Release Stem GTE Memory epoch2 q8 with calibrated thresholds and evaluation documentation

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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.

NOTICE

@@ -0,0 +1,17 @@
+Stem GTE Memory
+
+Derived from Alibaba-NLP/gte-multilingual-reranker-base by the GTE authors
+at Alibaba Group. The upstream model declares Apache License 2.0.
+https://huggingface.co/Alibaba-NLP/gte-multilingual-reranker-base
+Model revision: 8215cf04918ba6f7b6a62bb44238ce2953d8831c
+Upstream implementation: Alibaba-NLP/new-impl
+Code revision: 40ced75c3017eb27626c9d4ea981bde21a2662f4
+
+Stem modifications (September 2026): fine-tuned encoder and classification
+head for personal-memory relevance using fictional profiles and Czech,
+Slovak, German and English queries; exported epoch2 to ONNX and dynamically
+quantized weights to int8; calibrated separate fact and skill thresholds.
+The supplied model configuration and tokenizer match the tested export.
+
+This notice describes attribution and modifications; it does not imply
+endorsement by the upstream authors. See LICENSE for Apache License 2.0.

README.md

@@ -0,0 +1,117 @@
+---
+license: apache-2.0
+language:
+- cs
+- sk
+- de
+- en
+base_model: Alibaba-NLP/gte-multilingual-reranker-base
+base_model_relation: finetune
+pipeline_tag: text-ranking
+tags:
+- onnx
+- reranker
+- memory
+- stem
+- quantized
+- experimental
+---
+
+# Stem GTE Memory
+
+A custom GTE reranker fine-tuned for Stem's personal-memory retrieval, with training queries in **Czech, Slovak, German, and English**. It scores how relevant a stored memory is to a user's message. Stem also uses the same weights for skill selection with a separately calibrated threshold.
+
+This is the selected **epoch2 q8 ONNX** release, model ID `gte-memory-20260905-epoch2`. The five inference files total **358,119,455 bytes (341.53 MiB)**; Stem's dropdown rounds this to approximately 342 MB. The quantized graph alone is 341,032,790 bytes.
+
+In Stem's fresh synthetic memory benchmark, this checkpoint improved recall from **43.1% to 64.7%** and reduced irrelevant selections from **166 to 87**, compared with the configured Qwen3 Reranker 0.6B baseline. A separate local timing experiment measured **320 ms vs 3,116 ms median** for the benchmark pipeline, approximately **9.74× faster**. These are scoped benchmark results, not universal model rankings or end-to-end chat speed guarantees.
+
+## Intended use
+
+Rerank a shortlist of memory facts, or skill descriptions, before an assistant responds. Training and the reported multilingual evaluations used English stored facts or descriptions with multilingual user requests. Broader language coverage inherited from the base model has not been established by this fine-tune's evaluation.
+
+This is an experimental, opt-in release. Publishing the files does not enable automatic downloading in existing Stem versions; that app integration is separate.
+
+## Files and integrity
+
+- `onnx/model_quantized.onnx`: selected q8 inference graph, ONNX opset 17.
+- `config.json`, `tokenizer.json`, `tokenizer_config.json`, `special_tokens_map.json`: the exact measured inference configuration and tokenizer.
+- `stem-model.json`: immutable model identity, upstream revisions, per-file SHA-256 hashes and sizes, and Stem thresholds.
+- `example.mjs`: local Node.js inference example using Transformers.js 3.8.1.
+- `LICENSE` and `NOTICE`: licensing and modification notices.
+
+Pin a Hub commit revision when downloading, then verify all five inference files against `stem-model.json`. Hashes are also pinned in Stem's runtime. No training datasets, chat transcripts, benchmark examples, FP32 weights, or training checkpoints are included.
+
+`config.json` retains an inert temporary export path in `_name_or_path` to preserve its measured hash. It does not need to exist. Its upstream `auto_map` metadata is likewise preserved; the supported ONNX path below does not execute remote Python code.
+
+## Inference contract
+
+Use **Transformers.js 3.8.1 `PreTrainedModel`**, not its auto sequence-classification loader: this export retains the upstream custom `model_type: new`. This repository contains ONNX weights, not a PyTorch checkpoint.
+
+1. Tokenize a `(query, document)` text pair with the supplied tokenizer.
+2. Score **one pair per forward pass**, sequentially. Do not silently truncate. Stem rejects pairs longer than 8,192 tokens, including special tokens; long-context quality has not been validated here.
+3. Read the single finite **raw logit**. Higher means more relevant. Do not apply sigmoid or reinterpret it as a probability.
+
+Install `@huggingface/transformers@3.8.1` in a Node.js project, download this repository's files to a local folder, and run:
+
+```sh
+node example.mjs /absolute/path/to/downloaded/model
+```
+
+For Stem's measured configuration:
+
+| Purpose | Raw-logit threshold |
+|---|---:|
+| Memory facts | -1.6370911598205566 |
+| Skill selection | -3.9743599891662598 |
+| Additional margin for sensitive facts | +2 |
+
+These thresholds belong to this exact graph, tokenizer, and pipeline. They are not interchangeable or universal cutoffs. Stem uses a Qwen3 Embedding 0.6B shortlist, up to 24 fact candidates and at most 16 relevant selected facts (subject to a smaller user setting). Pinned facts are handled separately.
+
+For fact retrieval with conversational context, Stem takes at most two preceding eligible user messages in chronological order, clipping each to 400 Unicode code points, and formats the query as:
+
+```text
+Earlier messages from the user in this conversation:
+- <earlier user message>
+- <later user message>
+
+Current message: <current user message>
+```
+
+With no eligible history, use the current message alone. Skill selection uses the current message alone and its own threshold.
+
+## Training
+
+Base: [Alibaba-NLP/gte-multilingual-reranker-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-reranker-base), revision `8215cf04918ba6f7b6a62bb44238ce2953d8831c`. Upstream implementation: `Alibaba-NLP/new-impl`, revision `40ced75c3017eb27626c9d4ea981bde21a2662f4`.
+
+Fine-tuning used **23,684 binary pairs from 88 fictional training profiles**, including 797 relevant pairs. Query-language pair counts: Czech 5,905; Slovak 6,051; German 5,963; English 5,765. Borderline examples were excluded. Real personal-memory benchmarks were not used for training and are not published.
+
+The encoder and classification head were trained (113,920,513 trainable parameters); token embeddings were frozen. AdamW used learning rate 1e-5, weight decay 0.01, batch size 16, 10% linear warmup, gradient clipping 1.0 and BCE positive weight 3. The maximum tokenized training pair length was 94; no training examples were truncated. Three epochs were planned; epoch2 was selected after q8 export using development data. Feasible settings had to meet the configured Qwen baseline recall overall and per language, then minimize `3 * false negatives + false positives`.
+
+Export used PyTorch 2.8.0 and ONNX Runtime 1.22.1. Dynamic weight quantization used QInt8, per-channel quantization, reduced range, symmetric weights and constant-matrix-only MatMul quantization. Four synthetic export probes had maximum FP32/PyTorch error 0.0000019074 and q8/FP32 error 0.065004; these probes do not establish broad numerical parity.
+
+## Evaluation and limitations
+
+The fresh memory test contained 192 requests from 16 fictional profiles, 48 in each language. Its references were synthetic author/reviewer judgments, with disagreements treated as borderline, not human gold. Labels covered the reviewed union of candidate pools, so facts missed by both retrieval paths remained unjudged.
+
+| Request language | Configured Qwen recall | Stem GTE recall |
+|---|---:|---:|
+| Czech | 19.4% | 58.1% |
+| Slovak | 10.3% | 53.8% |
+| German | 48.7% | 64.1% |
+| English | 74.1% | 75.9% |
+
+Two previously seen real-data regression sets showed small recall changes (15.4% to 19.2%, and 23.5% to 25.7%) and fewer irrelevant selections. Their recall-difference intervals included zero; they do not establish a large real-world recall gain. No real-data examples are distributed.
+
+The timing result above measured 64 warm observations per model on a local Mac. Each observation embedded a contextual query, sequentially scored 24 candidates and applied the gate. Candidate retrieval, database work, IPC, model loading and answer generation were excluded. Repeated observations were correlated. This is not a promise about complete response latency, other hardware, or application-wide memory consumption.
+
+Linux validation found numerical differences from macOS despite identical tokenized inputs (maximum absolute logit difference 0.645472 on 16 probes). With the frozen fact threshold, Linux selected 106 useful and 84 irrelevant facts on the same fresh synthetic set, versus macOS GTE's 108 and 87. An English-only same-server rerun selected 42 useful facts with GTE versus 39 with Qwen; other languages' Qwen baselines were not rerun on Linux. Validate your target runtime; do not assume bitwise portability.
+
+Sensitive-fact selection remains a limitation: in the fresh macOS test, GTE selected 3 irrelevant sensitive facts versus Qwen's 1 while finding more useful sensitive facts. The inherited +2 margin is not equally calibrated across models.
+
+A separate fresh skill test found the correct skill on 39/48 positive requests versus Qwen's 33/48, with false loads on 11/48 negative requests versus 12/48. GTE still **missed the predeclared 90% correct-loading target** (81.25%). Both models found the correct skill on only 15/24 concise conversational positives. The weights were not trained again for this skill evaluation; only the threshold was calibrated beforehand.
+
+These experiments do not establish improved final answers, long-input accuracy, performance outside the four training languages, or universal superiority over other rerankers. The model should remain a selectable option while broader evaluation continues.
+
+## License and attribution
+
+Released under Apache License 2.0, following the upstream model's declared license. See `LICENSE` and `NOTICE`. Stem modifications comprise memory-relevance fine-tuning, ONNX export, quantization and task-specific calibration. This release is a Stem adaptation, not an official Alibaba release.

SHA256SUMS

@@ -0,0 +1,10 @@
+cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30  LICENSE
+c943475cbb6f4cf48f04e009ba003ebc63b6fc5f7a9c1329bda7ef294bc9bef2  NOTICE
+d1ebe6222bfaf23ac515be79aced8ca113d5d95b4bfe96d54a97645ad5d8d86a  README.md
+e5f2efd1e04e5e4465b8c6c2f6af1f00a5d66a839e825b0af8edba68ceb8b1bb  config.json
+7702e5276936c92f0283150c5032c5a74dfb5bc25e00d53b75c062a01c28f3b8  example.mjs
+5cbb66c672aa71fb6609880ba8e8370ff5be3376fc95215317c92e41e7743e4e  onnx/model_quantized.onnx
+8c785abebea9ae3257b61681b4e6fd8365ceafde980c21970d001e834cf10835  special_tokens_map.json
+196a6a4a0d4973bbc39095cb8b95d519df1a093fcf84124b720ddcd8096d9b2b  stem-model.json
+3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20  tokenizer.json
+6f00514620aff01ba8b7291b2394e98daca5be264cb743805232d9ae27494b2a  tokenizer_config.json

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "/private/tmp/stem-gte-finetune-20260905-2008/checkpoints/epoch2",
+  "architectures": [
+    "NewForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "ntk"
+  },
+  "rope_theta": 20000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 250048
+}

example.mjs

@@ -0,0 +1,27 @@
+import { resolve } from 'node:path';
+import { AutoTokenizer, PreTrainedModel, env } from '@huggingface/transformers';
+
+if (!process.argv[2]) throw new Error('Usage: node example.mjs /path/to/model');
+const directory = resolve(process.argv[2]);
+env.allowRemoteModels = false;
+const tokenizer = await AutoTokenizer.from_pretrained(directory, { local_files_only: true });
+const model = await PreTrainedModel.from_pretrained(directory, {
+  dtype: 'q8', local_files_only: true, session_options: { enableCpuMemArena: false }
+});
+try {
+  const query = 'Suggest a vegetarian dinner.';
+  const documents = ['The user is vegetarian.', 'The user plays the violin.'];
+  for (const document of documents) {
+    const inputs = tokenizer([query], { text_pair: [document], padding: true, truncation: false });
+    const [batch, length] = inputs.input_ids.dims;
+    if (batch !== 1 || length < 1 || length > 8192) throw new Error('Unsupported pair length');
+    const { logits } = await model(inputs);
+    const score = Number(logits.data[0]);
+    if (logits.data.length !== 1 || logits.dims.some(n => n !== 1) || !Number.isFinite(score)) {
+      throw new Error('Expected one finite raw logit');
+    }
+    console.log(JSON.stringify({ document, score }));
+  }
+} finally {
+  await model.dispose();
+}

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cbb66c672aa71fb6609880ba8e8370ff5be3376fc95215317c92e41e7743e4e
+size 341032790

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

stem-model.json

@@ -0,0 +1,42 @@
+{
+  "schema_version": 1,
+  "model_id": "gte-memory-20260905-epoch2",
+  "display_name": "Stem GTE Memory",
+  "base_model": "Alibaba-NLP/gte-multilingual-reranker-base",
+  "base_revision": "8215cf04918ba6f7b6a62bb44238ce2953d8831c",
+  "upstream_code_revision": "40ced75c3017eb27626c9d4ea981bde21a2662f4",
+  "checkpoint": "epoch2",
+  "dtype": "q8",
+  "scoring": "gte-scalar",
+  "fact_threshold": -1.6370911598205566,
+  "skill_threshold": -3.9743599891662598,
+  "sensitive_fact_margin": 2,
+  "languages": [
+    "cs",
+    "sk",
+    "de",
+    "en"
+  ],
+  "files": {
+    "config.json": {
+      "sha256": "e5f2efd1e04e5e4465b8c6c2f6af1f00a5d66a839e825b0af8edba68ceb8b1bb",
+      "bytes": 1627
+    },
+    "tokenizer.json": {
+      "sha256": "3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20",
+      "bytes": 17082734
+    },
+    "tokenizer_config.json": {
+      "sha256": "6f00514620aff01ba8b7291b2394e98daca5be264cb743805232d9ae27494b2a",
+      "bytes": 1340
+    },
+    "special_tokens_map.json": {
+      "sha256": "8c785abebea9ae3257b61681b4e6fd8365ceafde980c21970d001e834cf10835",
+      "bytes": 964
+    },
+    "onnx/model_quantized.onnx": {
+      "sha256": "5cbb66c672aa71fb6609880ba8e8370ff5be3376fc95215317c92e41e7743e4e",
+      "bytes": 341032790
+    }
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}