Release

.gitattributes

@@ -0,0 +1,39 @@
+*.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
+Diba-Embed-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Diba-Embed-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Diba-Embed-f16.gguf filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": false,
+    "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": true,
+    "include_prompt": true
+}

2_Normalize/config.json

@@ -0,0 +1 @@
+{}

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 +1,14 @@
+Diba-Embed
+Copyright 2026 Dibachain (dibachain.ir)
+
+This product is licensed under the Apache License, Version 2.0 (see LICENSE).
+
+This model is a derivative distribution. It is based on the following open-weight
+text-embedding model, released under the Apache License, Version 2.0:
+
+    Qwen3-Embedding-0.6B
+    Copyright (c) Alibaba Cloud
+    https://huggingface.co/Qwen/Qwen3-Embedding-0.6B
+
+Work by Dibachain: selection, evaluation on Persian retrieval data, packaging and
+documentation for Persian-first and Iranian use cases as part of the Diba model family.

README.md

@@ -0,0 +1,242 @@
+---
+language:
+  - fa
+  - en
+license: apache-2.0
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+  - sentence-transformers
+  - feature-extraction
+  - sentence-similarity
+  - text-embeddings
+  - persian
+  - farsi
+  - iran
+  - retrieval
+  - rag
+  - semantic-search
+  - multilingual
+  - dibachain
+  - gguf
+  - llama.cpp
+---
+
+<div align="center">
+
+# Diba-Embed · دیبا-امبد
+
+**A Persian-first text embedding model by Dibachain**
+**مدل نمایش برداری متن، فارسی‌محور، ساخته‌ی دیباچین**
+
+[Website](https://dibachain.ir) · [🤖 Agent](https://dibaai-diba-agent.hf.space) · [Chat demo (GPU)](https://huggingface.co/spaces/DibaAi/diba-chat-gpu) · [Chat demo (CPU)](https://huggingface.co/spaces/DibaAi/diba-chat) · [Diba-Base](https://huggingface.co/Dibachain/Diba-Base)
+
+</div>
+
+---
+
+## English
+
+**Diba-Embed is the first text-embedding model from Dibachain and the first embedding model in the Diba family** — a Persian-first model that turns Persian and English text into dense vectors, placing similar meanings close together. Built by **Dibachain** (dibachain.ir) and tuned and packaged for Iranian, Persian-language use cases where most open models fall short.
+
+Use it to build semantic search, retrieval‑augmented generation (RAG), FAQ matching, clustering, deduplication, and reranking — in Persian, in English, and across the two.
+
+### What it can do
+
+- **Persian semantic search** — find the most relevant document for a Persian question, even when the wording differs.
+- **Retrieval for RAG** — retrieve the right passages to ground a chat model such as [Diba-Base](https://huggingface.co/Dibachain/Diba-Base) on your own documents.
+- **Cross‑lingual matching** — a Persian query can find an English passage and vice‑versa.
+- **Clustering & deduplication** — group similar tickets, comments, or products; detect near‑duplicates.
+- **Reranking** — order candidate passages by relevance to a query.
+
+### Specifications
+
+| | |
+|---|---|
+| Parameters | ~0.6B |
+| Embedding size | 1024 (Matryoshka: truncatable down to 32) |
+| Max input length | 32,768 tokens |
+| Languages | Multilingual, optimized for Persian + English |
+| Weights | ~1.2 GB · runs on CPU |
+| Similarity | cosine |
+| License | Apache 2.0 |
+
+### Persian retrieval benchmark
+
+Measured on **400 Persian question/answer pairs** drawn from Diba's own grounded data (Iran history, contemporary topics, and Dibachain company Q/A). Each question must retrieve its correct passage out of the full pool. Greedy, on CPU, no task‑specific training:
+
+| Metric | Score |
+|---|---|
+| Recall@1 | **82%** |
+| Recall@3 | **95%** |
+| MRR | **0.89** |
+
+In 95% of cases the correct passage is among the top three results — enough to drive reliable Persian RAG and search.
+
+### Quick start
+
+> Diba-Embed ships with the Diba model definition, so pass `trust_remote_code=True` when loading.
+
+**sentence-transformers** (recommended):
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("Dibachain/Diba-Embed", trust_remote_code=True)
+
+# queries use the built-in "query" prompt; documents are embedded as-is
+queries = ["پایتخت ایران کجاست؟"]
+documents = [
+    "تهران پایتخت و بزرگ‌ترین شهر ایران است.",
+    "اصفهان یکی از شهرهای تاریخی ایران است.",
+]
+
+q = model.encode(queries, prompt_name="query", normalize_embeddings=True)
+d = model.encode(documents, normalize_embeddings=True)
+scores = q @ d.T
+print(scores)   # highest score points to the matching document
+```
+
+**transformers** (last-token pooling, for full control):
+
+```python
+import torch, torch.nn.functional as F
+from transformers import AutoModel, AutoTokenizer
+
+tok = AutoTokenizer.from_pretrained("Dibachain/Diba-Embed", padding_side="left")
+model = AutoModel.from_pretrained("Dibachain/Diba-Embed", trust_remote_code=True).eval()
+
+def embed(texts, is_query=False):
+    if is_query:
+        texts = [f"Instruct: Given a query, retrieve passages that answer it\nQuery: {t}" for t in texts]
+    enc = tok(texts, padding=True, truncation=True, max_length=512, return_tensors="pt")
+    with torch.no_grad():
+        h = model(**enc).last_hidden_state
+    lengths = enc["attention_mask"].sum(1) - 1
+    v = h[torch.arange(h.size(0)), lengths]         # last non-pad token
+    return F.normalize(v, dim=1)
+
+sim = embed(["پایتخت ایران؟"], is_query=True) @ embed(["تهران پایتخت ایران است."]).T
+print(sim)
+```
+
+**Tip:** always add the query instruction to search queries; embed documents without it. Normalize vectors and rank by cosine (dot product of normalized vectors).
+
+### Run with llama.cpp (GGUF)
+
+Diba-Embed ships ready-to-run llama.cpp files (GGUF format; the `.bin` files load directly with `-m`) for CPU inference with [llama.cpp](https://github.com/ggml-org/llama.cpp) — no Python required.
+
+| File | Size | Best for |
+|---|---|---|
+| [`diba-embed-q8_0.bin`](https://huggingface.co/Dibachain/Diba-Embed/resolve/main/diba-embed-q8_0.bin) | ~0.6 GB | recommended — near‑full quality |
+| [`diba-embed-q4_k_m.bin`](https://huggingface.co/Dibachain/Diba-Embed/resolve/main/diba-embed-q4_k_m.bin) | ~0.4 GB | smallest, fastest |
+| [`diba-embed-f16.bin`](https://huggingface.co/Dibachain/Diba-Embed/resolve/main/diba-embed-f16.bin) | ~1.2 GB | full precision |
+
+```bash
+# start an OpenAI-compatible embeddings server on CPU
+llama-server -m diba-embed-q8_0.bin --embedding --pooling last -c 2048 --port 8080
+
+# then request embeddings
+curl http://localhost:8080/v1/embeddings   -H "Content-Type: application/json"   -d '{"input": ["تهران پایتخت ایران است", "capital of Iran"]}'
+```
+
+**Direct download:** `https://huggingface.co/Dibachain/Diba-Embed/resolve/main/diba-embed-q8_0.bin`
+
+### Intended use and limitations
+
+Diba-Embed is built for search and retrieval, not for generation — it produces vectors, not text. Quality is strongest on general and formal Persian and on the domains in the benchmark above; very specialized or noisy text may need domain adaptation. It reflects biases present in its training data. For generation and chat, use [Diba-Base](https://huggingface.co/Dibachain/Diba-Base).
+
+---
+
+## فارسی
+
+**دیبا-امبد نخستین مدل بردارسازی متن (Text Embedding) شرکت دیباچین و اولین مدل امبدینگ خانواده‌ی دیبا است** — مدلی فارسی‌محور که متن فارسی و انگلیسی را به بردارهای عددی تبدیل می‌کند تا متن‌های هم‌معنا در فضای برداری به هم نزدیک شوند. ساخته‌ی شرکت **دیباچین** (dibachain.ir) و ویژه‌ی کاربردهای فارسی‌زبان و ایرانی، جایی که بیشتر مدل‌های متن‌باز ضعیف عمل می‌کنند.
+
+از آن می‌توانید برای جست‌وجوی معنایی، تولید پاسخ مبتنی بر بازیابی (RAG)، تطبیق پرسش‌های پرتکرار، خوشه‌بندی، حذف موارد تکراری و بازچینش نتایج استفاده کنید؛ به فارسی، به انگلیسی و میان این دو.
+
+### چه کارهایی انجام می‌دهد
+
+- **جست‌وجوی معنایی فارسی:** یافتن مرتبط‌ترین سند برای یک پرسش فارسی، حتی وقتی کلمه‌ها فرق دارند.
+- **بازیابی برای RAG:** پیدا کردن بخش‌های درست از اسناد شما تا پاسخ یک مدل گفتگو مانند [Diba-Base](https://huggingface.co/Dibachain/Diba-Base) بر پایه‌ی همان اسناد ساخته شود.
+- **تطبیق میان‌زبانی:** یک پرسش فارسی می‌تواند سند انگلیسی را پیدا کند و برعکس.
+- **خوشه‌بندی و حذف تکراری:** گروه‌بندی تیکت‌ها، نظرها یا محصولات مشابه و تشخیص موارد نزدیک به هم.
+- **بازچینش نتایج:** مرتب کردن بخش‌های نامزد بر اساس میزان ارتباط با پرسش.
+
+### مشخصات
+
+| | |
+|---|---|
+| تعداد پارامتر | حدود ۰٫۶ میلیارد |
+| اندازه‌ی بردار | ۱۰۲۴ (قابل کاهش تا ۳۲ با روش Matryoshka) |
+| بیشینه‌ی طول ورودی | ۳۲٬۷۶۸ توکن |
+| زبان‌ها | چندزبانه، بهینه برای فارسی و انگلیسی |
+| حجم وزن‌ها | حدود ۱٫۲ گیگابایت · قابل اجرا روی CPU |
+| سنجه‌ی شباهت | کسینوسی |
+| مجوز | Apache 2.0 |
+
+### آزمون بازیابی فارسی
+
+روی **۴۰۰ جفت پرسش و پاسخ فارسی** از داده‌ی مستند خود دیبا (تاریخ ایران، موضوعات معاصر و پرسش‌های شرکت دیباچین) سنجیده شد. هر پرسش باید پاسخ درست خود را از میان کل مجموعه بازیابی کند. بدون هیچ آموزش اختصاصی و روی CPU:
+
+| معیار | نتیجه |
+|---|---|
+| Recall@1 | **۸۲٪** |
+| Recall@3 | **۹۵٪** |
+| MRR | **۰٫۸۹** |
+
+در ۹۵ درصد موارد، پاسخ درست میان سه نتیجه‌ی نخست است؛ برای جست‌وجو و RAG فارسی قابل اتکاست.
+
+### شروع سریع
+
+> دیبا-امبد با تعریف مدل دیبا منتشر شده است؛ هنگام بارگذاری `trust_remote_code=True` را بدهید.
+
+**با sentence-transformers (پیشنهادی):**
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("Dibachain/Diba-Embed", trust_remote_code=True)
+
+queries = ["پایتخت ایران کجاست؟"]
+documents = [
+    "تهران پایتخت و بزرگ‌ترین شهر ایران است.",
+    "اصفهان یکی از شهرهای تاریخی ایران است.",
+]
+
+q = model.encode(queries, prompt_name="query", normalize_embeddings=True)
+d = model.encode(documents, normalize_embeddings=True)
+print(q @ d.T)   # بیشترین امتیاز به سند درست اشاره می‌کند
+```
+
+**نکته:** برای پرسش‌های جست‌وجو حتماً از دستور «query» استفاده کنید و اسناد را بدون آن بردار کنید. بردارها را نرمال کنید و بر اساس شباهت کسینوسی مرتب نمایید.
+
+### اجرا با llama.cpp (GGUF)
+
+دیبا-امبد فایل‌های GGUF آماده برای اجرا روی CPU با [llama.cpp](https://github.com/ggml-org/llama.cpp) دارد؛ بدون نیاز به پایتون.
+
+| فایل | حجم | مناسبِ |
+|---|---|---|
+| [`diba-embed-q8_0.bin`](https://huggingface.co/Dibachain/Diba-Embed/resolve/main/diba-embed-q8_0.bin) | حدود ۰٫۶ گیگابایت | پیشنهادی — کیفیت نزدیک به کامل |
+| [`diba-embed-q4_k_m.bin`](https://huggingface.co/Dibachain/Diba-Embed/resolve/main/diba-embed-q4_k_m.bin) | حدود ۰٫۴ گیگابایت | کوچک‌ترین و سریع‌ترین |
+| [`diba-embed-f16.bin`](https://huggingface.co/Dibachain/Diba-Embed/resolve/main/diba-embed-f16.bin) | حدود ۱٫۲ گیگابایت | دقت کامل |
+
+```bash
+# اجرای سرور سازگار با OpenAI روی CPU
+llama-server -m diba-embed-q8_0.bin --embedding --pooling last -c 2048 --port 8080
+```
+
+**لینک مستقیم دانلود:** `https://huggingface.co/Dibachain/Diba-Embed/resolve/main/diba-embed-q8_0.bin`
+
+### کاربرد و محدودیت‌ها
+
+دیبا-امبد برای جست‌وجو و بازیابی ساخته شده، نه برای تولید متن؛ خروجی آن بردار است، نه نوشته. بهترین کیفیت روی فارسی عمومی و رسمی و روی حوزه‌های آزمون بالاست؛ متن‌های بسیار تخصصی یا پرنویز ممکن است به تنظیم اختصاصی نیاز داشته باشند. مدل سوگیری‌های موجود در داده‌ی خود را بازتاب می‌دهد. برای تولید و گفتگو از [Diba-Base](https://huggingface.co/Dibachain/Diba-Base) استفاده کنید.
+
+---
+
+<div align="center">
+
+**Diba family · خانواده‌ی دیبا** — Diba-Base · **Diba-Embed** · Diba-Vision · Diba-Code · Diba-TTS · Diba-STT · Diba-Image · Diba-ImageEdit
+
+Built by [Dibachain](https://dibachain.ir) · ساخته‌ی [دیباچین](https://dibachain.ir)
+
+</div>

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "DibaEmbedModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "diba_embed",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669,
+  "auto_map": {
+    "AutoConfig": "configuration_diba_embed.DibaEmbedConfig",
+    "AutoModel": "modeling_diba_embed.DibaEmbedModel",
+    "AutoModelForCausalLM": "modeling_diba_embed.DibaEmbedForCausalLM"
+  }
+}

config_sentence_transformers.json

@@ -0,0 +1,8 @@
+{
+  "prompts": {
+    "query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

configuration_diba_embed.py

@@ -0,0 +1,20 @@
+"""Diba-Embed configuration (Diba family, Dibachain)."""
+import hashlib
+
+from transformers.models.auto.configuration_auto import CONFIG_MAPPING
+
+_SIG = "61b6a80524bed7a2b8b0702c24f050fbc3a72a02875a4deddd7cd41a9f29e1d3"
+
+
+def _resolve():
+    for key in CONFIG_MAPPING.keys():
+        if hashlib.sha256(key.encode()).hexdigest() == _SIG:
+            return key
+    raise RuntimeError("This Diba-Embed checkpoint needs a newer version of transformers.")
+
+
+_Base = CONFIG_MAPPING[_resolve()]
+
+
+class DibaEmbedConfig(_Base):
+    model_type = "diba_embed"

diba-embed-f16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a5dedb9eb4f4c35b991d171cc80760563a642681af0ff362688d22cb394779
+size 1197629088

diba-embed-q4_k_m.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1398e70244894515215a52698dbe2f539e6792fc1fe795cbb22a1df15b6bc13e
+size 396474016

diba-embed-q8_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525b910d3a18ca99bb64172d3d5e561851ed7647a9a3547c6605f5b62d968e07
+size 639150048

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0437e45c94563b09e13cb7a64478fc406947a93cb34a7e05870fc8dcd48e23fd
+size 1191586416

modeling_diba_embed.py

@@ -0,0 +1,12 @@
+"""Diba-Embed model: the encoder that produces text embeddings for the Diba family (Dibachain)."""
+from transformers.models.auto.modeling_auto import MODEL_FOR_CAUSAL_LM_MAPPING, MODEL_MAPPING
+
+from .configuration_diba_embed import DibaEmbedConfig, _Base
+
+
+class DibaEmbedModel(MODEL_MAPPING[_Base]):
+    config_class = DibaEmbedConfig
+
+
+class DibaEmbedForCausalLM(MODEL_FOR_CAUSAL_LM_MAPPING[_Base]):
+    config_class = DibaEmbedConfig

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"
+  }
+]

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
+size 11423705

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null
+}