hyper-connections 0.0.1__tar.gz

hyper_connections-0.0.1/.github/workflows/python-publish.yml

@@ -0,0 +1,36 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

hyper_connections-0.0.1/.gitignore

@@ -0,0 +1,171 @@
+# 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
+
+# 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
+
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+
+# PyPI configuration file
+.pypirc

hyper_connections-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Phil Wang
+
+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.

hyper_connections-0.0.1/PKG-INFO

@@ -0,0 +1,106 @@
+Metadata-Version: 2.4
+Name: hyper-connections
+Version: 0.0.1
+Summary: Hyper-Connections
+Project-URL: Homepage, https://pypi.org/project/hyper-connections/
+Project-URL: Repository, https://github.com/lucidrains/hyper-connections
+Author-email: Phil Wang <lucidrains@gmail.com>
+License: MIT License
+        
+        Copyright (c) 2024 Phil Wang
+        
+        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.
+License-File: LICENSE
+Keywords: artificial intelligence,deep learning,residual
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Requires-Dist: einops>=0.8.0
+Requires-Dist: torch>=2.3
+Provides-Extra: examples
+Provides-Extra: test
+Requires-Dist: pytest; extra == 'test'
+Description-Content-Type: text/markdown
+
+<img src="./hyper-connections.png" width="450px"></img>
+
+## Hyper Connections
+
+Attempt to make the multiple residual stream approach proposed by Hyper-Connections paper by Bytedance AI more accessible as a reusable library, and for following any new research in this direction.
+
+## Install
+
+```bash
+$ pip install hyper-connections
+```
+
+## Usage
+
+```python
+import torch
+from torch import nn
+
+# a single branch layer
+
+branch = nn.Linear(512, 512)
+
+# before
+
+residual = torch.randn(2, 1024, 512)
+
+residual = branch(residual) + residual
+
+# after, say 4 streams in paper
+
+from hyper_connections import HyperConnections
+
+expand_stream, reduce_stream = HyperConnections.get_expand_reduce_stream_functions(4)
+
+# 1. wrap your branch function
+
+hyper_conn_branch = HyperConnections(4, dim = 512, branch = branch)
+
+# 2. expand to 4 streams, this must be done before your trunk, typically a for-loop with many branch functions
+
+residual = expand_stream(residual)
+
+# 3. forward your residual as usual into the wrapped branch function(s)
+
+residual = hyper_conn_branch(residual) 
+
+# 4. reduce 4 streams with a summation, this has to be done after your for-loop trunk. for transformer, unsure whether to do before or after final norm
+
+residual = reduce_stream(residual)
+```
+
+## Citation
+
+```bibtex
+@article{Zhu2024HyperConnections,
+    title   = {Hyper-Connections},
+    author  = {Defa Zhu and Hongzhi Huang and Zihao Huang and Yutao Zeng and Yunyao Mao and Banggu Wu and Qiyang Min and Xun Zhou},
+    journal = {ArXiv},
+    year    = {2024},
+    volume  = {abs/2409.19606},
+    url     = {https://api.semanticscholar.org/CorpusID:272987528}
+}
+```

hyper_connections-0.0.1/README.md

@@ -0,0 +1,63 @@
+<img src="./hyper-connections.png" width="450px"></img>
+
+## Hyper Connections
+
+Attempt to make the multiple residual stream approach proposed by Hyper-Connections paper by Bytedance AI more accessible as a reusable library, and for following any new research in this direction.
+
+## Install
+
+```bash
+$ pip install hyper-connections
+```
+
+## Usage
+
+```python
+import torch
+from torch import nn
+
+# a single branch layer
+
+branch = nn.Linear(512, 512)
+
+# before
+
+residual = torch.randn(2, 1024, 512)
+
+residual = branch(residual) + residual
+
+# after, say 4 streams in paper
+
+from hyper_connections import HyperConnections
+
+expand_stream, reduce_stream = HyperConnections.get_expand_reduce_stream_functions(4)
+
+# 1. wrap your branch function
+
+hyper_conn_branch = HyperConnections(4, dim = 512, branch = branch)
+
+# 2. expand to 4 streams, this must be done before your trunk, typically a for-loop with many branch functions
+
+residual = expand_stream(residual)
+
+# 3. forward your residual as usual into the wrapped branch function(s)
+
+residual = hyper_conn_branch(residual) 
+
+# 4. reduce 4 streams with a summation, this has to be done after your for-loop trunk. for transformer, unsure whether to do before or after final norm
+
+residual = reduce_stream(residual)
+```
+
+## Citation
+
+```bibtex
+@article{Zhu2024HyperConnections,
+    title   = {Hyper-Connections},
+    author  = {Defa Zhu and Hongzhi Huang and Zihao Huang and Yutao Zeng and Yunyao Mao and Banggu Wu and Qiyang Min and Xun Zhou},
+    journal = {ArXiv},
+    year    = {2024},
+    volume  = {abs/2409.19606},
+    url     = {https://api.semanticscholar.org/CorpusID:272987528}
+}
+```

hyper_connections-0.0.1/hyper_connections/__init__.py

@@ -0,0 +1,3 @@
+from hyper_connections.hyper_connections import (
+    HyperConnections
+)

hyper_connections-0.0.1/hyper_connections/hyper_connections.py

@@ -0,0 +1,107 @@
+from __future__ import annotations
+from functools import partial
+from random import randrange
+
+import torch
+from torch import nn
+from torch.nn import Module
+import torch.nn.functional as F
+
+from einops import rearrange, repeat, reduce, einsum
+
+# helper functions
+
+def exists(v):
+    return v is not None
+
+def default(v, d):
+    return v if exists(v) else d
+
+# main class
+
+# hyper connection residual streams
+
+class HyperConnections(Module):
+    def __init__(
+        self,
+        num_residual_streams,
+        *,
+        dim,
+        branch: Module | None = None,
+        layer_index = None,
+        tanh = True,
+    ):
+        """
+        Appendix J, Algorithm2 in - https://arxiv.org/abs/2409.19606
+        """
+        super().__init__()
+
+        self.branch = branch
+
+        self.act = nn.Tanh() if tanh else nn.Identity()
+        self.norm = nn.RMSNorm(dim)
+
+        self.num_residual_streams = num_residual_streams
+        init_residual_index = default(layer_index, randrange(num_residual_streams)) % num_residual_streams # just choose one random residual stream if layer index not given
+
+        self.static_beta = nn.Parameter(torch.ones(num_residual_streams))
+
+        init_alpha0 = torch.zeros((num_residual_streams, 1))
+        init_alpha0[init_residual_index, 0] = 1.
+
+        self.static_alpha = nn.Parameter(torch.cat([init_alpha0, torch.eye(num_residual_streams)], dim = 1))
+
+        self.dynamic_alpha_fn = nn.Parameter(torch.zeros(dim, num_residual_streams + 1))
+        self.dynamic_alpha_scale = nn.Parameter(torch.ones(()) * 1e-2)
+        self.dynamic_beta_fn = nn.Parameter(torch.zeros(dim))
+        self.dynamic_beta_scale = nn.Parameter(torch.ones(()) * 1e-2)
+
+    @classmethod
+    def get_expand_reduce_stream_functions(cls, num_streams):
+        expand_fn = partial(repeat, pattern = 'b ... -> (b s) ...', s = num_streams)
+        reduce_fn = partial(reduce, pattern = '(b s) ... -> b ...', reduction = 'sum', s = num_streams)
+
+        return expand_fn, reduce_fn
+
+    def width_connection(self, residuals):
+        # width connection
+
+        residuals = rearrange(residuals, '(b s) ... d -> b ... s d', s = self.num_residual_streams)
+
+        normed = self.norm(residuals)
+
+        wc_weight = self.act(normed @ self.dynamic_alpha_fn)
+        dynamic_alpha = wc_weight * self.dynamic_alpha_scale
+        alpha = dynamic_alpha + self.static_alpha
+
+        dc_weight = self.act(normed @ self.dynamic_beta_fn)
+        dynamic_beta = dc_weight * self.dynamic_beta_scale
+        beta = dynamic_beta + self.static_beta
+
+        # width connection
+
+        mix_h = einsum(alpha, residuals, '... s t, ... s d -> ... t d')
+
+        branch_input, residuals = mix_h[..., 0, :], mix_h[..., 1:, :]
+
+        return branch_input, residuals, beta
+
+    def depth_connection(self, branch_output, residuals, beta):
+        # 'depth' connection
+
+        residuals = einsum(branch_output, beta, 'b ... d, b ... s -> b ... s d') + residuals
+        return rearrange(residuals, 'b ... s d -> (b s) ... d')
+
+    def forward(self, residuals, **branch_kwargs):
+
+        branch_input, residuals, beta = self.width_connection(residuals)
+
+        def add_residual_fn(branch_out):
+            return self.depth_connection(branch_out, residuals, beta)
+
+        if not exists(self.branch):
+            return branch_input, add_residual_fn
+
+        branch_output = self.branch(branch_input, **branch_kwargs)
+
+        return add_residual_fn(branch_output)

hyper_connections-0.0.1/pyproject.toml

@@ -0,0 +1,57 @@
+[project]
+name = "hyper-connections"
+version = "0.0.1"
+description = "Hyper-Connections"
+authors = [
+    { name = "Phil Wang", email = "lucidrains@gmail.com" }
+]
+readme = "README.md"
+requires-python = ">= 3.9"
+license = { file = "LICENSE" }
+keywords = [
+    'artificial intelligence',
+    'deep learning',
+    'residual',
+]
+
+classifiers=[
+    'Development Status :: 4 - Beta',
+    'Intended Audience :: Developers',
+    'Topic :: Scientific/Engineering :: Artificial Intelligence',
+    'License :: OSI Approved :: MIT License',
+    'Programming Language :: Python :: 3.9',
+]
+
+dependencies = [
+    "einops>=0.8.0",
+    "torch>=2.3",
+]
+
+[project.urls]
+Homepage = "https://pypi.org/project/hyper-connections/"
+Repository = "https://github.com/lucidrains/hyper-connections"
+
+[project.optional-dependencies]
+examples = []
+test = [
+    "pytest"
+]
+
+[tool.pytest.ini_options]
+pythonpath = [
+  "."
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.rye]
+managed = true
+dev-dependencies = []
+
+[tool.hatch.metadata]
+allow-direct-references = true
+
+[tool.hatch.build.targets.wheel]
+packages = ["hyper_connections"]