40
|
+
uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
|
|
41
|
+
with:
|
|
42
|
+
fetch-depth: 0
|
|
43
|
+
|
|
44
|
+
- name: Spellcheck
|
|
45
|
+
uses: rojopolis/spellcheck-github-actions@d354a4dc525c8067555c7481b60416cedb0060ff # v0.38.0
|
|
@@ -0,0 +1,173 @@
|
|
|
1
|
+
# Attribution:
|
|
2
|
+
# .gitignore file sourced from a repository licensed under CC0-1.0
|
|
3
|
+
# Original source: https://github.com/github/gitignore/blob/main/Python.gitignore
|
|
4
|
+
|
|
5
|
+
# add sample data
|
|
6
|
+
sample-data
|
|
7
|
+
|
|
8
|
+
# Byte-compiled / optimized / DLL files
|
|
9
|
+
__pycache__/
|
|
10
|
+
*.py[cod]
|
|
11
|
+
*$py.class
|
|
12
|
+
|
|
13
|
+
# C extensions
|
|
14
|
+
*.so
|
|
15
|
+
|
|
16
|
+
# Distribution / packaging
|
|
17
|
+
.Python
|
|
18
|
+
build/
|
|
19
|
+
develop-eggs/
|
|
20
|
+
dist/
|
|
21
|
+
downloads/
|
|
22
|
+
eggs/
|
|
23
|
+
.eggs/
|
|
24
|
+
lib/
|
|
25
|
+
lib64/
|
|
26
|
+
parts/
|
|
27
|
+
sdist/
|
|
28
|
+
var/
|
|
29
|
+
wheels/
|
|
30
|
+
share/python-wheels/
|
|
31
|
+
*.egg-info/
|
|
32
|
+
.installed.cfg
|
|
33
|
+
*.egg
|
|
34
|
+
MANIFEST
|
|
35
|
+
src/instructlab/training/_version.py
|
|
36
|
+
|
|
37
|
+
# PyInstaller
|
|
38
|
+
# Usually these files are written by a python script from a template
|
|
39
|
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
|
40
|
+
*.manifest
|
|
41
|
+
*.spec
|
|
42
|
+
|
|
43
|
+
# Installer logs
|
|
44
|
+
pip-log.txt
|
|
45
|
+
pip-delete-this-directory.txt
|
|
46
|
+
|
|
47
|
+
# Unit test / coverage reports
|
|
48
|
+
htmlcov/
|
|
49
|
+
.tox/
|
|
50
|
+
.nox/
|
|
51
|
+
.coverage
|
|
52
|
+
.coverage.*
|
|
53
|
+
.cache
|
|
54
|
+
nosetests.xml
|
|
55
|
+
coverage.xml
|
|
56
|
+
*.cover
|
|
57
|
+
*.py,cover
|
|
58
|
+
.hypothesis/
|
|
59
|
+
.pytest_cache/
|
|
60
|
+
cover/
|
|
61
|
+
|
|
62
|
+
# Translations
|
|
63
|
+
*.mo
|
|
64
|
+
*.pot
|
|
65
|
+
|
|
66
|
+
# Django stuff:
|
|
67
|
+
*.log
|
|
68
|
+
local_settings.py
|
|
69
|
+
db.sqlite3
|
|
70
|
+
db.sqlite3-journal
|
|
71
|
+
|
|
72
|
+
# Flask stuff:
|
|
73
|
+
instance/
|
|
74
|
+
.webassets-cache
|
|
75
|
+
|
|
76
|
+
# Scrapy stuff:
|
|
77
|
+
.scrapy
|
|
78
|
+
|
|
79
|
+
# Sphinx documentation
|
|
80
|
+
docs/_build/
|
|
81
|
+
|
|
82
|
+
# PyBuilder
|
|
83
|
+
.pybuilder/
|
|
84
|
+
target/
|
|
85
|
+
|
|
86
|
+
# Jupyter Notebook
|
|
87
|
+
.ipynb_checkpoints
|
|
88
|
+
|
|
89
|
+
# IPython
|
|
90
|
+
profile_default/
|
|
91
|
+
ipython_config.py
|
|
92
|
+
|
|
93
|
+
# pyenv
|
|
94
|
+
# For a library or package, you might want to ignore these files since the code is
|
|
95
|
+
# intended to run in multiple environments; otherwise, check them in:
|
|
96
|
+
# .python-version
|
|
97
|
+
|
|
98
|
+
# pipenv
|
|
99
|
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
|
100
|
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
|
101
|
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
|
102
|
+
# install all needed dependencies.
|
|
103
|
+
#Pipfile.lock
|
|
104
|
+
|
|
105
|
+
# poetry
|
|
106
|
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
|
107
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
108
|
+
# commonly ignored for libraries.
|
|
109
|
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
|
110
|
+
#poetry.lock
|
|
111
|
+
|
|
112
|
+
# pdm
|
|
113
|
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
|
114
|
+
#pdm.lock
|
|
115
|
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
|
116
|
+
# in version control.
|
|
117
|
+
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
|
|
118
|
+
.pdm.toml
|
|
119
|
+
.pdm-python
|
|
120
|
+
.pdm-build/
|
|
121
|
+
|
|
122
|
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
|
123
|
+
__pypackages__/
|
|
124
|
+
|
|
125
|
+
# Celery stuff
|
|
126
|
+
celerybeat-schedule
|
|
127
|
+
celerybeat.pid
|
|
128
|
+
|
|
129
|
+
# SageMath parsed files
|
|
130
|
+
*.sage.py
|
|
131
|
+
|
|
132
|
+
# Environments
|
|
133
|
+
.env
|
|
134
|
+
.venv
|
|
135
|
+
env/
|
|
136
|
+
venv/
|
|
137
|
+
ENV/
|
|
138
|
+
env.bak/
|
|
139
|
+
venv.bak/
|
|
140
|
+
|
|
141
|
+
# Spyder project settings
|
|
142
|
+
.spyderproject
|
|
143
|
+
.spyproject
|
|
144
|
+
|
|
145
|
+
# Rope project settings
|
|
146
|
+
.ropeproject
|
|
147
|
+
|
|
148
|
+
# mkdocs documentation
|
|
149
|
+
/site
|
|
150
|
+
|
|
151
|
+
# mypy
|
|
152
|
+
.mypy_cache/
|
|
153
|
+
.dmypy.json
|
|
154
|
+
dmypy.json
|
|
155
|
+
|
|
156
|
+
# Pyre type checker
|
|
157
|
+
.pyre/
|
|
158
|
+
|
|
159
|
+
# pytype static type analyzer
|
|
160
|
+
.pytype/
|
|
161
|
+
|
|
162
|
+
# Cython debug symbols
|
|
163
|
+
cython_debug/
|
|
164
|
+
|
|
165
|
+
# PyCharm
|
|
166
|
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
|
167
|
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
|
168
|
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
|
169
|
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
|
170
|
+
#.idea/
|
|
171
|
+
|
|
172
|
+
# spellcheck
|
|
173
|
+
dictionary.dic
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
[settings]
|
|
2
|
+
profile=black
|
|
3
|
+
from_first=true
|
|
4
|
+
import_heading_future=Future
|
|
5
|
+
import_heading_stdlib=Standard
|
|
6
|
+
import_heading_thirdparty=Third Party
|
|
7
|
+
import_heading_firstparty=First Party
|
|
8
|
+
import_heading_localfolder=Local
|
|
9
|
+
known_firstparty=
|
|
10
|
+
known_localfolder=tuning
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
|
|
3
|
+
config:
|
|
4
|
+
line-length: false
|
|
5
|
+
no-emphasis-as-header: false
|
|
6
|
+
first-line-heading: false
|
|
7
|
+
code-block-style: false
|
|
8
|
+
no-duplicate-header: false
|
|
9
|
+
single-trailing-newline: false
|
|
10
|
+
globs:
|
|
11
|
+
- "**/*.md"
|
|
12
|
+
ignores:
|
|
13
|
+
- ".github/**"
|
|
14
|
+
- "venv/**"
|
|
15
|
+
- ".venv/**"
|
|
16
|
+
- ".tox/**"
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
|
|
3
|
+
repos:
|
|
4
|
+
- repo: https://github.com/PyCQA/isort
|
|
5
|
+
rev: 5.11.5
|
|
6
|
+
hooks:
|
|
7
|
+
- id: isort
|
|
8
|
+
exclude: imports
|
|
9
|
+
- repo: https://github.com/astral-sh/ruff-pre-commit
|
|
10
|
+
# Ruff version.
|
|
11
|
+
rev: v0.3.4
|
|
12
|
+
hooks:
|
|
13
|
+
# Run the linter (most fixers are disabled for now).
|
|
14
|
+
- id: ruff
|
|
15
|
+
# Run the formatter.
|
|
16
|
+
- id: ruff-format
|