:hammer: Read token from os environment, or .env file

.env_sample

@@ -0,0 +1 @@
+HF_TOKEN=hf_YOUR_AWESOME_TOKEN

.gitignore

@@ -1,3 +1,169 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# c++ generated files
+*.out
+*.exe
+
+# my custom gitignores
 lightning_logs/
 *.pth
 my-awesome-model/

app.py

@@ -17,6 +17,9 @@ from torch import nn
 from datasets import load_dataset, IterableDataset
 from huggingface_hub import PyTorchModelHubMixin
 
+from dotenv import load_dotenv
+from huggingface_hub import login
+
 timber = logging.getLogger()
 # logging.basicConfig(level=logging.DEBUG)
 logging.basicConfig(level=logging.INFO)  # change to level=logging.DEBUG to print more logs...
@@ -36,6 +39,30 @@ BACKWARD = "BACKWARD_INPUT"
 DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 
+def login_inside_huggingface_virtualmachine():
+  # Load the .env file, but don't crash if it's not found (e.g., in Hugging Face Space)
+  try:
+    load_dotenv()  # Only useful on your laptop if .env exists
+    print(".env file loaded successfully.")
+  except Exception as e:
+    print(f"Warning: Could not load .env file. Exception: {e}")
+
+  # Try to get the token from environment variables
+  try:
+    token = os.getenv("HF_TOKEN")
+
+    if not token:
+      raise ValueError("HF_TOKEN not found. Make sure to set it in the environment variables or .env file.")
+
+    # Log in to Hugging Face Hub
+    login(token)
+    print("Logged in to Hugging Face Hub successfully.")
+
+  except Exception as e:
+    print(f"Error during Hugging Face login: {e}")
+    # Handle the error appropriately (e.g., exit or retry)
+
+
 def one_hot_e(dna_seq: str) -> np.ndarray:
   mydict = {'A': np.asarray([1.0, 0.0, 0.0, 0.0]), 'C': np.asarray([0.0, 1.0, 0.0, 0.0]),
             'G': np.asarray([0.0, 0.0, 1.0, 0.0]), 'T': np.asarray([0.0, 0.0, 0.0, 1.0]),
@@ -457,11 +484,15 @@ def start(classifier_model, model_save_path, is_attention_model=False, m_optimiz
   torch.save(classifier_module.state_dict(), model_save_path)
 
   #  save locally
-  classifier_model.save_pretrained(f"my-awesome-model-{WINDOW}")
+  model_subdirectory = f"my-awesome-model-{WINDOW}"
+  classifier_model.save_pretrained(model_subdirectory)
 
   # push to the hub
-  classifier_model.push_to_hub(repo_id="fahimfarhan/mqtl-classifier-model",
-                               commit_message=":tada: Push model using huggingface_hub")
+  classifier_model.push_to_hub(
+    repo_id="fahimfarhan/mqtl-classifier-model",
+    # subfolder=f"my-awesome-model-{WINDOW}", subfolder didn't work :/
+    commit_message=f":tada: Push model for window size {WINDOW}"
+  )
 
   # reload
   model = classifier_model.from_pretrained(f"my-awesome-model-{WINDOW}")
@@ -481,12 +512,14 @@ def start(classifier_model, model_save_path, is_attention_model=False, m_optimiz
 
 
 if __name__ == '__main__':
-  WINDOW = 4000
+  login_inside_huggingface_virtualmachine()
+
+  WINDOW = 200
   simple_cnn = Cnn1dClassifier(seq_len=WINDOW)
   simple_cnn.enable_logging = True
 
   start(classifier_model=simple_cnn, model_save_path=simple_cnn.file_name, WINDOW=WINDOW,
-        dataset_folder_prefix="inputdata/", is_debug=True, max_epochs=5)
+        dataset_folder_prefix="inputdata/", is_debug=True, max_epochs=10)
 
   pass
 

requirements.txt

@@ -29,4 +29,5 @@ torchviz
 gReLU # luckily now available in pip!
 # gReLU @ git+https://github.com/Genentech/gReLU # @623fee8023aabcef89f0afeedbeafff4b71453af
 # lightning[extra]  # cz I got a stupid warning in the console logs
-torchmetrics
+torchmetrics
+python-dotenv