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]>
74 lines
2.1 KiB
Python
74 lines
2.1 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 os
|
|
from abc import ABC, abstractmethod
|
|
from dataclasses import fields
|
|
from typing import Dict
|
|
|
|
STORAGE_URI_ENV = "STORAGE_URI"
|
|
HF_SCHEME = "hf"
|
|
CACHE_SCHEME = "cache"
|
|
S3_SCHEME = "s3"
|
|
|
|
# The default path to the users' workspace.
|
|
# TODO (andreyvelich): Discuss how to keep this path is sync with Kubeflow SDK constants.
|
|
WORKSPACE_PATH = "/workspace"
|
|
|
|
# The path where initializer downloads dataset.
|
|
DATASET_PATH = os.path.join(WORKSPACE_PATH, "dataset")
|
|
|
|
# The path where initializer downloads model.
|
|
MODEL_PATH = os.path.join(WORKSPACE_PATH, "model")
|
|
|
|
|
|
class ModelProvider(ABC):
|
|
@abstractmethod
|
|
def load_config(self):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def download_model(self):
|
|
raise NotImplementedError()
|
|
|
|
|
|
class DatasetProvider(ABC):
|
|
@abstractmethod
|
|
def load_config(self):
|
|
raise NotImplementedError()
|
|
|
|
@abstractmethod
|
|
def download_dataset(self):
|
|
raise NotImplementedError()
|
|
|
|
|
|
# Get DataClass config from the environment variables.
|
|
# Env names must be equal to the DataClass parameters.
|
|
def get_config_from_env(config) -> Dict:
|
|
config_from_env = {}
|
|
|
|
for field in fields(config):
|
|
env_value = os.getenv(field.name.upper())
|
|
|
|
if field.name == "ignore_patterns":
|
|
config_from_env[field.name] = (
|
|
[item.strip() for item in env_value.split(",") if item.strip()]
|
|
if env_value
|
|
else None
|
|
)
|
|
else:
|
|
config_from_env[field.name] = env_value if env_value else None
|
|
|
|
return config_from_env
|