Add matrix reconstruction model

ATTRIBUTIONS.md

@@ -0,0 +1,38 @@
+# Attributions
+
+Aparecium's code and learned nonlinear projection are distributed under the [MIT License](LICENSE). The model artifact also contains the original MPNet input-vocabulary weights and tokenizer files, which retain their Apache-2.0 terms and applicable notices. The MIT license does not relicense those upstream components or source datasets.
+
+The upstream terms are included in [UPSTREAM_LICENSE](UPSTREAM_LICENSE), with component notices in [NOTICE](NOTICE).
+
+## Encoder and vocabulary
+
+| Component | Source | Upstream license |
+| --- | --- | --- |
+| Input encoder, tokenizer, and original vocabulary weights | [all-mpnet-base-v2, Sentence Transformers](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) | Apache-2.0 |
+
+The supported encoder and tokenizer revision is `e8c3b32edf5434bc2275fc9bab85f82640a19130`. Matrix reconstruction loads the included tokenizer and vocabulary. The full encoder is obtained separately when producing matrices or using text convenience methods.
+
+The implementation uses [PyTorch](https://github.com/pytorch/pytorch), [Transformers](https://github.com/huggingface/transformers), [Hugging Face Hub](https://github.com/huggingface/huggingface_hub), [Safetensors](https://github.com/huggingface/safetensors), and [NumPy](https://github.com/numpy/numpy). The optional service uses [FastAPI](https://github.com/fastapi/fastapi), [Pydantic](https://github.com/pydantic/pydantic), and [Uvicorn](https://github.com/encode/uvicorn). Their copyright and license notices remain with their distributions.
+
+## Training sources
+
+The general-English training collection contains 5,000 short texts from the sources below. Dataset-level license labels do not replace the terms or attribution attached to individual source documents.
+
+| Collection | Training texts | Source and acknowledgment | Recorded license information |
+| --- | ---: | --- | --- |
+| C4, realnewslike | 978 | [Allen Institute for AI C4 distribution](https://huggingface.co/datasets/allenai/c4), derived from Common Crawl | ODC-By |
+| Common Pile News | 499 | [Common Pile contributors](https://huggingface.co/datasets/common-pile/news_filtered) and original news authors | Document-level CC-BY filtering; retained documents record Attribution 4.0 |
+| HuffPost News Category | 767 | [News Category Dataset by Rishabh Misra](https://rishabhmisra.github.io/publications/), via [heegyu/news-category-dataset](https://huggingface.co/datasets/heegyu/news-category-dataset) | CC-BY-4.0, as labeled by the collection |
+| Wikinews | 270 | [Wikinews contributors](https://en.wikinews.org/), via [Izumi Lab's English collection](https://huggingface.co/datasets/izumi-lab/wikinews-en-20230728) | CC-BY-2.5 |
+| Wikipedia sentences | 756 | [Wikipedia contributors](https://en.wikipedia.org/), via [Sentence Transformers' English collection](https://huggingface.co/datasets/sentence-transformers/wikipedia-en-sentences) | Wikipedia CC-BY-SA terms; the collection does not specify a version |
+| FineWeb-Edu | 728 | [Hugging Face FineWeb-Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu), derived from Common Crawl | ODC-By |
+| Webis TL;DR | 1,002 | [Webis Group TL;DR collection](https://huggingface.co/datasets/webis/tldr-17) and original contributors | CC-BY-4.0 |
+| **General-English total** | **5,000** | | |
+
+Crypto training additionally uses 140 original public X posts across 133 event families. Those authors retain rights in their posts; public availability does not imply an open-content license. The source collections supply headlines, short summaries, sentences, and social commentary. Separate held-out diagnostic collections contain 500 general-English texts and 50 crypto posts.
+
+The release distributes model parameters and tokenizer assets, not training or evaluation text. Original authors, corpus maintainers, and upstream notices remain the authorities for source content and its terms.
+
+## Evaluation sources
+
+Source-fidelity measurements use held-out public crypto posts, grouped by historical event and distinct author. The reported scores assess preservation of supplied source claims, not their external truth. Public documentation includes aggregate measurements and short paraphrased error descriptions without redistributing the underlying posts.

LICENSE

@@ -0,0 +1,7 @@
+Copyright (c) 2024-2025 SentiChain
+
+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.

NOTICE

@@ -0,0 +1,9 @@
+Aparecium includes the original input-vocabulary weights and tokenizer of
+sentence-transformers/all-mpnet-base-v2 by Sentence Transformers.
+These upstream components are distributed under the Apache License.
+Source: https://huggingface.co/sentence-transformers/all-mpnet-base-v2
+Revision: e8c3b32edf5434bc2275fc9bab85f82640a19130
+The input-vocabulary weights are unchanged. The learned projection and
+vocabulary bias are separate parameters developed by SentiChain.
+The full encoder and training texts are not included.
+See UPSTREAM_LICENSE and ATTRIBUTIONS.md for attribution and terms.

README.md

@@ -0,0 +1,155 @@
+---
+language:
+- en
+license: other
+license_name: mit-and-apache-2.0
+license_link: https://huggingface.co/SentiChain/aparecium-matrix/blob/main/ATTRIBUTIONS.md
+library_name: safetensors
+base_model: sentence-transformers/all-mpnet-base-v2
+tags:
+- matrix
+- embedding-inversion
+- crypto
+datasets:
+- allenai/c4
+- common-pile/news_filtered
+- heegyu/news-category-dataset
+- izumi-lab/wikinews-en-20230728
+- sentence-transformers/wikipedia-en-sentences
+- HuggingFaceFW/fineweb-edu
+- webis/tldr-17
+---
+
+# Aparecium Matrix
+
+[Aparecium Matrix](https://huggingface.co/SentiChain/aparecium-matrix) reconstructs short English text from full token-state matrices produced by [`sentence-transformers/all-mpnet-base-v2`](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). A learned nonlinear projection predicts a token from each interior state using the encoder's original frozen vocabulary weights.
+
+**Outputs are approximate reconstructions.** They can omit or change numbers, dates, names, actions, conditions, and relationships. The model can preserve an event's broad meaning while introducing a material error. Reconstructions are not verified source text, news, financial forecasts, or evidence of trading profitability.
+
+## Loading
+
+```bash
+pip install --pre aparecium
+```
+
+```python
+import numpy as np
+from aparecium import Aparecium
+
+model = Aparecium(model_id="SentiChain/aparecium-matrix")
+matrix = np.load("matrix.npy", allow_pickle=False)
+result = model.invert_matrix(matrix)
+print(result.text)
+```
+
+This artifact uses the Aparecium Python loader. It is not a standalone Transformers `AutoModel` checkpoint or a text-prompt model. Matrix reconstruction loads the artifact's weights and tokenizer without loading the full encoder. It receives no source text, reference token IDs, or retrieved material.
+
+`invert_matrices` accepts up to 32 matrices, including a list of different sequence lengths. Results contain `text`, `token_ids`, and `input_rows`. The token IDs include every visible interior prediction, including predicted special IDs; text decoding skips special tokens. The input-row count includes the visible first and last framing positions.
+
+`invert_text` and `invert_texts` are round-trip convenience methods. They load the separately cached pinned encoder, produce `AutoModel.last_hidden_state` without pooling, and reconstruct those states. Text producing more than 256 rows is rejected. See the [input and producer examples](https://github.com/SentiChain/aparecium/blob/master/README.md) before creating stored matrices.
+
+CPU is the default device. MPS is available only when explicitly requested on supported hardware. An unavailable requested device raises an error. `local_files_only=True` prevents downloads; matrix loading requires the local artifact, and text convenience methods additionally require the pinned encoder files in the local cache.
+
+## Input contract
+
+| Property | Required representation |
+| --- | --- |
+| Encoder | `sentence-transformers/all-mpnet-base-v2` |
+| Encoder and tokenizer revision | `e8c3b32edf5434bc2275fc9bab85f82640a19130` |
+| States | Complete `AutoModel.last_hidden_state`, with no pooling or row normalization |
+| Shape per input | 3 through 256 rows by 768 columns |
+| Stored dtype | Native float32 |
+| Framing | Include first and last visible beginning/end positions |
+| Optional mask | Binary visible prefix with right padding; at least three visible rows |
+| Values | Finite real numbers; conversion to float32 must not overflow |
+
+Pooled 768-element sentence vectors are incompatible. A pooled vector cannot substitute for the full token matrix, and vectors from another encoder are unsupported even when their width matches. The caller must preserve encoder provenance because matrix shape does not identify how states were produced.
+
+## Architecture and decoding
+
+| Component | Configuration |
+| --- | --- |
+| Nonlinear projection | Dense 768-to-768 layer, GELU, and LayerNorm |
+| Learned vocabulary bias | One bias per vocabulary entry |
+| Learned parameters | 622,655 |
+| Original frozen vocabulary | 30,527 entries by 768 dimensions, totaling 23,444,736 parameters |
+| Token selection | Float32 top-one argmax at each visible token row |
+| Framing removal | Remove only the known first and last visible positions |
+| Text decoding | Skip special tokens; disable tokenization-space cleanup |
+
+The learned projection and vocabulary bias were fitted while the original MPNet input-vocabulary weights remained unchanged. Predictions are selected independently for each token state; each state already contains context supplied by the encoder. Reconstruction does not include source retrieval, text repair, sampling, or a confidence-based withholding rule. Token predictions are not calibrated probabilities of source fidelity.
+
+## Artifact contents and configuration
+
+The artifact contains `model.safetensors`, `config.json`, `tokenizer.json`, `tokenizer_config.json`, `special_tokens_map.json`, and `vocab.txt`, together with the model card and license notices. It contains no optimizer state or pickled model checkpoint. The Safetensors file holds the dense layer, LayerNorm, vocabulary bias, and original frozen vocabulary table.
+
+The configuration records the following fields:
+
+| Fields | Purpose |
+| --- | --- |
+| `schema_version`, `model_type`, `architecture` | Identify the supported artifact contract and computation. |
+| `state_width`, `vocabulary_size`, `max_sequence_length`, `layer_norm_eps` | Fix dimensions, row limit, and LayerNorm behavior. |
+| `encoder_model_id`, `encoder_revision`, `tokenizer_revision` | Pin input and tokenizer provenance. |
+| `pad_token_id`, `bos_token_id`, `eos_token_id`, `unk_token_id` | Fix tokenizer framing and special-token identities. |
+| `weights_file`, `weights_sha256` | Name and verify the tensor file. |
+| `tensor_sha256`, `vocabulary_array_sha256` | Verify individual tensor content and the unchanged upstream vocabulary. |
+| `tokenizer_files_sha256` | Verify the bundled tokenizer files. |
+| `source_checkpoint_sha256` | Record the source-weight digest for artifact traceability. |
+
+The loader validates the complete configuration, file digests, tensor names, shapes, dtype, and finite values. These integrity checks detect incompatible or altered artifacts; they do not certify reconstruction quality.
+
+## Training data and procedure
+
+Training used 5,000 general-English texts and 140 original public crypto posts spanning 133 event families. General-English texts consist of short news, encyclopedic and educational passages, and social summaries from the following collections:
+
+| Collection | Training texts |
+| --- | ---: |
+| C4, realnewslike | 978 |
+| Common Pile News | 499 |
+| HuffPost News Category | 767 |
+| Wikinews | 270 |
+| Wikipedia sentences | 756 |
+| FineWeb-Edu | 728 |
+| Webis TL;DR | 1,002 |
+| **General-English total** | **5,000** |
+
+Separate held-out collections of 500 general-English texts and 50 crypto posts supported training diagnostics. Crypto training posts were collected from September 2026 source content. Event-family, identifier, link, and normalized-text checks separated the crypto training and held-out collections.
+
+The model completed 1,000 optimizer updates with 255,798 supervised token targets. General-English and crypto targets each contributed 127,899 presentations, giving a 50:50 target mixture. The objective was cross entropy over the original vocabulary. Training included interior content without source-derived URL masking, and the final update supplied the released parameters. These are target presentations, not distinct training examples.
+
+The release does not redistribute training or evaluation text. See [source acknowledgments](https://github.com/SentiChain/aparecium/blob/master/ATTRIBUTIONS.md) for collection licenses and authorship.
+
+## Evaluation
+
+A held-out collection contains 20 historical crypto event families and 60 original posts, with three distinct authors per event. It covers February through June 2026 and uses six bullish, six bearish, four mixed, and four unclear source contexts. This balanced historical selection does not represent live-news prevalence.
+
+Event accounts formed from the reconstructed posts received two judgment-based source-fidelity assessments. These assessments have not been independently human validated. Both recorded the following event-level counts:
+
+| Measure | Result |
+| --- | ---: |
+| Useful central claim | 20 / 20 |
+| Useful without a critical assertion | 18 / 20 |
+| At least one critical assertion | 2 / 20 |
+| Actionable event context | 20 / 20 |
+
+The same posts yielded 1,439 correct body token slots out of 1,713 excluding URLs, or 84.00%. Tolerated financial-value F1 was 0.860 under the primary assessment and 0.837 under the sensitivity assessment. Timing-role F1 was 0.846 and 0.835 respectively. These measures concern different aspects of recovery; none establishes complete event fidelity or trading safety.
+
+Recorded errors include turning about 2,000 BTC into about 2,000,000 BTC and changing a 2030 forecast horizon into 2036. Ranges, conditions, and secondary quantities can be lost. Other separately composed historical collections of 20 event families produced useful accounts without critical assertions in 65% through 90% of events. Different event content prevents interpreting those percentages as a performance trend.
+
+One recorded four-thread CPU run processed the 60 stored matrices in about 2.43 seconds, including associated validation in the measurement path. This is not an isolated decoder-throughput measurement or a service-latency guarantee. Downloads, different hardware, and sustained service workloads can change costs.
+
+See the [benchmark details](https://github.com/SentiChain/aparecium/blob/master/docs/benchmarks.md) for role definitions, complete-coverage counts, timing scope, and qualitative errors.
+
+## Intended use and limitations
+
+Aparecium supports inspecting the approximate content represented by short English MPNet token states. It is intended for workflows where a person or downstream system can inspect missing or corrupted details and consult source material when accuracy matters.
+
+The model has not established exact quotation recovery, long-document quality, multilingual quality, verified reporting, profitable trading, or reliable unattended replacement of original posts. Historical balanced event assessments are small and judgment based. General-English training text and public crypto posts can contain incomplete, biased, inaccurate, or disputed content; reconstruction does not verify it.
+
+Financial quantities, units, inequalities, actor roles, timing windows, action status, and negation need particular care. Multiple reconstructions can share the same wrong detail. A fluent or recognizable account does not certify that those roles survived.
+
+## License and attribution
+
+Aparecium code and the learned nonlinear projection are licensed under MIT. The included original MPNet vocabulary weights and tokenizer retain their Apache-2.0 terms and applicable notices. The artifact includes upstream license material. Training-source terms remain with their owners, and public availability of an X post does not imply an open-content license.
+
+Developed and maintained by [SentiChain](https://github.com/SentiChain). Source code, [usage documentation](https://github.com/SentiChain/aparecium/blob/master/README.md), and [issue tracking](https://github.com/SentiChain/aparecium/issues) are available in the [Aparecium repository](https://github.com/SentiChain/aparecium).

SHA256SUMS

@@ -0,0 +1,11 @@
+ab872efe3f76dd7a5961a92c49eadab7ab9a95be384be5a3bda66879e0c97c7f  ATTRIBUTIONS.md
+5b00bcb8a6dc9942d8256909fe3690361786da5e0dd2d78b9eb6db8d11a08e25  LICENSE
+d47c1c887f6d20e0aa41a5a8029b3a0da51b456033d490cee3c7783c0eaa2a5d  NOTICE
+543ad40467f4be3f17fba4943131c3a9be42f93efcfbdeed59520db00238bc66  README.md
+cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30  UPSTREAM_LICENSE
+89e261570c037e6ecb939c7deac4e186e15b8d78afab75f1114b76d29da5ea1a  config.json
+6640352b827d1175d0e2d7673e6a1e61e68eea55c8ef12a9d8510dd3aa2e8584  model.safetensors
+becf54aafa607d9dc2ec7e7ba8eb6ed71f5133009a815a0aa86677c733046fe2  special_tokens_map.json
+d00dad6f80b7eab804479a58634a58a50966366627f847e47848bac52873995d  tokenizer.json
+9b2bebc2f0cf757ba71279c15500ab39b8a5788c04b00b7fb0b7c6b958400068  tokenizer_config.json
+dbd90cb94e2247bd4d4ccaecbf616d2290e66691d7d5e5bb81f063c2d0649ada  vocab.txt

UPSTREAM_LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 [yyyy] [name of copyright owner]
+
+   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.

config.json

@@ -0,0 +1,34 @@
+{
+  "schema_version": 1,
+  "model_type": "aparecium_matrix",
+  "architecture": "dense_gelu_layernorm_frozen_vocabulary",
+  "state_width": 768,
+  "vocabulary_size": 30527,
+  "encoder_model_id": "sentence-transformers/all-mpnet-base-v2",
+  "encoder_revision": "e8c3b32edf5434bc2275fc9bab85f82640a19130",
+  "tokenizer_revision": "e8c3b32edf5434bc2275fc9bab85f82640a19130",
+  "pad_token_id": 1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "unk_token_id": 104,
+  "max_sequence_length": 256,
+  "layer_norm_eps": 1e-05,
+  "weights_file": "model.safetensors",
+  "weights_sha256": "6640352b827d1175d0e2d7673e6a1e61e68eea55c8ef12a9d8510dd3aa2e8584",
+  "source_checkpoint_sha256": "020c818a4acce8ed170d44076111751217dcd65689072ba969ad318813997116",
+  "vocabulary_array_sha256": "7002c8c982d9df1ddbe7cef4f392ac427ce74bebdbf98a466a2a49f5d7ddcd1b",
+  "tensor_sha256": {
+    "dense.bias": "aaeac72ea50d9a015f1828c7971785893a089b8af23df5b61bc46cf53bf25452",
+    "dense.weight": "c955da8b808af45dd440d23e82461f6571bb9d17f0e540661d91d89a21201651",
+    "layer_norm.bias": "fe9af289962d10ad51d1a45b3d204a5c28ab697959ab9f2f7c52b27f44e2dd5a",
+    "layer_norm.weight": "5d1e6415fd58abb9208e05b3ce75e9ff7618cde6dab4e26e8b2e84435c7d24ba",
+    "vocabulary": "7002c8c982d9df1ddbe7cef4f392ac427ce74bebdbf98a466a2a49f5d7ddcd1b",
+    "vocabulary_bias": "4f2b391deaffada907134ba70d5c83d77983c545b2e73767670b43eb8add988f"
+  },
+  "tokenizer_files_sha256": {
+    "tokenizer.json": "d00dad6f80b7eab804479a58634a58a50966366627f847e47848bac52873995d",
+    "tokenizer_config.json": "9b2bebc2f0cf757ba71279c15500ab39b8a5788c04b00b7fb0b7c6b958400068",
+    "special_tokens_map.json": "becf54aafa607d9dc2ec7e7ba8eb6ed71f5133009a815a0aa86677c733046fe2",
+    "vocab.txt": "dbd90cb94e2247bd4d4ccaecbf616d2290e66691d7d5e5bb81f063c2d0649ada"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6640352b827d1175d0e2d7673e6a1e61e68eea55c8ef12a9d8510dd3aa2e8584
+size 96270180

special_tokens_map.json

@@ -0,0 +1,58 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": false,
+    "special": true
+  },
+  "eos_token": {
+    "content": "</s>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": false,
+    "special": true
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": false,
+    "special": true
+  },
+  "sep_token": {
+    "content": "</s>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": false,
+    "special": true
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": false,
+    "special": true
+  },
+  "cls_token": {
+    "content": "<s>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": false,
+    "special": true
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "single_word": false,
+    "lstrip": true,
+    "rstrip": false,
+    "normalized": false,
+    "special": true
+  }
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": true,
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}