mirror of
https://github.com/hanzo-ml/trainer.git
synced 2026-09-24 00:31:34 +00:00
Tariq HasanandGitHub
9183dfd24f
* chore(scripts): add copyright boilerplate verification system Signed-off-by: tariq-hasan <[email protected]> * chore(ci): add boilerplate verification to CI pipeline Signed-off-by: tariq-hasan <[email protected]> * chore: regenerate files with year-less copyright headers Signed-off-by: tariq-hasan <[email protected]> * refactor(boilerplate): simplify verification logic Signed-off-by: tariq-hasan <[email protected]> * chore(boilerplate): add missing copyright headers Signed-off-by: tariq-hasan <[email protected]> * ci(boilerplate): move verifier to code-quality workflow and run unit tests Signed-off-by: tariq-hasan <[email protected]> * feat(boilerplate): accept license headers with any year and remove year validation logic Signed-off-by: tariq-hasan <[email protected]> * feat(boilerplate): add copyright headers to generated Python API Signed-off-by: tariq-hasan <[email protected]> * refactor(boilerplate): use block-comment header for generated Go files Signed-off-by: tariq-hasan <[email protected]> * feat(boilerplate): verify copyright headers in Rust files Signed-off-by: tariq-hasan <[email protected]> --------- Signed-off-by: tariq-hasan <[email protected]>
58 lines
1.7 KiB
Python
58 lines
1.7 KiB
Python
# Copyright The Kubeflow Authors.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import logging
|
|
import os
|
|
from urllib.parse import urlparse
|
|
|
|
import pkg.initializers.utils.utils as utils
|
|
from pkg.initializers.model.huggingface import HuggingFace
|
|
from pkg.initializers.model.s3 import S3
|
|
|
|
logging.basicConfig(
|
|
format="%(asctime)s %(levelname)-8s [%(filename)s:%(lineno)d] %(message)s",
|
|
datefmt="%Y-%m-%dT%H:%M:%SZ",
|
|
level=logging.INFO,
|
|
)
|
|
|
|
|
|
def main():
|
|
logging.info("Starting pre-trained model initialization")
|
|
|
|
try:
|
|
storage_uri = os.environ[utils.STORAGE_URI_ENV]
|
|
except Exception as e:
|
|
logging.error("STORAGE_URI env variable must be set.")
|
|
raise e
|
|
|
|
match urlparse(storage_uri).scheme:
|
|
# TODO (andreyvelich): Implement more model providers.
|
|
case utils.HF_SCHEME:
|
|
hf = HuggingFace()
|
|
hf.load_config()
|
|
hf.download_model()
|
|
case utils.S3_SCHEME:
|
|
s3 = S3()
|
|
s3.load_config()
|
|
s3.download_model()
|
|
case _:
|
|
logging.error(
|
|
f"STORAGE_URI must have the valid model provider. STORAGE_URI: {storage_uri}"
|
|
)
|
|
raise Exception
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|