attempt to convert to onnx

.gitignore

@@ -0,0 +1,160 @@
+# 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/

config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d8e25d7e2253e2cdf052086eb65616b5c239cfa17febbeb22c28cb9601b9c8
-size 1703
+oid sha256:affcab423cf457c5772f3964841cde223b6e8bf0beb34624ed70174bc3752f35
+size 1707

decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff3b4a6bb62ddd4fe4f9b541a9c6197326118fb855ea2785bb66d1687b0d86d8
+size 1222666655

decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea74662431a57df2675e9d950d629e42aab2fa18c929094135e7c80203f6f627
+size 1121888515

encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1a5e7021e95441c44514c23c4316548c4bd1e428559aea2c9359787ca67a7f
+size 814841685

handler.py

@@ -1,9 +1,9 @@
 from optimum.onnxruntime import ORTModelForSeq2SeqLM
-from transformers import AutoTokenizer, pipeline
+from transformers import pipeline, AutoTokenizer
 
 class EndpointHandler():
     def __init__(self, path=""):
-        model = ORTModelForSeq2SeqLM.from_pretrained(path, from_transformers=True)
+        model = ORTModelForSeq2SeqLM.from_pretrained(path)
         tokenizer = AutoTokenizer.from_pretrained(path)
         self.pipeline = pipeline("summarization", model=model, tokenizer=tokenizer)
 

old/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d8e25d7e2253e2cdf052086eb65616b5c239cfa17febbeb22c28cb9601b9c8
+size 1703

old/export_model.py

@@ -0,0 +1,11 @@
+from optimum.onnxruntime import ORTModelForSeq2SeqLM
+from transformers import AutoTokenizer
+model_checkpoint = "getvector/earnings-transcript-summary"
+save_directory = "tmp/onnx/"
+huggingface_auth_token = "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"
+# Load a model from transformers and export it to ONNX
+ort_model = ORTModelForSeq2SeqLM.from_pretrained(model_checkpoint, from_transformers=True, use_auth_token=huggingface_auth_token)
+tokenizer = AutoTokenizer.from_pretrained(model_checkpoint, use_auth_token=huggingface_auth_token)
+# Save the onnx model and tokenizer
+ort_model.save_pretrained(save_directory)
+tokenizer.save_pretrained(save_directory)

old/special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e405a36dfe4b9604f484f6a1e619af1a7f7d09e34a8555eb0b77b66318067f
+size 280

old/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dcc90e1c6bea98fde74f85a2a307a1935fe9067bd4c9d6623c520965efce58f
+size 2108689

old/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d09c165ebe460bc0c338606208e725ce9e1c24df798a156d43cd854fff12db
+size 375

old/vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed19656ea1707df69134c4af35c8ceda2cc9860bf2c3495026153a133670ab5e
+size 798293

requirements.txt

@@ -1 +1,24 @@
-optimum[onnxruntime]==1.4.0
+certifi==2022.9.24
+charset-normalizer==2.1.1
+coloredlogs==15.0.1
+filelock==3.8.0
+huggingface-hub==0.10.0
+humanfriendly==10.0
+idna==3.4
+mpmath==1.2.1
+numpy==1.23.3
+optimum==1.4.0
+packaging==21.3
+protobuf==3.20.1
+pyparsing==3.0.9
+PyYAML==6.0
+regex==2022.9.13
+requests==2.28.1
+sentencepiece==0.1.97
+sympy==1.11.1
+tokenizers==0.12.1
+torch==1.12.1
+tqdm==4.64.1
+transformers==4.22.2
+typing_extensions==4.3.0
+urllib3==1.26.12

tokenizer_config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d09c165ebe460bc0c338606208e725ce9e1c24df798a156d43cd854fff12db
-size 375
+oid sha256:9c88e5132bac58e796a8cd076e7c9d3bd93f701c1bf5454486f7d24846150025
+size 403