topologies 0.0.1__tar.gz

topologies-0.0.1/.gitignore

@@ -0,0 +1,20 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+/dist/
+/build/
+.venv/
+venv/
+.env
+.pytest_cache/
+.ruff_cache/
+.DS_Store
+/artifacts/
+/runs/
+/experiments/
+/data/
+/docs/
+/benchmarks/
+/examples/
+/scripts/
+/tests/

topologies-0.0.1/CHANGELOG.md

@@ -0,0 +1,41 @@
+# Changelog
+
+All notable changes to `topologies` are listed here.
+
+## 0.0.1 — 2026-10-20
+
+First public release: the training engine, data utilities, tokenizers, model constructor,
+generation, evaluation, experiments and introspection, plus the experimental catalog of
+reference implementations in `topologies.models` and `topologies.layers`.
+
+### Added
+- **Models**: `xmem` (XMem) ([paper](https://arxiv.org/abs/2207.07115))
+- **Models**: `consistency-model` (Consistency Models) ([paper](https://arxiv.org/abs/2303.01469))
+- **Models**: `distributional-q` (A Distributional Perspective on Reinforcement Learning) ([paper](https://arxiv.org/abs/1707.06887))
+- **Models**: `biggan` (Large Scale GAN Training for High Fidelity Natural Image Synthesis) ([paper](https://arxiv.org/abs/1809.11096))
+- **Models**: `dqn-family` (Playing Atari with Deep Reinforcement Learning) ([paper](https://arxiv.org/abs/1312.5602))
+- **Models**: `latent-diffusion` (High-Resolution Image Synthesis with Latent Diffusion Models) ([paper](https://arxiv.org/abs/2112.10752))
+- **Models**: `rgcn` (R-GCN) ([paper](https://arxiv.org/abs/1703.06103))
+- **Models**: `graphsage` (GraphSAGE Mean Aggregator) ([paper](https://arxiv.org/abs/1706.02216))
+- **Models**: `qmix` (QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning) ([paper](https://arxiv.org/abs/1803.11485))
+- **Models**: `lightgcn` (LightGCN) ([paper](https://arxiv.org/abs/2002.02126))
+- **Models**: `tft` (TFT) ([paper](https://arxiv.org/abs/1912.09363))
+- **Models**: `dcrnn` (DCRNN diffusion-GRU sequence primitive) ([paper](https://arxiv.org/abs/1707.01926))
+- **Components**: `cbam-gate` (CBAM channel-and-spatial attention block) ([paper](https://arxiv.org/abs/1807.06521))
+- **Components**: `topk-moe-layer` (Deterministic top-k MoE core; excludes noisy gating and balance losses) ([paper](https://arxiv.org/abs/1701.06538))
+- **Components**: `meshcnn` (MeshCNN: edge convolution and collapse pooling) ([paper](https://arxiv.org/abs/1809.05910))
+- **Components**: `crestereo` (CREStereo local correlation/disparity-offset primitive) ([paper](https://arxiv.org/abs/2203.11483))
+- **Components**: `paged-attention` (Paged Attention) ([paper](https://arxiv.org/abs/2309.06180))
+- **Components**: `conformer` (Conformer Convolution Module) ([paper](https://arxiv.org/abs/2005.08100))
+- **Components**: `v-trace` (IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures) ([paper](https://arxiv.org/abs/1802.01561))
+- **Components**: `cluster-gcn` (Cluster-GCN) ([paper](https://arxiv.org/abs/1905.07953))
+- **Components**: `film` (FiLM) ([paper](https://arxiv.org/abs/1709.07871))
+- **Losses**: `a2c` and `poly1-loss`.
+- **Training/docs**: Add a guide and an end-to-end `poly1-loss` quickstart.
+
+### Changed
+- Document how to enumerate catalog entries from Python.
+- Add a licensed catalog-listing example.
+
+### Fixed
+- Validate synthetic loader sample counts.

topologies-0.0.1/LICENSE

@@ -0,0 +1,191 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+Copyright 2026 Topologies Contributors
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

topologies-0.0.1/PKG-INFO

@@ -0,0 +1,143 @@
+Metadata-Version: 2.5
+Name: topologies
+Version: 0.0.1
+Summary: A continuously updated library of modern neural-network architectures on PyTorch
+Project-URL: Homepage, https://topologies.hackwhiz.net
+Project-URL: Documentation, https://topologies.hackwhiz.net
+Project-URL: Repository, https://github.com/yvsazh/topologies
+Project-URL: Issues, https://github.com/yvsazh/topologies/issues
+Author: Yaroslav Sazhchenko
+License: Apache-2.0
+License-File: LICENSE
+Keywords: architectures,deep-learning,neural-networks,pytorch,transformer
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+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: httpx>=0.27
+Requires-Dist: numpy>=1.23
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: tomli>=2.0; python_version < '3.11'
+Requires-Dist: torch<2.13,>=2.2
+Provides-Extra: all
+Requires-Dist: datasets>=2.14; extra == 'all'
+Requires-Dist: matplotlib>=3.7; extra == 'all'
+Requires-Dist: pillow>=9; extra == 'all'
+Requires-Dist: psutil>=5.9; extra == 'all'
+Requires-Dist: pyarrow>=12; extra == 'all'
+Requires-Dist: tensorboard>=2.12; extra == 'all'
+Requires-Dist: tokenizers>=0.15; extra == 'all'
+Requires-Dist: torchvision>=0.17; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: build; extra == 'dev'
+Requires-Dist: matplotlib>=3.7; extra == 'dev'
+Requires-Dist: pytest-timeout>=2.3; extra == 'dev'
+Requires-Dist: pytest>=8; extra == 'dev'
+Requires-Dist: ruff==0.16.9; extra == 'dev'
+Requires-Dist: twine; extra == 'dev'
+Provides-Extra: introspection
+Requires-Dist: matplotlib>=3.7; extra == 'introspection'
+Provides-Extra: nlp
+Requires-Dist: datasets>=2.14; extra == 'nlp'
+Requires-Dist: tokenizers>=0.15; extra == 'nlp'
+Provides-Extra: optimization
+Requires-Dist: torchao==0.18.0; extra == 'optimization'
+Provides-Extra: qt
+Requires-Dist: pyside6>=6.5; extra == 'qt'
+Provides-Extra: synth-parquet
+Requires-Dist: pyarrow>=12; extra == 'synth-parquet'
+Provides-Extra: system
+Requires-Dist: psutil>=5.9; extra == 'system'
+Provides-Extra: tensorboard
+Requires-Dist: tensorboard>=2.12; extra == 'tensorboard'
+Provides-Extra: vision
+Requires-Dist: pillow>=9; extra == 'vision'
+Requires-Dist: torchvision>=0.17; extra == 'vision'
+Provides-Extra: visualization
+Requires-Dist: matplotlib>=3.7; extra == 'visualization'
+Description-Content-Type: text/markdown
+
+# topologies
+
+A PyTorch toolbox for building, training, comparing and inspecting neural-network
+architectures — plus a catalog of small reference implementations (GPT, LLaMA, ViT,
+ResNet, BERT, Mamba, ...).
+
+> **Early alpha (v0.0.1).** The toolbox — training engine, data utilities, tokenizers,
+> model constructor, generation, evaluation, experiments, introspection — is tested.
+> Catalog models in `topologies.models` / `topologies.layers` are experimental
+> references: importable, trainable and smoke-tested, but not validated against the papers.
+> APIs may change between releases.
+
+## Install
+
+```bash
+pip install topologies                 # core
+pip install "topologies[all]"          # + vision, nlp, tensorboard, visualization, ...
+```
+
+Python 3.10–3.13, PyTorch `>=2.2,<2.13`.
+
+## Quickstart
+
+Train a tiny language model on any text corpus:
+
+```python
+from topologies import Trainer, build, data, generate, train_tokenizer
+from topologies.nn import TransformerLM
+
+docs = data.read_documents("corpus.txt")
+train_docs, val_docs = data.train_val_split(docs, 0.1)
+tok = train_tokenizer(train_docs, kind="bpe", vocab_size=2048)
+model = build(TransformerLM, "tiny", vocab_size=tok.vocab_size, max_seq=128)
+
+trainer = Trainer(model, data.lm_dataset(train_docs, tok, 128),
+                  data.lm_dataset(val_docs, tok, 128),
+                  tokenizer=tok, batch_size=32, max_epochs=20, lr=1e-3)
+trainer.fit()
+trainer.save_pretrained("artifacts/tiny-lm")
+print(generate(model, "Once upon a time", tokenizer=tok, max_new_tokens=100, top_k=40))
+```
+
+Compare many configurations with one declaration — the library runs every trial
+(resumably), then ranks and explains the results:
+
+```python
+from topologies import Experiment
+from topologies.experiments import LanguageModeling, Variant
+
+exp = Experiment("arch-x-tokenizer",
+                 task=LanguageModeling(docs, val_fraction=0.1, block_size=128),
+                 axes={"model": [TransformerLM,
+                                 Variant("llama-ish", TransformerLM, pos="rope",
+                                         norm="rms", activation="swiglu")],
+                       "tokenizer": ["char", "bpe:1k", "bpe:4k"]},
+                 target_params="1M", train_for="2 epochs", seeds=2)
+exp.run().show()
+```
+
+## What's inside
+
+- `topologies.nn` — composable stacks, presets and parameter budgets
+- `Trainer`, `generate`, evaluation, optimization and quantization helpers
+- `topologies.data`, dataset catalog, tokenizers
+- `Experiment` — sweeps, leaderboards, pivots, importance analysis
+- `topologies.introspection` / `topologies.visualization` — look inside trained models
+- `topologies` CLI — `topologies --help`
+
+## Links
+
+- Documentation: <https://topologies.hackwhiz.net>
+- Repository and issues: <https://github.com/yvsazh/topologies>
+
+## License
+
+Apache-2.0

topologies-0.0.1/README.md

@@ -0,0 +1,76 @@
+# topologies
+
+A PyTorch toolbox for building, training, comparing and inspecting neural-network
+architectures — plus a catalog of small reference implementations (GPT, LLaMA, ViT,
+ResNet, BERT, Mamba, ...).
+
+> **Early alpha (v0.0.1).** The toolbox — training engine, data utilities, tokenizers,
+> model constructor, generation, evaluation, experiments, introspection — is tested.
+> Catalog models in `topologies.models` / `topologies.layers` are experimental
+> references: importable, trainable and smoke-tested, but not validated against the papers.
+> APIs may change between releases.
+
+## Install
+
+```bash
+pip install topologies                 # core
+pip install "topologies[all]"          # + vision, nlp, tensorboard, visualization, ...
+```
+
+Python 3.10–3.13, PyTorch `>=2.2,<2.13`.
+
+## Quickstart
+
+Train a tiny language model on any text corpus:
+
+```python
+from topologies import Trainer, build, data, generate, train_tokenizer
+from topologies.nn import TransformerLM
+
+docs = data.read_documents("corpus.txt")
+train_docs, val_docs = data.train_val_split(docs, 0.1)
+tok = train_tokenizer(train_docs, kind="bpe", vocab_size=2048)
+model = build(TransformerLM, "tiny", vocab_size=tok.vocab_size, max_seq=128)
+
+trainer = Trainer(model, data.lm_dataset(train_docs, tok, 128),
+                  data.lm_dataset(val_docs, tok, 128),
+                  tokenizer=tok, batch_size=32, max_epochs=20, lr=1e-3)
+trainer.fit()
+trainer.save_pretrained("artifacts/tiny-lm")
+print(generate(model, "Once upon a time", tokenizer=tok, max_new_tokens=100, top_k=40))
+```
+
+Compare many configurations with one declaration — the library runs every trial
+(resumably), then ranks and explains the results:
+
+```python
+from topologies import Experiment
+from topologies.experiments import LanguageModeling, Variant
+
+exp = Experiment("arch-x-tokenizer",
+                 task=LanguageModeling(docs, val_fraction=0.1, block_size=128),
+                 axes={"model": [TransformerLM,
+                                 Variant("llama-ish", TransformerLM, pos="rope",
+                                         norm="rms", activation="swiglu")],
+                       "tokenizer": ["char", "bpe:1k", "bpe:4k"]},
+                 target_params="1M", train_for="2 epochs", seeds=2)
+exp.run().show()
+```
+
+## What's inside
+
+- `topologies.nn` — composable stacks, presets and parameter budgets
+- `Trainer`, `generate`, evaluation, optimization and quantization helpers
+- `topologies.data`, dataset catalog, tokenizers
+- `Experiment` — sweeps, leaderboards, pivots, importance analysis
+- `topologies.introspection` / `topologies.visualization` — look inside trained models
+- `topologies` CLI — `topologies --help`
+
+## Links
+
+- Documentation: <https://topologies.hackwhiz.net>
+- Repository and issues: <https://github.com/yvsazh/topologies>
+
+## License
+
+Apache-2.0

topologies-0.0.1/pyproject.toml

@@ -0,0 +1,146 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "topologies"
+dynamic = ["version"]
+description = "A continuously updated library of modern neural-network architectures on PyTorch"
+readme = "README.md"
+license = { text = "Apache-2.0" }
+requires-python = ">=3.10"
+authors = [{ name = "Yaroslav Sazhchenko" }]
+keywords = ["pytorch", "deep-learning", "neural-networks", "architectures", "transformer"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Science/Research",
+  "License :: OSI Approved :: Apache Software License",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+  "torch>=2.2,<2.13",  # upper bound = newest torch the local suite passes on; raise after testing
+  "numpy>=1.23",
+  "pydantic>=2.0",
+  "PyYAML>=6.0",
+  "httpx>=0.27",  # artifact-store HTTP integration (only via topologies.artifact_store.client)
+  "tomli>=2.0; python_version < '3.11'",  # tomllib backport (utils.config, artifact_store)
+]
+urls = { Homepage = "https://topologies.hackwhiz.net", Documentation = "https://topologies.hackwhiz.net", Repository = "https://github.com/yvsazh/topologies", Issues = "https://github.com/yvsazh/topologies/issues" }
+
+[project.optional-dependencies]
+dev = ["pytest>=8", "pytest-timeout>=2.3", "ruff==0.16.9", "build", "twine", "matplotlib>=3.7"]
+vision = ["torchvision>=0.17", "pillow>=9"]
+nlp = ["tokenizers>=0.15", "datasets>=2.14"]
+tensorboard = ["tensorboard>=2.12"]
+system = ["psutil>=5.9"]
+optimization = ["torchao==0.18.0"]
+visualization = ["matplotlib>=3.7"]
+introspection = ["topologies[visualization]"]  # alias: figures for topologies.introspection
+qt = ["PySide6>=6.5"]  # optional GUI reference example only; core visualization stays Qt-free
+synth-parquet = ["pyarrow>=12"]  # optional: parquet shards and exports
+all = ["topologies[vision,nlp,tensorboard,system,synth-parquet,visualization]"]
+
+[project.scripts]
+topologies = "topologies.cli:main"
+
+[tool.hatch.version]
+path = "src/topologies/__init__.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/topologies"]
+include = ["src/topologies/training/model_recipes.json"]
+ignore-vcs = true
+
+[tool.hatch.build.targets.sdist]
+# Explicit allow-list: package only the library and its public metadata.
+include = [
+  "/src/topologies",
+  "/README.md",
+  "/CHANGELOG.md",
+  "/LICENSE",
+  "/pyproject.toml",
+]
+exclude = ["__pycache__"]
+
+[tool.ruff]
+target-version = "py310"
+line-length = 100
+extend-exclude = ["src/topologies/models/[!_]*.py", "src/topologies/layers/[!_]*.py"]
+
+[tool.ruff.lint]
+# Explicit rule set (H-P07): the rules ruff 0.16.9 enabled by default when this was
+# written, frozen so a ruff upgrade cannot silently change what CI enforces.
+select = [
+  "ASYNC100", "ASYNC105", "ASYNC115", "ASYNC116", "ASYNC210", "ASYNC220", "ASYNC221",
+  "ASYNC222", "ASYNC230", "ASYNC251", "B002", "B003", "B004", "B005", "B006", "B008",
+  "B009", "B010", "B012", "B013", "B014", "B015", "B016", "B017", "B018", "B019", "B020",
+  "B021", "B022", "B023", "B025", "B026", "B029", "B030", "B031", "B032", "B033", "B035",
+  "B039", "BLE001", "C400", "C401", "C402", "C403", "C404", "C405", "C406", "C408", "C409",
+  "C410", "C411", "C413", "C414", "C415", "C417", "C418", "C419", "D419", "DTZ001", "DTZ002",
+  "DTZ004", "DTZ005", "DTZ006", "DTZ007", "DTZ011", "DTZ012", "DTZ901", "E722", "E902",
+  "EXE002", "EXE004", "EXE005", "F401", "F402", "F404", "F407", "F501", "F502", "F503",
+  "F504", "F505", "F506", "F507", "F508", "F509", "F521", "F522", "F523", "F524", "F525",
+  "F541", "F601", "F602", "F621", "F622", "F631", "F632", "F633", "F634", "F701", "F702",
+  "F704", "F706", "F707", "F811", "F821", "F822", "F823", "F841", "F842", "F901", "FA100",
+  "FA102", "FLY002", "FURB105", "FURB122", "FURB129", "FURB132", "FURB136", "FURB157",
+  "FURB161", "FURB162", "FURB163", "FURB166", "FURB167", "FURB168", "FURB169", "FURB177",
+  "FURB181", "FURB188", "FURB192", "G010", "G101", "G201", "G202", "I001", "INT001",
+  "INT002", "INT003", "ISC004", "LOG001", "LOG002", "LOG009", "LOG014", "LOG015", "N999",
+  "PERF101", "PERF102", "PERF402", "PGH005", "PIE790", "PIE794", "PIE796", "PIE800",
+  "PIE804", "PIE807", "PIE808", "PIE810", "PLC0105", "PLC0131", "PLC0132", "PLC0205",
+  "PLC0206", "PLC0208", "PLC0414", "PLC3002", "PLE0100", "PLE0101", "PLE0115", "PLE0116",
+  "PLE0117", "PLE0118", "PLE0303", "PLE0304", "PLE0305", "PLE0307", "PLE0308", "PLE0309",
+  "PLE0604", "PLE0605", "PLE0643", "PLE0704", "PLE1132", "PLE1142", "PLE1205", "PLE1206",
+  "PLE1300", "PLE1307", "PLE1310", "PLE1507", "PLE1519", "PLE1520", "PLE1700", "PLE2502",
+  "PLE2510", "PLE2512", "PLE2513", "PLE2514", "PLE2515", "PLR0124", "PLR0133", "PLR0206",
+  "PLR1704", "PLR1708", "PLR1711", "PLR1716", "PLR1722", "PLR1730", "PLR1733", "PLR1736",
+  "PLR2044", "PLW0120", "PLW0127", "PLW0128", "PLW0129", "PLW0131", "PLW0133", "PLW0177",
+  "PLW0211", "PLW0245", "PLW0406", "PLW0602", "PLW0604", "PLW0642", "PLW0711", "PLW1501",
+  "PLW1507", "PLW1508", "PLW1509", "PLW1510", "PLW2101", "PT010", "PT014", "PT020", "PT025",
+  "PT026", "PT031", "PTH124", "PTH210", "PYI001", "PYI002", "PYI003", "PYI004", "PYI005",
+  "PYI006", "PYI007", "PYI008", "PYI009", "PYI010", "PYI012", "PYI013", "PYI015", "PYI016",
+  "PYI017", "PYI018", "PYI019", "PYI020", "PYI025", "PYI026", "PYI029", "PYI030", "PYI032",
+  "PYI033", "PYI034", "PYI035", "PYI036", "PYI041", "PYI042", "PYI043", "PYI044", "PYI045",
+  "PYI046", "PYI047", "PYI048", "PYI049", "PYI050", "PYI052", "PYI055", "PYI057", "PYI058",
+  "PYI059", "PYI061", "PYI062", "PYI063", "PYI064", "PYI066", "RET501", "RUF007", "RUF008",
+  "RUF009", "RUF010", "RUF013", "RUF015", "RUF016", "RUF017", "RUF018", "RUF019", "RUF020",
+  "RUF022", "RUF023", "RUF024", "RUF026", "RUF028", "RUF030", "RUF032", "RUF033", "RUF034",
+  "RUF040", "RUF041", "RUF046", "RUF048", "RUF049", "RUF051", "RUF053", "RUF057", "RUF058",
+  "RUF059", "RUF063", "RUF068", "RUF100", "RUF101", "RUF200", "S102", "S110", "S112",
+  "SIM101", "SIM102", "SIM103", "SIM107", "SIM113", "SIM114", "SIM115", "SIM117", "SIM118",
+  "SIM201", "SIM202", "SIM208", "SIM210", "SIM211", "SIM220", "SIM221", "SIM222", "SIM223",
+  "SIM401", "SIM905", "SIM911", "T100", "TC004", "TC005", "TC007", "TC010", "TRY002",
+  "TRY004", "TRY201", "TRY203", "TRY401", "UP001", "UP003", "UP004", "UP005", "UP006",
+  "UP007", "UP008", "UP009", "UP010", "UP011", "UP012", "UP014", "UP017", "UP018", "UP019",
+  "UP020", "UP021", "UP022", "UP023", "UP024", "UP025", "UP026", "UP028", "UP029", "UP030",
+  "UP031", "UP032", "UP033", "UP034", "UP035", "UP036", "UP037", "UP039", "UP040", "UP041",
+  "UP043", "UP044", "UP045", "UP046", "UP047", "UP049", "UP050", "W605", "YTT101", "YTT102",
+  "YTT103", "YTT201", "YTT202", "YTT203", "YTT204", "YTT301", "YTT302", "YTT303",
+]
+# DTZ003: utcnow()+"Z" is the deliberate ISO convention used across registry/runs.
+# PLR0402: `import torch.nn as nn` is the universal PyTorch idiom.
+ignore = ["RUF012", "DTZ003", "PLR0402", "EXE001"]
+
+[tool.ruff.lint.per-file-ignores]
+"src/topologies/training/charformer_data.py" = ["I001"]
+"src/topologies/training/recipes/__init__.py" = ["I001"]
+"src/topologies/training/recipes/permutation_lm.py" = ["I001", "RUF059", "TRY004"]
+"src/topologies/training/recipes/spanbert.py" = ["I001", "TRY004"]
+"src/topologies/validation/catalog_workflows.py" = ["F401", "I001"]
+"tests/test_catalog_workflows.py" = ["S102"]
+"tests/test_component_workflows.py" = ["I001", "S102", "SIM102"]
+"tests/test_modernbert_usage_projection.py" = ["S102"]
+"tests/test_xlnet_models.py" = ["S102"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+markers = ["slow: long-running tests (deselect with -m 'not slow')"]
+# New deprecations raised from our own modules fail the suite; third-party ones stay warnings.
+filterwarnings = ["error::DeprecationWarning:topologies.*"]