sysone 0.2.0__tar.gz

sysone-0.2.0/.gitignore

@@ -0,0 +1,225 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+*.lcov
+.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
+
+# uv
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.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
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi/*
+!.pixi/config.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
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs/Zensical 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/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore that
+#   can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, you
+#   could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# custom
+reference/
+.DS_Store
+quickstart-model/

sysone-0.2.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Goutham Balaraman
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

sysone-0.2.0/PKG-INFO

@@ -0,0 +1,144 @@
+Metadata-Version: 2.5
+Name: sysone
+Version: 0.2.0
+Summary: Fine-tune and calibrate system-one decision models with a scikit-learn style fit / predict interface.
+Project-URL: Homepage, https://github.com/ForwardMetric/sysone
+Project-URL: Repository, https://github.com/ForwardMetric/sysone
+Project-URL: Issues, https://github.com/ForwardMetric/sysone/issues
+Project-URL: Design, https://github.com/ForwardMetric/sysone/blob/main/docs/DESIGN.md
+Author: Goutham Balaraman
+License-Expression: MIT
+License-File: LICENSE
+Keywords: calibration,classification,decision models,fine-tuning,lora,modernbert,qlora,qwen,transformers
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: bitsandbytes>=0.45; sys_platform == 'linux' or sys_platform == 'win32'
+Requires-Dist: huggingface-hub>=0.25
+Requires-Dist: numpy>=1.26
+Requires-Dist: peft>=0.13
+Requires-Dist: safetensors>=0.4
+Requires-Dist: torch>=2.4
+Requires-Dist: transformers>=5.0
+Provides-Extra: pandas
+Requires-Dist: pandas>=2.0; extra == 'pandas'
+Description-Content-Type: text/markdown
+
+# sysone
+
+Fine-tune and calibrate "system one" decision models: small transformers that answer typed
+questions (choice, score, yes/no) about a piece of text in a single forward pass. You pick a base
+model, call `fit` on labelled rows and `predict` on new ones. sysone handles tokenization,
+position ids, attention masks, layer freezing, the decision head and the training loop.
+
+Supported base models: **ModernBERT** (`EncoderModel`) and **Qwen3** (`DecoderModel`). Others can
+be added by writing one architecture class.
+
+## Install
+
+```bash
+pip install sysone
+pip install "sysone[pandas]"   # also installs pandas, for the comparison tables of `compare`
+```
+
+On Linux and Windows this also installs bitsandbytes, for 4-bit training (`tuning="qlora"`).
+
+## Quickstart
+
+```python
+from sysone import DecoderModel
+
+questions = {
+    "team":     {"type": "choice", "instructions": "Which team should handle it?",
+                 "criteria": ["sales", "operations", "servicing"]},
+    "severity": {"type": "score", "instructions": "How severe is it?",
+                 "criteria": ["none", "minor", "major", "critical"]},
+    "refund":   {"type": "noul", "instructions": "Is the customer asking for a refund?"},
+}
+
+rows = [
+    {"state": "Hi, my order is stuck in the warehouse and our line is down.",
+     "category": "operations",
+     "questions": questions,
+     "expected": {"team": "operations", "severity": 3, "refund": False}},
+    # ... more rows; rows may mix different question sets
+]
+
+model = DecoderModel(tuning="head").fit(rows)
+
+model.predict("I'd like my money back for the broken unit.", questions)
+# {"answers": {"team": {"type": "choice", "choice": "servicing", "probabilities": {...}, "confidence": ...},
+#              "severity": {"type": "score", "score": 1.2, "legend": {...}, ...},
+#              "refund": {"type": "noul", "noul": 0.97, ...}},
+#  "usage": {"input_tokens": 118, "output_tokens": 0}}
+
+model.save("my-model")
+model = DecoderModel.load("my-model")
+```
+
+To measure the model on held-out labelled rows, and compare it with simple baselines:
+
+```python
+from sysone import baselines, compare
+
+results = baselines(test_rows, train=rows)      # random guess, average answer
+results["trained"] = model.evaluate(test_rows)
+compare(results)                                # accuracy per question type, as a table
+```
+
+Answers follow the Jev `/v1/systemone` response shape. Training data can be records like the
+above, records plus a shared question catalog, a long DataFrame, or a `.jsonl` / `.csv` /
+`.parquet` file. Labels go in `expected`, in a `label` inside each question, or as soft `gold`
+probabilities.
+
+Example notebooks, each comparing accuracy before and after training:
+
+- [quickstart.ipynb](https://github.com/ForwardMetric/sysone/blob/main/examples/quickstart.ipynb): synthetic support tickets, a few minutes;
+- bev-decision-150K, 18 domains, hard labels:
+  [decoder_bev_decision.ipynb](https://github.com/ForwardMetric/sysone/blob/main/examples/decoder_bev_decision.ipynb) (Qwen3) and
+  [encoder_bev_decision.ipynb](https://github.com/ForwardMetric/sysone/blob/main/examples/encoder_bev_decision.ipynb) (ModernBERT);
+- typed-decisions, soft labels from several raters:
+  [decoder_typed_decisions.ipynb](https://github.com/ForwardMetric/sysone/blob/main/examples/decoder_typed_decisions.ipynb) (Qwen3) and
+  [encoder_typed_decisions.ipynb](https://github.com/ForwardMetric/sysone/blob/main/examples/encoder_typed_decisions.ipynb) (ModernBERT).
+
+Notebooks other than the quickstart are named `<model type>_<dataset>.ipynb`.
+
+## Status
+
+This is an early version (0.2). Training covers every `tuning` mode:
+
+- `"head"`: the backbone is frozen, its outputs are computed once and cached (in memory, and on
+  disk with `cache_dir`), and only the decision head trains;
+- `"lora"`, `"qlora"` and `"full"`: adapters or whole layers of the backbone train along with the
+  head. These run on a laptop GPU (Apple MPS) for small datasets; a CUDA GPU is recommended for
+  full-size runs. `"qlora"` needs bitsandbytes and an NVIDIA GPU and falls back to `"lora"`
+  elsewhere, with a warning. It has trained in real 4-bit on a Colab GPU.
+
+`DecoderModel` (Qwen3) defaults to `"qlora"`. `EncoderModel` (ModernBERT) defaults to `"full"`:
+adapters barely moved ModernBERT, while full tuning reached 0.79 test accuracy on typed-decisions.
+
+Training stops at `epochs`, by early stopping, or at `target_loss`. A run that is interrupted
+(Ctrl-C), or saved and loaded, resumes exactly where it stopped. Calibration and `head="full"` are
+designed but not yet implemented.
+
+See [docs/DESIGN.md](https://github.com/ForwardMetric/sysone/blob/main/docs/DESIGN.md) for the full design: every parameter, the layouts,
+architectures, heads, training and checkpoint format.
+
+## Development
+
+```bash
+uv sync                  # or: pip install -e . with the dev dependencies
+uv run pytest            # fast tests on tiny random-weight models, no downloads
+uv run pytest -m slow    # end-to-end tests on the real base models (~1.8 GB download)
+uv run ruff check src tests
+```

sysone-0.2.0/README.md

@@ -0,0 +1,108 @@
+# sysone
+
+Fine-tune and calibrate "system one" decision models: small transformers that answer typed
+questions (choice, score, yes/no) about a piece of text in a single forward pass. You pick a base
+model, call `fit` on labelled rows and `predict` on new ones. sysone handles tokenization,
+position ids, attention masks, layer freezing, the decision head and the training loop.
+
+Supported base models: **ModernBERT** (`EncoderModel`) and **Qwen3** (`DecoderModel`). Others can
+be added by writing one architecture class.
+
+## Install
+
+```bash
+pip install sysone
+pip install "sysone[pandas]"   # also installs pandas, for the comparison tables of `compare`
+```
+
+On Linux and Windows this also installs bitsandbytes, for 4-bit training (`tuning="qlora"`).
+
+## Quickstart
+
+```python
+from sysone import DecoderModel
+
+questions = {
+    "team":     {"type": "choice", "instructions": "Which team should handle it?",
+                 "criteria": ["sales", "operations", "servicing"]},
+    "severity": {"type": "score", "instructions": "How severe is it?",
+                 "criteria": ["none", "minor", "major", "critical"]},
+    "refund":   {"type": "noul", "instructions": "Is the customer asking for a refund?"},
+}
+
+rows = [
+    {"state": "Hi, my order is stuck in the warehouse and our line is down.",
+     "category": "operations",
+     "questions": questions,
+     "expected": {"team": "operations", "severity": 3, "refund": False}},
+    # ... more rows; rows may mix different question sets
+]
+
+model = DecoderModel(tuning="head").fit(rows)
+
+model.predict("I'd like my money back for the broken unit.", questions)
+# {"answers": {"team": {"type": "choice", "choice": "servicing", "probabilities": {...}, "confidence": ...},
+#              "severity": {"type": "score", "score": 1.2, "legend": {...}, ...},
+#              "refund": {"type": "noul", "noul": 0.97, ...}},
+#  "usage": {"input_tokens": 118, "output_tokens": 0}}
+
+model.save("my-model")
+model = DecoderModel.load("my-model")
+```
+
+To measure the model on held-out labelled rows, and compare it with simple baselines:
+
+```python
+from sysone import baselines, compare
+
+results = baselines(test_rows, train=rows)      # random guess, average answer
+results["trained"] = model.evaluate(test_rows)
+compare(results)                                # accuracy per question type, as a table
+```
+
+Answers follow the Jev `/v1/systemone` response shape. Training data can be records like the
+above, records plus a shared question catalog, a long DataFrame, or a `.jsonl` / `.csv` /
+`.parquet` file. Labels go in `expected`, in a `label` inside each question, or as soft `gold`
+probabilities.
+
+Example notebooks, each comparing accuracy before and after training:
+
+- [quickstart.ipynb](https://github.com/ForwardMetric/sysone/blob/main/examples/quickstart.ipynb): synthetic support tickets, a few minutes;
+- bev-decision-150K, 18 domains, hard labels:
+  [decoder_bev_decision.ipynb](https://github.com/ForwardMetric/sysone/blob/main/examples/decoder_bev_decision.ipynb) (Qwen3) and
+  [encoder_bev_decision.ipynb](https://github.com/ForwardMetric/sysone/blob/main/examples/encoder_bev_decision.ipynb) (ModernBERT);
+- typed-decisions, soft labels from several raters:
+  [decoder_typed_decisions.ipynb](https://github.com/ForwardMetric/sysone/blob/main/examples/decoder_typed_decisions.ipynb) (Qwen3) and
+  [encoder_typed_decisions.ipynb](https://github.com/ForwardMetric/sysone/blob/main/examples/encoder_typed_decisions.ipynb) (ModernBERT).
+
+Notebooks other than the quickstart are named `<model type>_<dataset>.ipynb`.
+
+## Status
+
+This is an early version (0.2). Training covers every `tuning` mode:
+
+- `"head"`: the backbone is frozen, its outputs are computed once and cached (in memory, and on
+  disk with `cache_dir`), and only the decision head trains;
+- `"lora"`, `"qlora"` and `"full"`: adapters or whole layers of the backbone train along with the
+  head. These run on a laptop GPU (Apple MPS) for small datasets; a CUDA GPU is recommended for
+  full-size runs. `"qlora"` needs bitsandbytes and an NVIDIA GPU and falls back to `"lora"`
+  elsewhere, with a warning. It has trained in real 4-bit on a Colab GPU.
+
+`DecoderModel` (Qwen3) defaults to `"qlora"`. `EncoderModel` (ModernBERT) defaults to `"full"`:
+adapters barely moved ModernBERT, while full tuning reached 0.79 test accuracy on typed-decisions.
+
+Training stops at `epochs`, by early stopping, or at `target_loss`. A run that is interrupted
+(Ctrl-C), or saved and loaded, resumes exactly where it stopped. Calibration and `head="full"` are
+designed but not yet implemented.
+
+See [docs/DESIGN.md](https://github.com/ForwardMetric/sysone/blob/main/docs/DESIGN.md) for the full design: every parameter, the layouts,
+architectures, heads, training and checkpoint format.
+
+## Development
+
+```bash
+uv sync                  # or: pip install -e . with the dev dependencies
+uv run pytest            # fast tests on tiny random-weight models, no downloads
+uv run pytest -m slow    # end-to-end tests on the real base models (~1.8 GB download)
+uv run ruff check src tests
+```