ebm-splats 2.0.0__tar.gz

ebm_splats-2.0.0/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
+      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
+
+   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 2026 Brian Tomas Schwabauer
+
+   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.

ebm_splats-2.0.0/PKG-INFO

@@ -0,0 +1,108 @@
+Metadata-Version: 2.4
+Name: ebm-splats
+Version: 2.0.0
+Summary: Energy-Based Model with Gaussian Splats on a 640D hypersphere — archived research project
+Author: Brian Schwabauer
+License: Apache-2.0
+Keywords: energy-based-model,gaussian-splats,riemannian,langevin-dynamics,sentence-embeddings
+Classifier: Development Status :: 7 - Inactive
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.0
+Requires-Dist: numpy>=1.24
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Provides-Extra: nlp
+Requires-Dist: sentence-transformers>=2.2; extra == "nlp"
+Requires-Dist: transformers>=4.30; extra == "nlp"
+Requires-Dist: datasets>=2.10; extra == "nlp"
+Provides-Extra: gpu
+Requires-Dist: faiss-cpu>=1.7; extra == "gpu"
+Provides-Extra: service
+Requires-Dist: flask>=3.0; extra == "service"
+Provides-Extra: all
+Requires-Dist: ebm-splats[dev,gpu,nlp,service]; extra == "all"
+Dynamic: license-file
+
+# EBM-Splats
+
+> **Status: Research complete.** Phase 1-2 empirical tests finished. Energy-guided generation continued in [m2m-energy-fields](https://github.com/schwabauerbriantomas-gif/m2m-energy-fields).
+
+Energy-Based Model with Gaussian Splats on a 640D hypersphere. Explores distributional representations for latent spaces, sampling via Langevin dynamics and Rectified Flow.
+
+## Project Phases
+
+### Phase 1: EBM + PGLF (April 2026) — Discarded
+
+EBM with Gaussian splats as attractors on S^639 + PGLF (projection over MiniLM with contrastive loss).
+
+**Result:** PGLF degraded MiniLM on STS-B (-4.7%). Projection over pre-trained embeddings always destroys geometry.
+
+### Phase 1 Empirical: Discard Tests (July 2026)
+
+3 empirical tests to discard or confirm alternatives. RTX 3090, real data.
+
+| Test | Hypothesis | Result | Verdict |
+|------|-----------|-----------|-----------|
+| PGLF Grid (14 configs) | Can any config beat MiniLM? | 0/14 beat baseline (0.8672) | **DISCARDED** |
+| OOD Detection | Does EBM energy detect OOD? | AUROC=1.0 but NN=0.999 | **NO ADVANTAGE** |
+| RF vs Langevin | Does RF solve the speed bottleneck? | 24-29x faster, better quality | **CONFIRMED** |
+
+**Key finding:** The argument that "200 Langevin steps per token" is prohibitive no longer applies. Rectified Flow with 1-2 steps produces better samples than Langevin with 200 steps, 24x faster.
+
+### Phase 2: Energy-Guided Generation (July 2026)
+
+EBM as a generator that learns its own latent space (not as a layer over pre-trained models), with sampling via Rectified Flow.
+
+| Test | Hypothesis | Result | Verdict |
+|------|-----------|-----------|-----------|
+| Energy-Guided Generation | Can energy manipulation steer generation? | 100% topic control at gs=1.0-2.0 | **CONFIRMED** |
+| Concept Composition | Can multiple concepts be combined? | 4/4 mechanisms work | **CONFIRMED** |
+
+**Composition results:**
+- Equal blend (A+B): balanced similarity to both topics
+- Weighted (70/30): asymmetric control confirmed
+- Suppression (A−B): sim_B dropped from 0.44 to −0.29
+- Triple (A+B+C): all three topics active (sim > 0.48)
+
+**EBM + RF enables semantic arithmetic on the hypersphere.**
+
+## Repository Structure
+
+```
+├── src/ebm/               # Core EBM modules (geometry, splats, energy, model, etc.)
+├── pglf/                  # PGLF (archived — discarded empirically)
+├── scripts/               # Training and generation scripts
+├── tests/
+│   ├── phase1_t11_rf_vs_langevin.py    # RF vs Langevin benchmark
+│   ├── phase1_t12_pglf_grid.py         # PGLF grid search
+│   ├── phase1_t13_ood_energy.py        # OOD detection test
+│   ├── phase2_energy_guided.py         # Energy-guided generation test
+│   ├── phase2_composition.py           # Concept composition test
+│   └── t*_results.jsonl                # Raw results
+├── docs/
+│   ├── PHASE1_RESULTS.md  # Full Phase 1 report
+│   ├── PHASE2_RESULTS.md  # Phase 2 energy-guided generation report
+│   └── ...
+└── benchmark_results/     # Previous benchmarks
+```
+
+## Detailed Results
+
+See [`docs/PHASE1_RESULTS.md`](docs/PHASE1_RESULTS.md) and [`docs/PHASE2_RESULTS.md`](docs/PHASE2_RESULTS.md) for full empirical test reports.
+
+## Tech Stack
+
+- Python, PyTorch (CUDA 12.4, RTX 3090)
+- sentence-transformers, HuggingFace datasets
+- Rust (M2M integration via HTTP)
+
+## License
+
+Apache-2.0

ebm_splats-2.0.0/README.md

@@ -0,0 +1,76 @@
+# EBM-Splats
+
+> **Status: Research complete.** Phase 1-2 empirical tests finished. Energy-guided generation continued in [m2m-energy-fields](https://github.com/schwabauerbriantomas-gif/m2m-energy-fields).
+
+Energy-Based Model with Gaussian Splats on a 640D hypersphere. Explores distributional representations for latent spaces, sampling via Langevin dynamics and Rectified Flow.
+
+## Project Phases
+
+### Phase 1: EBM + PGLF (April 2026) — Discarded
+
+EBM with Gaussian splats as attractors on S^639 + PGLF (projection over MiniLM with contrastive loss).
+
+**Result:** PGLF degraded MiniLM on STS-B (-4.7%). Projection over pre-trained embeddings always destroys geometry.
+
+### Phase 1 Empirical: Discard Tests (July 2026)
+
+3 empirical tests to discard or confirm alternatives. RTX 3090, real data.
+
+| Test | Hypothesis | Result | Verdict |
+|------|-----------|-----------|-----------|
+| PGLF Grid (14 configs) | Can any config beat MiniLM? | 0/14 beat baseline (0.8672) | **DISCARDED** |
+| OOD Detection | Does EBM energy detect OOD? | AUROC=1.0 but NN=0.999 | **NO ADVANTAGE** |
+| RF vs Langevin | Does RF solve the speed bottleneck? | 24-29x faster, better quality | **CONFIRMED** |
+
+**Key finding:** The argument that "200 Langevin steps per token" is prohibitive no longer applies. Rectified Flow with 1-2 steps produces better samples than Langevin with 200 steps, 24x faster.
+
+### Phase 2: Energy-Guided Generation (July 2026)
+
+EBM as a generator that learns its own latent space (not as a layer over pre-trained models), with sampling via Rectified Flow.
+
+| Test | Hypothesis | Result | Verdict |
+|------|-----------|-----------|-----------|
+| Energy-Guided Generation | Can energy manipulation steer generation? | 100% topic control at gs=1.0-2.0 | **CONFIRMED** |
+| Concept Composition | Can multiple concepts be combined? | 4/4 mechanisms work | **CONFIRMED** |
+
+**Composition results:**
+- Equal blend (A+B): balanced similarity to both topics
+- Weighted (70/30): asymmetric control confirmed
+- Suppression (A−B): sim_B dropped from 0.44 to −0.29
+- Triple (A+B+C): all three topics active (sim > 0.48)
+
+**EBM + RF enables semantic arithmetic on the hypersphere.**
+
+## Repository Structure
+
+```
+├── src/ebm/               # Core EBM modules (geometry, splats, energy, model, etc.)
+├── pglf/                  # PGLF (archived — discarded empirically)
+├── scripts/               # Training and generation scripts
+├── tests/
+│   ├── phase1_t11_rf_vs_langevin.py    # RF vs Langevin benchmark
+│   ├── phase1_t12_pglf_grid.py         # PGLF grid search
+│   ├── phase1_t13_ood_energy.py        # OOD detection test
+│   ├── phase2_energy_guided.py         # Energy-guided generation test
+│   ├── phase2_composition.py           # Concept composition test
+│   └── t*_results.jsonl                # Raw results
+├── docs/
+│   ├── PHASE1_RESULTS.md  # Full Phase 1 report
+│   ├── PHASE2_RESULTS.md  # Phase 2 energy-guided generation report
+│   └── ...
+└── benchmark_results/     # Previous benchmarks
+```
+
+## Detailed Results
+
+See [`docs/PHASE1_RESULTS.md`](docs/PHASE1_RESULTS.md) and [`docs/PHASE2_RESULTS.md`](docs/PHASE2_RESULTS.md) for full empirical test reports.
+
+## Tech Stack
+
+- Python, PyTorch (CUDA 12.4, RTX 3090)
+- sentence-transformers, HuggingFace datasets
+- Rust (M2M integration via HTTP)
+
+## License
+
+Apache-2.0

ebm_splats-2.0.0/ebm_splats.egg-info/PKG-INFO

@@ -0,0 +1,108 @@
+Metadata-Version: 2.4
+Name: ebm-splats
+Version: 2.0.0
+Summary: Energy-Based Model with Gaussian Splats on a 640D hypersphere — archived research project
+Author: Brian Schwabauer
+License: Apache-2.0
+Keywords: energy-based-model,gaussian-splats,riemannian,langevin-dynamics,sentence-embeddings
+Classifier: Development Status :: 7 - Inactive
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.0
+Requires-Dist: numpy>=1.24
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Provides-Extra: nlp
+Requires-Dist: sentence-transformers>=2.2; extra == "nlp"
+Requires-Dist: transformers>=4.30; extra == "nlp"
+Requires-Dist: datasets>=2.10; extra == "nlp"
+Provides-Extra: gpu
+Requires-Dist: faiss-cpu>=1.7; extra == "gpu"
+Provides-Extra: service
+Requires-Dist: flask>=3.0; extra == "service"
+Provides-Extra: all
+Requires-Dist: ebm-splats[dev,gpu,nlp,service]; extra == "all"
+Dynamic: license-file
+
+# EBM-Splats
+
+> **Status: Research complete.** Phase 1-2 empirical tests finished. Energy-guided generation continued in [m2m-energy-fields](https://github.com/schwabauerbriantomas-gif/m2m-energy-fields).
+
+Energy-Based Model with Gaussian Splats on a 640D hypersphere. Explores distributional representations for latent spaces, sampling via Langevin dynamics and Rectified Flow.
+
+## Project Phases
+
+### Phase 1: EBM + PGLF (April 2026) — Discarded
+
+EBM with Gaussian splats as attractors on S^639 + PGLF (projection over MiniLM with contrastive loss).
+
+**Result:** PGLF degraded MiniLM on STS-B (-4.7%). Projection over pre-trained embeddings always destroys geometry.
+
+### Phase 1 Empirical: Discard Tests (July 2026)
+
+3 empirical tests to discard or confirm alternatives. RTX 3090, real data.
+
+| Test | Hypothesis | Result | Verdict |
+|------|-----------|-----------|-----------|
+| PGLF Grid (14 configs) | Can any config beat MiniLM? | 0/14 beat baseline (0.8672) | **DISCARDED** |
+| OOD Detection | Does EBM energy detect OOD? | AUROC=1.0 but NN=0.999 | **NO ADVANTAGE** |
+| RF vs Langevin | Does RF solve the speed bottleneck? | 24-29x faster, better quality | **CONFIRMED** |
+
+**Key finding:** The argument that "200 Langevin steps per token" is prohibitive no longer applies. Rectified Flow with 1-2 steps produces better samples than Langevin with 200 steps, 24x faster.
+
+### Phase 2: Energy-Guided Generation (July 2026)
+
+EBM as a generator that learns its own latent space (not as a layer over pre-trained models), with sampling via Rectified Flow.
+
+| Test | Hypothesis | Result | Verdict |
+|------|-----------|-----------|-----------|
+| Energy-Guided Generation | Can energy manipulation steer generation? | 100% topic control at gs=1.0-2.0 | **CONFIRMED** |
+| Concept Composition | Can multiple concepts be combined? | 4/4 mechanisms work | **CONFIRMED** |
+
+**Composition results:**
+- Equal blend (A+B): balanced similarity to both topics
+- Weighted (70/30): asymmetric control confirmed
+- Suppression (A−B): sim_B dropped from 0.44 to −0.29
+- Triple (A+B+C): all three topics active (sim > 0.48)
+
+**EBM + RF enables semantic arithmetic on the hypersphere.**
+
+## Repository Structure
+
+```
+├── src/ebm/               # Core EBM modules (geometry, splats, energy, model, etc.)
+├── pglf/                  # PGLF (archived — discarded empirically)
+├── scripts/               # Training and generation scripts
+├── tests/
+│   ├── phase1_t11_rf_vs_langevin.py    # RF vs Langevin benchmark
+│   ├── phase1_t12_pglf_grid.py         # PGLF grid search
+│   ├── phase1_t13_ood_energy.py        # OOD detection test
+│   ├── phase2_energy_guided.py         # Energy-guided generation test
+│   ├── phase2_composition.py           # Concept composition test
+│   └── t*_results.jsonl                # Raw results
+├── docs/
+│   ├── PHASE1_RESULTS.md  # Full Phase 1 report
+│   ├── PHASE2_RESULTS.md  # Phase 2 energy-guided generation report
+│   └── ...
+└── benchmark_results/     # Previous benchmarks
+```
+
+## Detailed Results
+
+See [`docs/PHASE1_RESULTS.md`](docs/PHASE1_RESULTS.md) and [`docs/PHASE2_RESULTS.md`](docs/PHASE2_RESULTS.md) for full empirical test reports.
+
+## Tech Stack
+
+- Python, PyTorch (CUDA 12.4, RTX 3090)
+- sentence-transformers, HuggingFace datasets
+- Rust (M2M integration via HTTP)
+
+## License
+
+Apache-2.0

ebm_splats-2.0.0/ebm_splats.egg-info/SOURCES.txt

@@ -0,0 +1,46 @@
+LICENSE
+README.md
+pyproject.toml
+ebm_splats.egg-info/PKG-INFO
+ebm_splats.egg-info/SOURCES.txt
+ebm_splats.egg-info/dependency_links.txt
+ebm_splats.egg-info/entry_points.txt
+ebm_splats.egg-info/requires.txt
+ebm_splats.egg-info/top_level.txt
+pglf/__init__.py
+pglf/contrastive_head.py
+pglf/embedding_service.py
+pglf/encoders.py
+pglf/flow_matching.py
+pglf/pareto_filter.py
+pglf/service.py
+pglf/trainer.py
+src/ebm/__init__.py
+src/ebm/config.py
+src/ebm/context.py
+src/ebm/data.py
+src/ebm/data_loader.py
+src/ebm/decoder.py
+src/ebm/energy.py
+src/ebm/evaluation.py
+src/ebm/geometry.py
+src/ebm/langevin.py
+src/ebm/logger.py
+src/ebm/model.py
+src/ebm/score_network.py
+src/ebm/soc.py
+src/ebm/splats.py
+src/ebm/vulkan.py
+src/ebm/cuda/__init__.py
+src/ebm/cuda/energy.py
+tests/test_advanced.py
+tests/test_core.py
+tests/test_data_and_training.py
+tests/test_embedding_service.py
+tests/test_generate.py
+tests/test_geometry.py
+tests/test_pglf.py
+tests/test_score_network.py
+tests/test_scorematching.py
+tests/test_train.py
+tests/test_vulkan.py

ebm_splats-2.0.0/ebm_splats.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

ebm_splats-2.0.0/ebm_splats.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+ebm-embed-service = pglf.embedding_service:main

ebm_splats-2.0.0/ebm_splats.egg-info/requires.txt

@@ -0,0 +1,20 @@
+torch>=2.0
+numpy>=1.24
+
+[all]
+ebm-splats[dev,gpu,nlp,service]
+
+[dev]
+pytest>=7.0
+pytest-cov
+
+[gpu]
+faiss-cpu>=1.7
+
+[nlp]
+sentence-transformers>=2.2
+transformers>=4.30
+datasets>=2.10
+
+[service]
+flask>=3.0

ebm_splats-2.0.0/ebm_splats.egg-info/top_level.txt

@@ -0,0 +1,2 @@
+ebm
+pglf

ebm_splats-2.0.0/pglf/__init__.py

@@ -0,0 +1,33 @@
+"""
+PGLF — Pareto-Guided Langevin Flow Embedding Model.
+
+Omnimodal embedding system built on EBM-splats with three-phase training:
+1. Langevin exploration (energy landscape mapping)
+2. Pareto filtering (multi-objective optimization)
+3. Flow Matching (deterministic distillation)
+"""
+
+from .encoders import (
+    TextEncoder,
+    ImageEncoder,
+    AudioEncoder,
+    OmnimodalEncoder,
+)
+from .flow_matching import HypersphereFlowMatching, FlowMatchingLoss
+from .contrastive_head import HypersphereContrastiveLoss, UniformityAlignmentLoss
+from .pareto_filter import ParetoFilter
+from .trainer import PGLFTrainer
+
+__version__ = "0.1.0"
+__all__ = [
+    "TextEncoder",
+    "ImageEncoder",
+    "AudioEncoder",
+    "OmnimodalEncoder",
+    "HypersphereFlowMatching",
+    "FlowMatchingLoss",
+    "HypersphereContrastiveLoss",
+    "UniformityAlignmentLoss",
+    "ParetoFilter",
+    "PGLFTrainer",
+]