rxnn 0.1.0__py3-none-any.whl

rxnn-0.1.0.dist-info/LICENSE

@@ -0,0 +1,201 @@
+                                 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
+       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  owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the  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  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  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
+       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 , 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  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
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024-2025 Adam Filipek
+
+   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.

rxnn-0.1.0.dist-info/METADATA

@@ -0,0 +1,257 @@
+Metadata-Version: 2.3
+Name: rxnn
+Version: 0.1.0
+Summary: RxNN: Reactive Neural Networks Platform
+License: Apache-2.0
+Keywords: deep-learning,ai,machine-learning
+Author: Adam Filipek
+Author-email: adamfilipek@rxai.dev
+Requires-Python: >=3.10
+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
+Requires-Dist: datasets (>=3.5.0,<4.0.0)
+Requires-Dist: flash-attention (>=1.0.0,<2.0.0)
+Requires-Dist: huggingface-hub (>=0.30.0,<0.31.0)
+Requires-Dist: tensorboard (>=2.19.0,<3.0.0)
+Requires-Dist: tokenizers (>=0.21.0,<0.22.0)
+Requires-Dist: torch (>=2.6.0,<3.0.0)
+Requires-Dist: transformers (>=4.51.0,<5.0.0)
+Project-URL: Homepage, https://rxai.dev/rxnn
+Project-URL: Repository, https://github.com/RxAI-dev/rxnn/python
+Description-Content-Type: text/markdown
+
+<img src="logo_rxai.webp" width="300" />
+<img src="logo_rxnn.webp" width="300" />
+
+# Reactive AI - RxNN
+## Reactive Neural Networks Platform
+
+RxNN is AI/DeepLearning development platform made for Reactive Neural Networks and Event-driven AI, introduced by Reactive AI.
+
+## Reactive Neural Networks and Event-driven AI
+Reactive neural networks (RxNN) are a new family of memory-augmented neural networks that combine classical deep learning
+algorithms with reactive communication patterns. In Event-driven AI, input data (sequence) is treated as event, and memory
+state has to be kept between events/interactions. Technically, it's a specific kind of RNN that's storing data between
+processed sequences, instead of between sequence elements like in regular RNN. Then, their recurrence is on a higher level.
+In the case of reactive communication patterns, RxRNNs are stateful reactive data sources that you have to connect before
+you can send and receive messages.
+While RxNNs are using some RNN concepts, they are rather made to extend Transformer language/multi-modal models. In our
+opinion, the biggest downside of current LLMs is their stateless nature - conversational models have to process full chat
+history on every interaction! That's not real-time processing, and it's not how human's awareness is working. In RxNN based
+transformers, model is processing single messages, while all the previous interactions history should be saved and read
+from memory. That features are required for **Weak** Reactive Neural Networks specification, and it will be the first major
+step in transition from language models to awareness models - in Reactive AI ecosystem, it will be introduced in Reactive
+Transformer architecture.
+
+Additionally, to achieve awareness, **Strong** Reactive Neural Networks are working in reactive infinite reasoning loop,
+that's generating Infinite Chain-of-Thoughts and is communicating in push-based mode (model decides if and when return output).
+
+Reactive communication patterns in RxNN models are adapted to handle asynchronous nature of model - after it finish generating
+sequence, it has to process it and save it in memory, but it could be done in background.
+
+                                 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
+       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  owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the  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  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  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
+       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 , 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  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
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024-2025 Adam Filipek
+
+   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.
+

rxnn-0.1.0.dist-info/RECORD

@@ -0,0 +1,23 @@
+src/experimental/attention.py,sha256=BxNFOqQcz3v_wzn5n07UuZQIRLkVxNJEqZedvv8K_WQ,5633
+src/memory/norm.py,sha256=Ofl8Q5NYEF9GQeO0bhM43tkTW91J0y6TSvTAOYMgloM,6278
+src/memory/stm.py,sha256=EsD8slSP4_9dLuq6aFPDmuFe8PWilxh90so5Z3nm-ig,2057
+src/rxt/models.py,sha256=jmxdQ0FHjqYKVrwoEURez1WV-0quv-5q2eBFGhXyJM0,6932
+src/training/base.py,sha256=DHankUIta0wWuczN1O0pK7MCis9dYUvc5dAFkap9t5Q,11030
+src/training/bml.py,sha256=Al-qcQYQ-GsdXfa1DB1YF2vGJKgfIfMBy0GlZabUz1Y,14579
+src/training/callbacks.py,sha256=VAjwaAoSgYgU5WV9FybINznLhBRX9WMWNdgS41FtNfY,21093
+src/training/dataset.py,sha256=vQ5mDF3bA0HXya474n4D4iL8Mn3AEpJukgzFNVkxjGU,5106
+src/training/scheduler.py,sha256=ow6oALzWjWQmHSpcJEjv6tg4g4CDMvr73TypxfcefMc,712
+src/training/tokenizer.py,sha256=4Y41f07uo2KPA_7bp3FCcwGKbXoS2hsckOoXUsXfQxY,8052
+src/transformers/attention.py,sha256=fqNziF9gZOLM-RnrkaCOkel8w-EkLEAOiv7WO5G6IMw,14021
+src/transformers/ff.py,sha256=jJnuBDsnnX5uYC_WZH8cXAYrMnz0P-iX7MwcPivjRtI,2533
+src/transformers/layers.py,sha256=PBlnQzS_cyaAjEAQEgdsttSXhtwWsx4PKxRAtPMhTbY,5361
+src/transformers/mask.py,sha256=J0cfLVLt3SzS2ra3KcY4khrkhI975Dw4CjpUi3Sn25s,419
+src/transformers/models.py,sha256=aVY3YTKGKvwzRraduhIgO8phPDRkJytdTglDQm_U2_c,6716
+src/transformers/moe.py,sha256=JQ5QSX4FS7S-fqB7-s1ZmJbPpOeD_Injn8o4vo7wGQE,4936
+src/transformers/positional.py,sha256=2l38RS0Dini3f6Z3LUHr3XwWzg1UK7fO2C6wazWDAYU,4292
+src/transformers/sampler.py,sha256=wSz_1wNloqtuiix5w2Mcsj5NhaO9QlY0j__TVG7wJnM,3938
+src/utils.py,sha256=d5U8i5ukovgDyqiycc2AoxObTz_eF_bgo2MKvdtJ98s,467
+rxnn-0.1.0.dist-info/LICENSE,sha256=C8coDFIUYuOcke4JLPwTqahQUCyXyGq6WOaigOkx8tY,11275
+rxnn-0.1.0.dist-info/METADATA,sha256=HAt-q9BKoWBJNYr9Ht_sbBcPWMttuEMQmYj4RDrsFrA,14486
+rxnn-0.1.0.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+rxnn-0.1.0.dist-info/RECORD,,

rxnn-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: poetry-core 2.1.2
+Root-Is-Purelib: true
+Tag: py3-none-any

src/experimental/attention.py

@@ -0,0 +1,133 @@
+import torch
+from torch import nn
+from src.transformers.attention import MultiHeadAttention
+
+class FlexAttention(MultiHeadAttention):
+    def __init__(
+        self,
+        embed_dim: int,
+        num_heads: int,
+        num_global_tokens: int = 16,
+        window_size: int = 128,
+        **kwargs
+    ):
+        super().__init__(embed_dim, num_heads, **kwargs)
+        self.num_global_tokens = num_global_tokens
+        self.window_size = window_size
+        self.global_tokens = nn.Parameter(torch.zeros(1, num_global_tokens, embed_dim))
+
+    def forward(self, query: torch.Tensor, key: torch.Tensor, value: torch.Tensor, mask=None):
+        b, t, d = query.size()
+        head_dim = d // self.num_heads
+
+        # Split into global and local
+        x = torch.cat([self.global_tokens.expand(b, -1, -1), query], dim=1)
+        seq_len = x.size(1)
+        num_windows = (seq_len - self.num_global_tokens + self.window_size - 1) // self.window_size
+
+        # Project Q, K, V
+        q, k, v = self._forward_qkv(x, key, value, b, seq_len, d)
+
+        # Process Global-to-Global Attention
+        global_q = q[:, :, :self.num_global_tokens]  # [B, H, G, head_dim]
+        global_k = k[:, :, :self.num_global_tokens]
+        global_v = v[:, :, :self.num_global_tokens]
+        global_attn = self._calculate_attn_weights(global_q, global_k, d) @ global_v
+
+        # Process Global-to-Local Attention
+        local_k = k[:, :, self.num_global_tokens:]  # [B, H, (num_windows * window_size), head_dim]
+        local_v = v[:, :, self.num_global_tokens:]
+        # Apply RoPE to local_k if needed
+        if self.rope:
+            # Compute frequencies for entire local sequence
+            local_k = self.rope.forward_one(local_k)
+
+        global_local_attn = self._calculate_attn_weights(global_q, local_k, d) @ local_v
+
+        # Process Local-to-Local Attention (per window)
+        local_q = q[:, :, self.num_global_tokens:]  # [B, H, (num_windows * window_size), head_dim]
+        local_q = local_q.view(b, self.num_heads, num_windows, self.window_size, head_dim)
+        local_k = local_k.view(b, self.num_heads, num_windows, self.window_size, head_dim)
+        local_v = local_v.view(b, self.num_heads, num_windows, self.window_size, head_dim)
+
+        local_attn = []
+        for i in range(num_windows):
+            window_q = local_q[:, :, i]  # [B, H, window_size, head_dim]
+            window_k = local_k[:, :, i]
+            window_v = local_v[:, :, i]
+
+            # Apply RoPE to window_q and window_k
+            if self.rope:
+                # Compute frequencies for this window
+                window_q, window_k = self.rope(window_q, window_k)
+
+            # Calculate attention for this window
+            attn = self._calculate_attn_weights(window_q, window_k, d)
+            attn_i = torch.einsum('bhij, bhjd -> bhid', attn, window_v)
+            local_attn.append(attn_i)
+        local_attn = torch.cat(local_attn, dim=2).view(b, self.num_heads, -1, head_dim)
+
+        # Combine all attention outputs
+        combined_attn = torch.cat([global_attn, global_local_attn, local_attn], dim=2)
+        output = self._calculate_output(combined_attn, v, b, t, d)
+        return self.out_proj(output)
+
+class InfiniteAttention(MultiHeadAttention):
+    def __init__(
+        self,
+        embed_dim: int,
+        num_heads: int,
+        kernel_size: int = 128,
+        use_rotary: bool = True,
+        **kwargs
+    ):
+        super().__init__(embed_dim, num_heads, **kwargs)
+        self.kernel_size = kernel_size
+        self.use_rotary = use_rotary
+        self.register_buffer("fourier_basis", self._init_fourier_basis(embed_dim))
+
+    def _init_fourier_basis(self, embed_dim):
+        # Initialize Fourier features for positional encoding
+        freqs = torch.randn(embed_dim // 2)
+        return freqs
+
+    def _positional_encodings(self, x: torch.Tensor, device: torch.device):
+        """Generate positional encodings for arbitrary sequence length."""
+        seq_len = x.size(1)
+        pos = torch.arange(seq_len, device=device).float()
+        fourier_features = torch.einsum("d, s -> sd", self.fourier_basis, pos)
+        pe = torch.cat([torch.sin(fourier_features), torch.cos(fourier_features)], dim=1)
+        return pe.unsqueeze(0).expand(x.size(0), -1, -1)
+
+    def forward(self, query: torch.Tensor, key: torch.Tensor, value: torch.Tensor, mask=None):
+        b, t, d = query.size()
+        # Add positional encodings
+        pe = self._positional_encodings(query, query.device)
+        query = query + pe
+        key = key + pe
+
+        # Split into chunks for kernel-based attention
+        chunks = []
+        for i in range(0, t, self.kernel_size):
+            chunk = query[:, i:i + self.kernel_size]
+            chunks.append(chunk)
+
+        # Compute attention for each chunk
+        attn_output = []
+        for chunk in chunks:
+            q, k, v = self._forward_qkv(chunk, key, value, b, chunk.size(1), d)
+            # Use kernel approximation (e.g., Performer)
+            attn = self._performer_attention(q, k, v)
+            attn_output.append(attn)
+
+        # Concatenate and apply output projection
+        output = torch.cat(attn_output, dim=1)
+        return self.out_proj(output)
+
+    def _performer_attention(self, q: torch.Tensor, k: torch.Tensor, v: torch.Tensor):
+        # Performer kernel approximation (simplified)
+        # TODO: Replace with preferred kernel method
+        q = q / (q.shape[-1] ** 0.5)
+        attn = torch.einsum('b h i d, b h j d -> b h i j', q, k)
+        attn = torch.softmax(attn, dim=-1)
+        return torch.einsum('b h i j, b h j d -> b h i d', attn, v)