初始化项目，由ModelHub XC社区提供模型

Model: telepix/PIXIE-Rune-v1.0
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

LICENSE

@@ -0,0 +1,212 @@
+Copyright (c) 2026 TelePIX Co., Ltd. All rights reserved.
+
+Built with snowflake-arctic-embed-l-v2.0 — original model by Snowflake, licensed under the Apache License 2.0.
+
+Unless otherwise stated, all files in this repository (including modified model weights 
+and tokenizer files) are distributed under the terms of the Apache License, Version 2.0 
+(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 (Apache-2.0 §4 d)
+================================================================================
+
+This product is built with snowflake-arctic-embed-l-v2.0 developed by Snowflake.
+(https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) and distributed under the Apache License 2.0.
+
+See the upstream snowflake-arctic-embed-l-v2.0 for additional attribution details.
+
+================================================================================
+TRADEMARK
+================================================================================
+
+"TelePIX" and associated logos are trademarks of TelePIX Co., Ltd. 
+This License does not grant permission to use these trademarks without prior 
+written consent.
+
+================================================================================
+APACHE LICENSE 2.0
+================================================================================
+
+                                 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

README.md

@@ -0,0 +1,249 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- dense-encoder
+- dense
+- feature-extraction
+- retrieval
+- multimodal
+- multi-modal
+- crossmodal
+- cross-modal
+- aerospace
+- telepix
+language:
+- af
+- ar
+- az
+- be
+- bg
+- bn
+- ca
+- ceb
+- cs
+- cy
+- da
+- de
+- el
+- en
+- es
+- et
+- eu
+- fa
+- fi
+- fr
+- gl
+- gu
+- he
+- hi
+- hr
+- ht
+- hu
+- hy
+- id
+- is
+- it
+- ja
+- jv
+- ka
+- kk
+- km
+- kn
+- ko
+- ky
+- lo
+- lt
+- lv
+- mk
+- ml
+- mn
+- mr
+- ms
+- my
+- ne
+- nl
+- pa
+- pl
+- pt
+- qu
+- ro
+- ru
+- si
+- sk
+- sl
+- so
+- sq
+- sr
+- sv
+- sw
+- ta
+- te
+- th
+- tl
+- tr
+- uk
+- ur
+- vi
+- yo
+- zh
+pipeline_tag: feature-extraction
+library_name: sentence-transformers
+license: apache-2.0
+---
+<p align="center">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/61d6f4a4d49065ee28a1ee7e/V8n2En7BlMNHoi1YXVv8Q.png" width="400"/>
+<p>
+
+# PIXIE-Rune-v1.0
+**PIXIE-Rune-v1.0** is an encoder-based embedding model trained on Korean and English information retrieval dataset, 
+developed by [TelePIX Co., Ltd](https://telepix.net/).
+**PIXIE** stands for Tele**PIX** **I**ntelligent **E**mbedding, representing TelePIX’s high-performance embedding technology.
+This model is specifically optimized for semantic retrieval tasks in Korean and English, and demonstrates strong performance in aerospace domain. Through extensive fine-tuning and domain-specific evaluation, PIXIE shows robust retrieval quality for real-world use cases such as document understanding, technical QA, and semantic search in aerospace and related high-precision fields.
+It also performs competitively across a wide range of open-domain Korean and English retrieval benchmarks, making it a versatile foundation for multilingual semantic search systems.
+
+
+## Model Description
+- **Model Type:** Sentence Transformer
+<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 6144 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Language:** Multilingual — optimized for high performance in Korean and English
+- **Domain Specialization:** Aerospace Information Retrieval
+- **License:** apache-2.0 
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 6144, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Quality Benchmarks
+**PIXIE-Rune-v1.0** is a multilingual embedding model specialized for Korean and English retrieval tasks. 
+It delivers consistently strong performance across a diverse set of domain-specific and open-domain benchmarks in both languages, demonstrating its effectiveness in real-world semantic search applications.
+The table below presents the retrieval performance of several embedding models evaluated on a variety of Korean and English benchmarks.
+We report **Normalized Discounted Cumulative Gain (nDCG@10)** scores, which measure how well a ranked list of documents aligns with ground truth relevance. Higher values indicate better retrieval quality.  
+  
+All evaluations were conducted using the open-source **[Korean-MTEB-Retrieval-Evaluators](https://github.com/BM-K/Korean-MTEB-Retrieval-Evaluators)** codebase to ensure consistent dataset handling, indexing, retrieval, and nDCG@10 computation across models.
+
+### Benchmark Overview and Dataset Descriptions
+| Model Name | # params | STELLA (XL) | MTEB (ko) | BEIR (en) |
+|------|:---:|:---:|:---:|:---:|
+| **telepix/PIXIE-Rune-v1.0** | **0.5B** | **0.6345** | **0.7603** | **0.5872** |
+| | | | | |
+| nvidia/llama-embed-nemotron-8b | 8B | 0.7181 | 0.7813 | 0.6935 |
+| Qwen/Qwen3-Embedding-8B | 8B | 0.6154 | 0.7839 | 0.6701 |
+| Snowflake/snowflake-arctic-embed-l-v2.0 | 0.5B | 0.5448 | 0.7390 | 0.6006 |
+| BAAI/bge-m3 | 0.5B | 0.5056 | 0.7483 | 0.5573 |
+| Qwen/Qwen3-Embedding-0.6B | 0.6B | 0.4707 | 0.7017 | 0.5839 |
+| Octen/Octen-Embedding-0.6B | 0.6B | 0.4683 | 0.7057 | 0.5769 |
+| Salesforce/SFR-Embedding-Mistral | 7B | 0.4579 | N/A | N/A |
+| Alibaba-NLP/gte-multilingual-base | 0.3B | 0.4097 | 0.7084 | 0.5746 |
+| intfloat/multilingual-e5-large-instruct | 0.6B | 0.2384 | 0.7050 | N/A |
+| jinaai/jina-embeddings-v3 | 0.5B | N/A | 0.7088 | 0.4861 |
+| openai/text-embedding-3-large | N/A | N/A | 0.6646 | N/A |
+
+To better interpret the evaluation results above, we briefly describe the characteristics and evaluation intent of each benchmark suite used in this comparison.
+Each benchmark is designed to assess different aspects of retrieval capability, ranging from domain-specific technical understanding to open-domain and multilingual generalization.
+
+#### STELLA
+[STELLA](https://arxiv.org/abs/2601.03496) is an aerospace-domain Information Retrieval (IR) benchmark constructed from NASA Technical Reports Server (NTRS) documents. It is designed to evaluate both:
+
+- **Lexical matching** ability (does the retriever benefit from exact technical terms? | TCQ)
+- **Semantic matching** ability (can the retriever match concepts even when technical terms are not explicitly used? | TAQ).
+
+STELLA provides **dual-type synthetic queries** and a **cross-lingual extension** for multilingual evaluation while keeping the corpus in English.
+
+#### 6 Datasets of MTEB (Korean)
+Descriptions of the benchmark datasets used for evaluation are as follows:
+- **Ko-StrategyQA**  
+  A Korean multi-hop open-domain question answering dataset designed for complex reasoning over multiple documents.
+- **AutoRAGRetrieval**  
+  A domain-diverse retrieval dataset covering finance, government, healthcare, legal, and e-commerce sectors.
+- **MIRACLRetrieval**  
+  A document retrieval benchmark built on Korean Wikipedia articles.
+- **PublicHealthQA**  
+  A retrieval dataset focused on medical and public health topics.
+- **BelebeleRetrieval**  
+  A dataset for retrieving relevant content from web and news articles in Korean.
+- **MultiLongDocRetrieval**  
+  A long-document retrieval benchmark based on Korean Wikipedia and mC4 corpus.
+
+#### 7 Datasets of BEIR (English)
+Descriptions of the benchmark datasets used for evaluation are as follows:
+- **ArguAna**  
+  A dataset for argument retrieval based on claim-counterclaim pairs from online debate forums.
+- **FEVER**  
+  A fact verification dataset using Wikipedia for evidence-based claim validation.
+- **FiQA-2018**  
+  A retrieval benchmark tailored to the finance domain with real-world questions and answers.
+- **HotpotQA**  
+  A multi-hop open-domain QA dataset requiring reasoning across multiple documents.
+- **MSMARCO**  
+  A large-scale benchmark using real Bing search queries and corresponding web documents.
+- **NQ**  
+  A Google QA dataset where user questions are answered using Wikipedia articles.
+- **SCIDOCS**  
+  A citation-based document retrieval dataset focused on scientific papers.
+  
+## Direct Use (Semantic Search)
+
+```python
+from sentence_transformers import SentenceTransformer
+  
+# Load the model
+model_name = 'telepix/PIXIE-Rune-v1.0'
+model = SentenceTransformer(model_name)
+
+# Define the queries and documents
+queries = [
+        "텔레픽스는 어떤 산업 분야에서 위성 데이터를 활용하나요?",
+        "국방 분야에 어떤 위성 서비스가 제공되나요?",
+        "텔레픽스의 기술 수준은 어느 정도인가요?",
+]
+documents = [
+        "텔레픽스는 해양, 자원, 농업 등 다양한 분야에서 위성 데이터를 분석하여 서비스를 제공합니다.",
+        "정찰 및 감시 목적의 위성 영상을 통해 국방 관련 정밀 분석 서비스를 제공합니다.",
+        "TelePIX의 광학 탑재체 및 AI 분석 기술은 Global standard를 상회하는 수준으로 평가받고 있습니다.",
+        "텔레픽스는 우주에서 수집한 정보를 분석하여 '우주 경제(Space Economy)'라는 새로운 가치를 창출하고 있습니다.",
+        "텔레픽스는 위성 영상 획득부터 분석, 서비스 제공까지 전 주기를 아우르는 솔루션을 제공합니다.",
+]
+
+# Compute embeddings: use `prompt_name="query"` to encode queries!
+query_embeddings = model.encode(queries, prompt_name="query")
+document_embeddings = model.encode(documents)
+
+# Compute cosine similarity scores
+scores = model.similarity(query_embeddings, document_embeddings)
+
+# Output the results
+for query, query_scores in zip(queries, scores):
+    doc_score_pairs = list(zip(documents, query_scores))
+    doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
+    print("Query:", query)
+    for document, score in doc_score_pairs:
+        print(score, document)
+
+```
+
+## License
+The PIXIE-Rune-v1.0 model is licensed under Apache License 2.0.
+
+## Citation
+```
+@misc{TelePIX-PIXIE-Rune-v1.0,
+  title={PIXIE-Rune-v1.0},
+  author={TelePIX AI Research Team and Bongmin Kim},
+  year={2026},
+  url={https://huggingface.co/telepix/PIXIE-Rune-v1.0}
+}
+```
+
+## Contact
+
+If you have any suggestions or questions about the PIXIE, please reach out to the authors at bmkim@telepix.net.

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "matryoshka_dimensions": [
+    256
+  ],
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.56.2",
+    "pytorch": "2.8.0+cu128"
+  },
+  "prompts": {
+    "query": "query: ",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef21979fce2049a10048bddc7ac464b1d4617b04f82359cea2632350566d5ea
+size 2271064456

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa56838400193ffc08cda0a7a130abefde5035eb652d1a63a63bb9d7d39321b3
+size 614872

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d64606ff97e4abfbac9b03dc713c1fe3de955a66ea9f46c20c6a12d5f0512b
+size 2266886160

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 6144,
+    "do_lower_case": false
+}

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b81d158d38590c83f2e3b4c3644f5eb63136c14a77f6bdb147913ad33a9bbc
+size 17083054

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 6144,
+  "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>"
+}