fix path issues

.gitignore

@@ -0,0 +1,176 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python

app.py

@@ -45,13 +45,6 @@ def hold_deterministic(seed):
 
 
 def main():
-    # st.title("Privalingo Playground Demo")
-    # html_temp = """
-    # <div style="background:#025246 ;padding:10px">
-    # <h2 style="color:white;text-align:center;">Playground Demo </h2>
-    # </div>
-    # """
-    # st.markdown(html_temp, unsafe_allow_html=True)
     hold_deterministic(SEED)
 
     st.title("Neural Machine Translation with DP-SGD")
@@ -71,15 +64,13 @@ def main():
 
     st_model_load = st.text(f'Loading model trained on {dataset} with epsilon {epsilon}...')
 
-    ckpt = DATASETS_MODEL_INFO[dataset]['languages pairs'][language_pair]['epsilon'][str(epsilon)]
-    model_name = MODEL.split('/')[-1]
-    model_path = os.path.join(CHECKPOINTS_DIR, ckpt, model_name)
+    model_path = DATASETS_MODEL_INFO[dataset]['languages pairs'][language_pair]['epsilon'][str(epsilon)]
 
     if not os.path.exists(model_path):
-        st.error(f"Model not found. Use {MODEL} instead")
-        model_path = MODEL
+        st.error(f"Model not found. Use {DEFAULT_MODEL} instead")
+        model_path = DEFAULT_MODEL
 
-    model, tokenizer = load_model(model_path, tokenizer_name=MODEL)
+    model, tokenizer = load_model(model_path, tokenizer_name=DEFAULT_MODEL)
     st.success('Model loaded!')
     st_model_load.text("")
 
@@ -92,10 +83,9 @@ def main():
 
 
 if __name__ == '__main__':
-    DATASETS_MODEL_INFO_PATH = os.getcwd() + "/app/dataset_and_model_info.json"
-    CHECKPOINTS_DIR = os.getcwd() + "/checkpoints"
+    DATASETS_MODEL_INFO_PATH = os.path.join(os.getcwd(), "dataset_and_model_info.json")
     DATASETS_MODEL_INFO = load_json(DATASETS_MODEL_INFO_PATH)
-    MODEL = 'google/mt5-small'
+    DEFAULT_MODEL = 'google/mt5-small'
 
     MAX_SEQ_LEN = 512
     NUM_BEAMS = 3

dataset_and_model_info.json

@@ -3,9 +3,9 @@
         "languages pairs": {
             "German-English": {
                 "epsilon": {
-                    "1": "2023_10_07-05_50_17",
-                    "5": "2023_10_07-16_40_49",
-                    "non": "2023_11_24-20_58_27"
+                    "1": "MarcoYuTono/privalingo-WMT-de-en-eps1",
+                    "5": "MarcoYuTono/privalingo-WMT-de-en-eps5",
+                    "non": "MarcoYuTono/privalingo-WMT-de-en-infinite"
                 }
             }
         }