Squash history

.gitattributes

@@ -0,0 +1,4 @@
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,5 @@
+{
+    "embedding_dimension": 4096,
+    "pooling_mode": "lasttoken",
+    "include_prompt": true
+}

LICENSE

@@ -0,0 +1,238 @@
+comsat-embed-ko-8b-preview — License
+================================
+
+1. Model weights (this fine-tuned model)
+----------------------------------------
+The fine-tuned model weights in this repository are licensed under the
+Creative Commons Attribution-NonCommercial 4.0 International License
+(CC BY-NC 4.0).
+
+  - Human-readable summary: https://creativecommons.org/licenses/by-nc/4.0/
+  - Full legal code:        https://creativecommons.org/licenses/by-nc/4.0/legalcode
+
+You are free to share and adapt the material for NON-COMMERCIAL purposes,
+under the terms of attribution as described in the license. Commercial use is
+not permitted under this license.
+
+2. Third-party components and attribution
+-----------------------------------------
+This model is a fine-tuned derivative of:
+
+    Qwen/Qwen3-Embedding-8B  (https://huggingface.co/Qwen/Qwen3-Embedding-8B)
+    Copyright (c) Alibaba Cloud (the Qwen team)
+    Licensed under the Apache License, Version 2.0.
+
+A copy of the Apache License, Version 2.0 is available at:
+    http://www.apache.org/licenses/LICENSE-2.0
+
+In accordance with the Apache License 2.0, the above copyright and license
+notice for Qwen3-Embedding-8B is retained. See the accompanying NOTICE file
+for the required attribution notices.
+
+
+3. Full license text of the base model (Apache License 2.0)
+-----------------------------------------------------------
+The base model Qwen/Qwen3-Embedding-8B is licensed under the Apache License,
+Version 2.0. Its full text is reproduced below in compliance with Section 4.
+
+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 2024 Alibaba Cloud
+
+   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 +1,14 @@
+comsat-embed-ko-8b-preview
+Copyright (c) 2026 Sionic AI
+
+This model is a fine-tuned derivative of Qwen/Qwen3-Embedding-8B
+(https://huggingface.co/Qwen/Qwen3-Embedding-8B).
+
+The base model weights, tokenizer, and configuration are:
+    Copyright (c) Alibaba Cloud (the Qwen team)
+    Licensed under 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
+
+Modifications from the base model were made by Sionic AI.
+The fine-tuned model weights are distributed under CC BY-NC 4.0 (see LICENSE).

README.md

@@ -0,0 +1,169 @@
+---
+license: cc-by-nc-4.0
+base_model: Qwen/Qwen3-Embedding-8B
+base_model_relation: finetune
+language:
+- ko
+- en
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- mteb
+- korean
+- retrieval
+---
+
+<p align="center">
+  <img src="assets/sionic_ai.png" alt="Sionic AI" width="480"/>
+</p>
+
+# comsat-embed-ko-8b-preview
+
+**comsat-embed-ko-8b-preview** is a decoder-based embedding model developed by **Sionic AI**, optimized for Korean semantic retrieval tasks. Trained on **over 1M Korean examples**, it encodes queries and documents into vectors so that the most relevant documents can be found by similarity. The model is designed to provide high-quality text representations for real-world information retrieval scenarios, including document search, question answering, knowledge base retrieval, and enterprise semantic search. By leveraging Korean retrieval-oriented training data, comsat-embed-ko-8b-preview delivers robust performance across Korean search environments where accurate semantic matching is essential.
+
+## Highlights
+
+- **Korean-specialized** — trained on 1M+ Korean examples and tuned for Korean search; achieves **state-of-the-art average NDCG@10 (0.7930)** on the 9-subset MTEB Korean retrieval benchmark among the compared models.
+- **Long context** — handles inputs up to 8,192 tokens, well suited to long-document retrieval.
+- **Instruction-aware queries** — queries are encoded with a task-instruction prompt to improve retrieval quality; documents need no prefix.
+- **High-dimensional embeddings** — 4096-dimensional, last-token pooled and L2-normalized, compared with cosine similarity.
+
+## Usage
+
+First install the Sentence Transformers library
+
+```bash
+pip install -U sentence-transformers
+```
+
+### Sentence Transformers Usage
+
+> ⚠️ Queries **must** be encoded with the query prompt; documents are encoded **without** any prefix. (Skipping the query prompt slightly degrades retrieval quality.)
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("sionic-ai/comsat-embed-ko-8b-preview")
+
+queries  = ["한국의 수도는 어디인가?"]
+passages = ["대한민국의 수도는 서울특별시이다."]
+
+# Option 1) pass the query prompt explicitly (query only; documents get no prefix)
+q_emb = model.encode(queries,  prompt_name="query", normalize_embeddings=True)
+d_emb = model.encode(passages,                      normalize_embeddings=True)
+
+# Option 2) sentence-transformers 5.x helper API (equivalent result)
+# q_emb = model.encode_query(queries)
+# d_emb = model.encode_document(passages)
+
+scores = q_emb @ d_emb.T   # cosine similarity
+print(scores)
+```
+
+### Transformers Usage
+
+```python
+# Requires transformers>=4.51.0
+
+import torch
+import torch.nn.functional as F
+
+from torch import Tensor
+from transformers import AutoTokenizer, AutoModel
+
+
+def last_token_pool(last_hidden_states: Tensor,
+                 attention_mask: Tensor) -> Tensor:
+    left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
+    if left_padding:
+        return last_hidden_states[:, -1]
+    else:
+        sequence_lengths = attention_mask.sum(dim=1) - 1
+        batch_size = last_hidden_states.shape[0]
+        return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
+
+
+def get_detailed_instruct(task_description: str, query: str) -> str:
+    return f'Instruct: {task_description}\nQuery:{query}'
+
+# Each query must come with a one-sentence instruction that describes the task
+task = 'Given a web search query, retrieve relevant passages that answer the query'
+
+queries = [
+    get_detailed_instruct(task, '한국의 수도는 어디인가?'),
+    get_detailed_instruct(task, '광합성은 어떻게 일어나는가?')
+]
+# No need to add instruction for retrieval documents
+documents = [
+    "대한민국의 수도는 서울특별시이다.",
+    "광합성은 식물이 빛 에너지를 이용해 이산화탄소와 물로 포도당을 합성하는 과정이다."
+]
+input_texts = queries + documents
+
+tokenizer = AutoTokenizer.from_pretrained('sionic-ai/comsat-embed-ko-8b-preview', padding_side='left')
+model = AutoModel.from_pretrained('sionic-ai/comsat-embed-ko-8b-preview')
+
+# We recommend enabling flash_attention_2 for better acceleration and memory saving.
+# model = AutoModel.from_pretrained('sionic-ai/comsat-embed-ko-8b-preview', attn_implementation="flash_attention_2", torch_dtype=torch.bfloat16).cuda()
+
+max_length = 8192
+
+# Tokenize the input texts
+batch_dict = tokenizer(
+    input_texts,
+    padding=True,
+    truncation=True,
+    max_length=max_length,
+    return_tensors="pt",
+)
+batch_dict.to(model.device)
+outputs = model(**batch_dict)
+embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
+
+# normalize embeddings
+embeddings = F.normalize(embeddings, p=2, dim=1)
+scores = (embeddings[:2] @ embeddings[2:].T)
+print(scores.tolist())
+```
+
+### Korean Retrieval Benchmark
+- [LawIRKo](https://huggingface.co/datasets/on-and-on/lawgov_ir-ko): A **Korean legal-domain retrieval dataset** for finding statutes and precedents relevant to legal queries.
+- [SQuADKorV1Retrieval](https://huggingface.co/datasets/yjoonjang/squad_kor_v1): A **Korean Wikipedia passage retrieval dataset** based on Korean SQuAD v1.
+- [AutoRAGRetrieval](https://huggingface.co/datasets/yjoonjang/markers_bm): A **Korean document retrieval dataset** constructed by parsing PDFs from five domains: **finance, public, medical, legal, and commerce**.
+- [Ko-StrategyQA](https://huggingface.co/datasets/taeminlee/Ko-StrategyQA): A Korean **ODQA multi-hop retrieval dataset**, translated from StrategyQA.
+- [PublicHealthQA](https://huggingface.co/datasets/xhluca/publichealth-qa): A **retrieval dataset** focused on **medical and public health domains** in Korean.
+- [BelebeleRetrieval](https://huggingface.co/datasets/mteb/belebele): A **Korean document retrieval dataset** based on FLORES-200.
+- [MultiLongDocRetrieval](https://huggingface.co/datasets/mteb/MultiLongDocRetrieval): A **long-document retrieval dataset** covering various domains in Korean.
+- [MIRACLRetrieval](https://huggingface.co/datasets/mteb/MIRACLRetrieval): A **Korean document retrieval dataset** based on Wikipedia.
+- [MrTidyRetrieval](https://huggingface.co/datasets/mteb/mrtidy): A **Wikipedia-based Korean document retrieval dataset**.
+
+## Performance (MTEB Korean Retrieval, NDCG@10)
+
+All scores are NDCG@10 on the **full corpus**, measured with the standard MTEB evaluation pipeline. For multilingual tasks the Korean subset is used (MLDR=ko, MIRACL/MrTidy=ko, Belebele=kor-kor).
+
+| Model | Avg | MIRACL | MrTidy | MLDR | AutoRAG | Ko-StrategyQA | PublicHealthQA | Belebele | SQuADKorV1 | LawIRKo |
+|---|---|---|---|---|---|---|---|---|---|---|
+| **comsat-embed-ko-8b-preview** | **0.7930** | 0.6964 | 0.6253 | 0.5183 | 0.8518 | 0.8394 | 0.8871 | 0.9853 | 0.9168 | 0.8164 |
+| Qwen/Qwen3-Embedding-8B | 0.7825 | 0.6783 | 0.6187 | 0.5036 | 0.8276 | 0.8363 | 0.8721 | 0.9828 | 0.9063 | 0.8171 |
+| Qwen/Qwen3-Embedding-4B | 0.7718 | 0.6803 | 0.6076 | 0.4895 | 0.8431 | 0.8270 | 0.8693 | 0.9479 | 0.9044 | 0.7769 |
+| upstage/solar-embedding-1-large | 0.7674 | 0.6703 | 0.5766 | 0.3850 | 0.8833 | 0.8366 | 0.8787 | 0.9684 | 0.9521 | 0.7557 |
+| microsoft/harrier-oss-v1-27b | 0.7669 | 0.6653 | 0.5306 | 0.4073 | 0.8176 | 0.8361 | 0.8971 | 0.9538 | 0.9204 | 0.8737 |
+| dragonkue/snowflake-arctic-embed-l-v2.0-ko | 0.7636 | 0.6685 | 0.5712 | 0.4150 | 0.9093 | 0.8050 | 0.8337 | 0.9518 | 0.9447 | 0.7735 |
+| codefuse-ai/F2LLM-v2-8B | 0.7621 | 0.6311 | 0.6162 | 0.3950 | 0.7678 | 0.8371 | 0.9332 | 0.9509 | 0.8874 | 0.8405 |
+| nlpai-lab/KURE-v1 | 0.7603 | 0.6816 | 0.5909 | 0.4521 | 0.8708 | 0.7999 | 0.8193 | 0.9502 | 0.9357 | 0.7426 |
+| telepix/PIXIE-Rune-v1.5 | 0.7602 | 0.6393 | 0.5492 | 0.4340 | 0.8927 | 0.8064 | 0.8426 | 0.9617 | 0.9457 | 0.7705 |
+| nvidia/llama-nemotron-embed-vl-1b-v2 | 0.7579 | 0.6975 | 0.5998 | 0.3704 | 0.8773 | 0.8084 | 0.8223 | 0.9584 | 0.9360 | 0.7513 |
+| dragonkue/BGE-m3-ko | 0.7534 | 0.6833 | 0.6099 | 0.3784 | 0.8738 | 0.7959 | 0.8155 | 0.9503 | 0.9414 | 0.7322 |
+| BAAI/bge-m3 | 0.7508 | 0.7015 | 0.6471 | 0.4273 | 0.8301 | 0.7941 | 0.8041 | 0.9316 | 0.9038 | 0.7174 |
+| intfloat/multilingual-e5-large | 0.7333 | 0.6649 | 0.6421 | 0.2708 | 0.8134 | 0.8035 | 0.8253 | 0.9450 | 0.9056 | 0.7293 |
+| nlpai-lab/KoE5 | 0.7329 | 0.6235 | 0.5841 | 0.2942 | 0.8434 | 0.8001 | 0.8351 | 0.9425 | 0.8980 | 0.7756 |
+
+> Avg is the mean over the 9 subsets (higher is better).
+> Reproduction: evaluated with the MTEB retrieval pipeline (NDCG@10, full corpus); the query prompt is applied to queries only (documents get no prefix).
+
+## License
+
+- Model weights: **cc-by-nc-4.0** (non-commercial use).

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.9.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.11.0+cu128",
+    "sentence_transformers": "5.5.1",
+    "transformers": "5.9.0"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "document": "",
+    "query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:"
+  },
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59185a9c38dc31edf85dcaa93276989bcea825cadad7e432e66296a34bc5c3e4
+size 15134634912

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f82e8f8c173bff1b34626d065393d33938f6d27a7448cfb706bbf9d3c0e651
+size 11422943

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}