KEP-2170: Create model and dataset initializers

.github/workflows/publish-core-images.yaml

@@ -30,6 +30,14 @@ jobs:
             dockerfile: cmd/training-operator.v2alpha1/Dockerfile
             platforms: linux/amd64,linux/arm64,linux/ppc64le
             tag-prefix: v2alpha1
+          - component-name: model-initiailizer-v2
+            dockerfile: cmd/initiailizer_v2/model/Dockerfile
+            platforms: linux/amd64,linux/arm64
+            tag-prefix: v2
+          - component-name: dataset-initiailizer-v2
+            dockerfile: cmd/initiailizer_v2/dataset/Dockerfile
+            platforms: linux/amd64,linux/arm64
+            tag-prefix: v2
           - component-name: kubectl-delivery
             dockerfile: build/images/kubectl-delivery/Dockerfile
             platforms: linux/amd64,linux/arm64,linux/ppc64le

.gitignore

@@ -10,8 +10,8 @@ cover.out
 .vscode/
 __debug_bin
 
-# Compiled python files.
-*.pyc
+# Python chache files
+__pycache__/
 
 # Emacs temporary files
 *~

cmd/initiailizer_v2/dataset/Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.11-alpine
+
+WORKDIR /workspace
+
+# Copy the required Python modules.
+COPY cmd/initiailizer_v2/dataset/requirements.txt .
+COPY sdk/python/kubeflow sdk/python/kubeflow
+COPY pkg/initiailizer_v2 pkg/initiailizer_v2
+
+# Install the needed packages.
+RUN pip install -r requirements.txt
+
+ENTRYPOINT ["python", "-m", "pkg.initiailizer_v2.dataset"]

cmd/initiailizer_v2/dataset/requirements.txt

@@ -0,0 +1 @@
+huggingface_hub==0.23.4

cmd/initiailizer_v2/model/Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.11-alpine
+
+WORKDIR /workspace
+
+# Copy the required Python modules.
+COPY cmd/initiailizer_v2/model/requirements.txt .
+COPY sdk/python/kubeflow sdk/python/kubeflow
+COPY pkg/initiailizer_v2 pkg/initiailizer_v2
+
+# Install the needed packages.
+RUN pip install -r requirements.txt
+
+ENTRYPOINT ["python", "-m", "pkg.initiailizer_v2.model"]

cmd/initiailizer_v2/model/requirements.txt

@@ -0,0 +1 @@
+huggingface_hub==0.23.4

pkg/initiailizer_v2/dataset/__main__.py

@@ -0,0 +1,31 @@
+import logging
+import os
+from urllib.parse import urlparse
+
+import pkg.initiailizer_v2.utils.utils as utils
+from pkg.initiailizer_v2.dataset.huggingface import HuggingFace
+
+logging.basicConfig(
+    format="%(asctime)s %(levelname)-8s [%(filename)s:%(lineno)d] %(message)s",
+    datefmt="%Y-%m-%dT%H:%M:%SZ",
+    level=logging.INFO,
+)
+
+if __name__ == "__main__":
+    logging.info("Starting dataset 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 dataset providers.
+        case utils.HF_SCHEME:
+            hf = HuggingFace()
+            hf.load_config()
+            hf.download_dataset()
+        case _:
+            logging.error("STORAGE_URI must have the valid dataset provider")
+            raise Exception

pkg/initiailizer_v2/dataset/config.py

@@ -0,0 +1,9 @@
+from dataclasses import dataclass
+from typing import Optional
+
+
+# TODO (andreyvelich): This should be moved under Training V2 SDK.
+@dataclass
+class HuggingFaceDatasetConfig:
+    storage_uri: str
+    access_token: Optional[str] = None

pkg/initiailizer_v2/dataset/huggingface.py

@@ -0,0 +1,42 @@
+import logging
+from urllib.parse import urlparse
+
+import huggingface_hub
+
+import pkg.initiailizer_v2.utils.utils as utils
+
+# TODO (andreyvelich): This should be moved to SDK V2 constants.
+import sdk.python.kubeflow.storage_initializer.constants as constants
+from pkg.initiailizer_v2.dataset.config import HuggingFaceDatasetConfig
+
+logging.basicConfig(
+    format="%(asctime)s %(levelname)-8s [%(filename)s:%(lineno)d] %(message)s",
+    datefmt="%Y-%m-%dT%H:%M:%SZ",
+    level=logging.INFO,
+)
+
+
+class HuggingFace(utils.DatasetProvider):
+
+    def load_config(self):
+        config_dict = utils.get_config_from_env(HuggingFaceDatasetConfig)
+        logging.info(f"Config for HuggingFace dataset initiailizer: {config_dict}")
+        self.config = HuggingFaceDatasetConfig(**config_dict)
+
+    def download_dataset(self):
+        storage_uri_parsed = urlparse(self.config.storage_uri)
+        dataset_uri = storage_uri_parsed.netloc + storage_uri_parsed.path
+
+        logging.info(f"Downloading dataset: {dataset_uri}")
+        logging.info("-" * 40)
+
+        if self.config.access_token:
+            huggingface_hub.login(self.config.access_token)
+
+        huggingface_hub.snapshot_download(
+            repo_id=dataset_uri,
+            repo_type="dataset",
+            local_dir=constants.VOLUME_PATH_DATASET,
+        )
+
+        logging.info("Dataset has been downloaded")

pkg/initiailizer_v2/model/__main__.py

@@ -0,0 +1,33 @@
+import logging
+import os
+from urllib.parse import urlparse
+
+import pkg.initiailizer_v2.utils.utils as utils
+from pkg.initiailizer_v2.model.huggingface import HuggingFace
+
+logging.basicConfig(
+    format="%(asctime)s %(levelname)-8s [%(filename)s:%(lineno)d] %(message)s",
+    datefmt="%Y-%m-%dT%H:%M:%SZ",
+    level=logging.INFO,
+)
+
+if __name__ == "__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 _:
+            logging.error(
+                f"STORAGE_URI must have the valid model provider. STORAGE_URI: {storage_uri}"
+            )
+            raise Exception

pkg/initiailizer_v2/model/config.py

@@ -0,0 +1,9 @@
+from dataclasses import dataclass
+from typing import Optional
+
+
+# TODO (andreyvelich): This should be moved under Training V2 SDK.
+@dataclass
+class HuggingFaceModelInputConfig:
+    storage_uri: str
+    access_token: Optional[str] = None

pkg/initiailizer_v2/model/huggingface.py

@@ -0,0 +1,44 @@
+import logging
+from urllib.parse import urlparse
+
+import huggingface_hub
+
+import pkg.initiailizer_v2.utils.utils as utils
+
+# TODO (andreyvelich): This should be moved to SDK V2 constants.
+import sdk.python.kubeflow.storage_initializer.constants as constants
+from pkg.initiailizer_v2.model.config import HuggingFaceModelInputConfig
+
+logging.basicConfig(
+    format="%(asctime)s %(levelname)-8s [%(filename)s:%(lineno)d] %(message)s",
+    datefmt="%Y-%m-%dT%H:%M:%SZ",
+    level=logging.INFO,
+)
+
+
+class HuggingFace(utils.ModelProvider):
+
+    def load_config(self):
+        config_dict = utils.get_config_from_env(HuggingFaceModelInputConfig)
+        logging.info(f"Config for HuggingFace model initiailizer: {config_dict}")
+        self.config = HuggingFaceModelInputConfig(**config_dict)
+
+    def download_model(self):
+        storage_uri_parsed = urlparse(self.config.storage_uri)
+        model_uri = storage_uri_parsed.netloc + storage_uri_parsed.path
+
+        logging.info(f"Downloading model: {model_uri}")
+        logging.info("-" * 40)
+
+        if self.config.access_token:
+            huggingface_hub.login(self.config.access_token)
+
+        # TODO (andreyvelich): We should verify these patterns for different models.
+        huggingface_hub.snapshot_download(
+            repo_id=model_uri,
+            local_dir=constants.VOLUME_PATH_MODEL,
+            allow_patterns=["*.json", "*.safetensors", "*.model"],
+            ignore_patterns=["*.msgpack", "*.h5", "*.bin"],
+        )
+
+        logging.info("Model has been downloaded")

pkg/initiailizer_v2/utils/utils.py

@@ -0,0 +1,37 @@
+import os
+from abc import ABC, abstractmethod
+from dataclasses import fields
+from typing import Dict
+
+STORAGE_URI_ENV = "STORAGE_URI"
+HF_SCHEME = "hf"
+
+
+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[str, str]:
+    config_from_env = {}
+    for field in fields(config):
+        config_from_env[field.name] = os.getenv(field.name.upper())
+
+    return config_from_env