Release dots3-note preview

.gitattributes

@@ -0,0 +1,44 @@
+*.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
+assets/bench_en1.png filter=lfs diff=lfs merge=lfs -text
+assets/bench_en2.png filter=lfs diff=lfs merge=lfs -text
+assets/bench_cn1.png filter=lfs diff=lfs merge=lfs -text
+assets/bench_cn2.png filter=lfs diff=lfs merge=lfs -text
+assets/benchmark_appendix_en_reasoning.png filter=lfs diff=lfs merge=lfs -text
+assets/benchmark_appendix_en_multimodal.png filter=lfs diff=lfs merge=lfs -text
+assets/benchmark_appendix_cn_reasoning.png filter=lfs diff=lfs merge=lfs -text
+assets/benchmark_appendix_cn_multimodal.png filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,315 @@
+---
+
+license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+- dots3
+- dots3-note
+- audio
+- multimodal
+- long-context
+- agentic
+
+
+---
+
+<p align="left">
+  <a href="https://huggingface.co/dots-studio/dots3-note-prev/blob/main/README_CN.md">中文</a>&nbsp;｜&nbsp;English
+</p>
+<br>
+
+<div align="center">
+  <img src="assets/dots%20logo@3x.png" alt="dots logo" width="200" />
+  <h1>dots3-note Preview</h1>
+</div>
+
+<div align="center" style="line-height: 1;">
+  <a href="https://github.com/studio-dots-ai/dots3-note-prev"><img alt="GitHub: studio-dots-ai" src="https://img.shields.io/badge/GitHub-studio--dots--ai-181717?logo=github&amp;logoColor=white" /></a>
+  <a href="https://github.com/huggingface/transformers/pull/47844"><img alt="Transformers: dots3-note" src="https://img.shields.io/badge/Transformers-dots3--note-yellow" /></a>
+  <a href="https://github.com/sgl-project/sglang/pull/33829"><img alt="SGLang: dots3-note" src="https://img.shields.io/badge/SGLang-dots3--note-blue" /></a>
+  <a href="https://recipes.vllm.ai/dots-studio/dots3-note-prev"><img alt="vLLM: dots3-note" src="https://img.shields.io/badge/vLLM-dots3--note-red" /></a>
+  <a href="https://modelscope.cn/collections/dots-studio/dots3-note"><img alt="ModelScope: dots-studio" src="https://img.shields.io/badge/ModelScope-dots--studio-624AFF" /></a>
+
+  <a href="https://www.xiaohongshu.com/user/profile/683ffe42000000001d021a4c"><img alt="Dots Studio" src="https://img.shields.io/badge/RedNote-Dots%20Studio-FF2442" /></a>
+  <a href="https://discord.gg/haym6hEUE"><img alt="Discord" src="https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&amp;logoColor=white" /></a>
+  <a href="https://x.com/dotsstudioai"><img alt="X: dotsstudioai" src="https://img.shields.io/badge/X-%40dotsstudioai-black" /></a>
+  <a href="#license"><img alt="License: Apache 2.0" src="https://img.shields.io/badge/License-Apache%202.0-blue" /></a>
+</div>
+
+<p align="center">
+  🌐&nbsp;<a href="https://studio.dots.ai/dots/dots3-en.html"><b>Tech Blog</b></a>&nbsp;&nbsp;|&nbsp;&nbsp;
+  📄&nbsp;<b>Full Report (coming soon)</b>
+</p>
+
+---
+
+
+## Table of Contents
+
+- [Model Introduction](#model-introduction)
+- [Model Overview](#model-overview)
+- [Evaluation Results](#evaluation-results)
+  - [General Reasoning and Agent](#general-reasoning-and-agent)
+  - [Multimodal Understanding](#multimodal-understanding)
+- [Model Links](#model-links)
+- [Quickstart](#quickstart)
+- [Deployment](#deployment)
+  - [Transformers](#transformers)
+  - [SGLang](#sglang)
+  - [vLLM](#vllm)
+- [Benchmark Appendix](#benchmark-appendix)
+- [License](#license)
+- [Contact Us](#contact-us)
+
+---
+
+## Model Introduction
+
+dots3-note preview is the first open-weight model in the dots3 family. It is a Mixture-of-Experts model with 280B total parameters, 16B activated parameters, and support for a context length of up to 512K tokens. The model can understand text, images, video, and audio, and produces text outputs.
+
+dots3-note preview is optimized for a broad range of tasks, including:
+
+- General knowledge and instruction following;
+- Mathematical and logical reasoning;
+- Tool use and multi-step agent workflows;
+- Interactive tasks that require exploration, memory updates, and adaptation;
+- Code generation and code-based problem solving;
+- Image, document, chart, audio, and video understanding;
+- Long-context information processing.
+
+The dots3 family is designed to include models with different trade-offs among capability, latency, and inference cost. dots3-note preview is the most lightweight member of the family.
+
+
+
+## Model Overview
+
+| Property | Value |
+| :--- | :--- |
+| Architecture | Multimodal MoE |
+| Total Parameters | 280B |
+| Activated Parameters | 16B |
+| MTP | 1 shared layer, 1.13B |
+| Number of Layers | 1 dense + 45 MoE |
+| Hidden Size | 5120 |
+| FFN Hidden Size | 13824 (dense), 1536 (per expert) |
+| Experts | 256 routed + 1 shared, top-8 |
+| Attention | 13 DSA + 33 SWA (~1:3) |
+| DSA | Top-2048 |
+| Context Length | 512K |
+| Vocabulary Size | 152K |
+| Vision Encoder | MoE ViT, 7B total, 1.2B activated |
+| Audio Encoder | Dense, 800M |
+| Supported Precision | BF16, FP8 |
+| Input | Text, image, video, audio |
+| Output | Text |
+
+
+## Evaluation Results
+
+### General Reasoning and Agent
+
+![General Reasoning and Agent evaluation results](assets/bench_en1.png)
+
+### Multimodal Understanding
+
+![Multimodal Understanding evaluation results](assets/bench_en2.png)
+
+## Model Links
+
+| Model Name | Description | HuggingFace | ModelScope |
+| --- | --- | --- | --- |
+| dots3-note-prev | Preview multimodal model | 🤗 [Model](https://huggingface.co/dots-studio/dots3-note-prev) | <span style="white-space: nowrap;"><img src="https://modelscope.cn/favicon.ico" width="16" alt="ModelScope" style="display: inline-block; vertical-align: middle; margin: 0;" />&nbsp;<a href="https://modelscope.cn/models/dots-studio/dots3-note-prev">Model</a></span> |
+| dots3-note-prev-fp8 | FP8-quantized preview multimodal model | 🤗 [Model](https://huggingface.co/dots-studio/dots3-note-prev-fp8) | <span style="white-space: nowrap;"><img src="https://modelscope.cn/favicon.ico" width="16" alt="ModelScope" style="display: inline-block; vertical-align: middle; margin: 0;" />&nbsp;<a href="https://modelscope.cn/models/dots-studio/dots3-note-prev-fp8">Model</a></span> |
+
+## Quickstart
+
+Recommended: serve the FP8 checkpoint on one 8-GPU node with [SGLang](#sglang) or [vLLM](#vllm).
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://127.0.0.1:8000/v1", api_key="EMPTY")
+
+response = client.chat.completions.create(
+    model="dots3-note-prev",
+    messages=[
+        {"role": "user", "content": "Hello! Can you briefly introduce yourself?"},
+    ],
+    temperature=1.0,
+    top_p=0.95,
+    max_tokens=256,
+    # Set enable_thinking=True for reasoning; False returns a direct response.
+    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
+)
+print(response.choices[0].message.content)
+```
+
+For a multimodal request, replace `messages` with one of these public examples:
+
+```python
+examples = {
+    "image": [
+        {"type": "image_url", "image_url": {"url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png"}},
+        {"type": "text", "text": "How many cats are in this image?"},
+    ],
+    "audio": [
+        {"type": "audio_url", "audio_url": {"url": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mary_had_lamb.mp3"}},
+        {"type": "text", "text": "Transcribe this nursery rhyme."},
+    ],
+    "video": [
+        {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
+        {"type": "text", "text": "Describe the performance and what can be heard."},
+    ],
+}
+messages = [{"role": "user", "content": examples["image"]}]
+```
+
+Video inputs include their audio track when available.
+
+## Deployment
+
+The commands below target FP8 on one 8-GPU node. BF16 requires more memory. Tune the context length to available memory, concurrency, and input modalities.
+
+Native support is available on [vLLM](https://recipes.vllm.ai/dots-studio/dots3-note-prev) `main`. [Transformers #47844](https://github.com/huggingface/transformers/pull/47844) and [SGLang #33829](https://github.com/sgl-project/sglang/pull/33829) are still under review; until they are merged, use the PR revisions below.
+
+### Transformers
+
+First install mutually compatible [PyTorch and torchvision](https://pytorch.org/get-started/locally/) builds supported by your NVIDIA driver. For audio and video, also install a PyTorch-compatible `torchcodec` (included below) and FFmpeg with your system package manager. Then install [Transformers #47844](https://github.com/huggingface/transformers/pull/47844):
+
+```bash
+pip install accelerate pillow torchcodec kernels==0.16.0 "transformers @ git+https://github.com/huggingface/transformers.git@refs/pull/47844/head"
+```
+
+Run a minimal local inference:
+
+```python
+from transformers import AutoModelForMultimodalLM, AutoProcessor
+
+model_id = "dots-studio/dots3-note-prev-fp8"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForMultimodalLM.from_pretrained(model_id, dtype="auto", device_map="auto")
+
+messages = [
+    {"role": "user", "content": "Hello! Please briefly introduce yourself."},
+]
+inputs = processor.tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt",
+    return_dict=True,
+    enable_thinking=False,
+).to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=128)
+print(processor.decode(outputs[0, inputs.input_ids.shape[1] :], skip_special_tokens=True))
+```
+
+Use SGLang or vLLM for multi-GPU OpenAI-compatible serving.
+
+### SGLang
+
+
+Recommended: use the release image [lmsysorg/sglang:dev-dots3-note](https://hub.docker.com/r/lmsysorg/sglang/tags). Full one-node recipes and tuning notes are in the [Dots3-Note cookbook](https://github.com/sgl-project/sglang/blob/main/docs/cookbook/autoregressive/RedNote/Dots3-Note.mdx). Source support is tracked in [SGLang #33829](https://github.com/sgl-project/sglang/pull/33829).
+
+Docker (the image downloads the checkpoint from Hugging Face on first run):
+
+```bash
+docker run --gpus all --ipc=host -p 8000:8000 \
+  lmsysorg/sglang:dev-dots3-note \
+  sglang serve \
+    --model-path dots-studio/dots3-note-prev-fp8 \
+    --served-model-name dots3-note-prev \
+    --host 0.0.0.0 \
+    --port 8000 \
+    --context-length 524288 \
+    --enable-dp-attention \
+    --dp-size 8 \
+    --tp-size 8 \
+    --ep-size 8 \
+    --moe-dense-tp-size 1 \
+    --page-size 64 \
+    --trust-remote-code \
+    --attention-backend fa3 \
+    --moe-a2a-backend deepep \
+    --enable-multimodal \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-path dots-studio/dots3-note-prev-fp8
+```
+
+Or install from source / the PR and run the same `sglang serve` arguments locally. `--attention-backend fa3` sets prefill, decode, and (when speculative decoding is enabled) draft attention. MTP/NEXTN (`--speculative-algorithm NEXTN` and the related flags) is optional and can reduce TPOT by more than 50%. Prefill CUDA graph is not supported yet.
+
+Optional features:
+
+```bash
+# Load only the language model
+--language-only
+
+# Enable OpenAI-compatible tool calling
+--tool-call-parser dots
+```
+
+### vLLM
+
+Native dots3-note preview support is available on [vLLM](https://recipes.vllm.ai/dots-studio/dots3-note-prev) `main`. Use a recent nightly build until it is included in a stable release.
+
+The following example deploys the FP8 checkpoint on eight NVIDIA H100 GPUs with TP=8 and EP=8:
+
+```bash
+vllm serve dots-studio/dots3-note-prev-fp8 \
+  --served-model-name dots3-note-prev \
+  --host 0.0.0.0 \
+  --tensor-parallel-size 8 \
+  --enable-expert-parallel \
+  --moe-backend deep_gemm \
+  --max-model-len 262144
+```
+
+Optional features:
+
+```bash
+# Load only the language model
+--language-model-only
+
+# Enable three-token MTP speculative decoding
+--speculative-config '{"method":"mtp","num_speculative_tokens":3}'
+
+# Enable OpenAI-compatible automatic tool calling
+--enable-auto-tool-choice --tool-call-parser dots
+
+```
+
+## Benchmark Appendix
+
+![General Reasoning and Agent benchmark appendix](assets/benchmark_appendix_en_reasoning.png)
+
+![Multimodal benchmark appendix](assets/benchmark_appendix_en_multimodal.png)
+
+## License
+
+Copyright (c) 2026 Xiaohongshu.
+
+Developed and released by dots studio.
+
+The dots3-note preview model weights and modeling code in this repository are licensed under the Apache License, Version 2.0.
+
+See the LICENSE file for details.
+
+Transformers, SGLang, vLLM, and other third-party software are subject to their respective licenses.
+
+
+## Contact Us
+
+For questions and feedback, please contact us through:
+ 
+- Email: dots-model-feedback@xiaohongshu.com
+
+---
+
+<p align="center">
+
+<i>dots3-note preview is developed and released by dots studio.</i>
+
+</p>

README_CN.md

@@ -0,0 +1,292 @@
+<p align="left">
+  <a href="https://huggingface.co/dots-studio/dots3-note-prev">English</a>&nbsp;｜&nbsp;中文
+</p>
+<br>
+
+<div align="center">
+  <img src="assets/dots%20logo@3x.png" alt="dots logo" width="200" />
+  <h1>dots3-note Preview</h1>
+</div>
+
+<div align="center" style="line-height: 1;">
+  <a href="https://github.com/studio-dots-ai/dots3-note-prev"><img alt="GitHub: studio-dots-ai" src="https://img.shields.io/badge/GitHub-studio--dots--ai-181717?logo=github&amp;logoColor=white" /></a>
+  <a href="https://github.com/huggingface/transformers/pull/47844"><img alt="Transformers: dots3-note" src="https://img.shields.io/badge/Transformers-dots3--note-yellow" /></a>
+  <a href="https://github.com/sgl-project/sglang/pull/33829"><img alt="SGLang: dots3-note" src="https://img.shields.io/badge/SGLang-dots3--note-blue" /></a>
+  <a href="https://recipes.vllm.ai/dots-studio/dots3-note-prev"><img alt="vLLM: dots3-note" src="https://img.shields.io/badge/vLLM-dots3--note-red" /></a>
+  <a href="https://modelscope.cn/collections/dots-studio/dots3-note"><img alt="ModelScope: dots-studio" src="https://img.shields.io/badge/ModelScope-dots--studio-624AFF" /></a>
+
+  <a href="https://www.xiaohongshu.com/user/profile/683ffe42000000001d021a4c"><img alt="Dots Studio" src="https://img.shields.io/badge/RedNote-Dots%20Studio-FF2442" /></a>
+  <a href="https://discord.gg/haym6hEUE"><img alt="Discord" src="https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&amp;logoColor=white" /></a>
+  <a href="https://x.com/dotsstudioai"><img alt="X: dotsstudioai" src="https://img.shields.io/badge/X-%40dotsstudioai-black" /></a>
+  <a href="#许可证"><img alt="License: Apache 2.0" src="https://img.shields.io/badge/License-Apache%202.0-blue" /></a>
+</div>
+
+<p align="center">
+  🌐&nbsp;<a href="https://studio.dots.ai/dots/dots3-zh.html"><b>技术博客</b></a>&nbsp;&nbsp;|&nbsp;&nbsp;
+  📄&nbsp;<b>完整报告（即将发布）</b>
+</p>
+
+---
+
+## 目录
+
+- [模型介绍](#模型介绍)
+- [模型概览](#模型概览)
+- [评测结果](#评测结果)
+  - [通用推理与智能体](#通用推理与智能体)
+  - [多模态理解](#多模态理解)
+- [模型链接](#模型链接)
+- [快速开始](#快速开始)
+- [部署](#部署)
+  - [Transformers](#transformers)
+  - [SGLang](#sglang)
+  - [vLLM](#vllm)
+- [评测附录](#评测附录)
+- [许可证](#许可证)
+- [联系我们](#联系我们)
+
+---
+
+## 模型介绍
+
+dots3-note preview 是 dots3 系列首个开放权重模型。该模型采用混合专家（Mixture-of-Experts，MoE）架构，总参数量为 280B，激活参数量为 16B，支持最长 512K 个 token 的上下文。模型支持文本、图像、视频和音频理解，并生成文本输出。
+
+dots3-note preview 针对以下任务进行了优化：
+
+- 通用知识与指令遵循；
+- 数学与逻辑推理；
+- 工具使用与多步骤智能体工作流；
+- 需要探索、记忆更新和适应能力的交互式任务；
+- 代码生成与基于代码的问题求解；
+- 图像、文档、图表、音频和视频理解；
+- 长上下文信息处理。
+
+dots3 系列包含在能力、时延和推理成本之间采用不同权衡的多款模型，dots3-note preview 是该系列中最轻量级的成员。
+
+## 模型概览
+
+| 属性 | 值 |
+| :--- | :--- |
+| 架构 | 多模态混合专家模型（MoE） |
+| 总参数量 | 280B |
+| 激活参数量 | 16B |
+| MTP | 1 个共享层，1.13B 参数 |
+| 层数 | 1 个稠密层 + 45 个 MoE 层 |
+| 隐藏层维度 | 5120 |
+| FFN 中间层维度 | 13824（稠密层），1536（每个专家） |
+| 专家数量 | 256 个路由专家 + 1 个共享专家，Top-8 激活 |
+| 注意力机制 | 13 DSA + 33 SWA（约 1:3） |
+| DSA | Top-2048 |
+| 上下文长度 | 512K |
+| 词表大小 | 152K |
+| 视觉编码器 | MoE ViT，总参数量 7B，激活参数量 1.2B |
+| 音频编码器 | 稠密模型，800M |
+| 支持精度 | BF16、FP8 |
+| 输入 | 文本、图像、视频、音频 |
+| 输出 | 文本 |
+
+## 评测结果
+
+### 通用推理与智能体
+
+![通用推理与智能体评测结果](assets/bench_cn1.png)
+
+### 多模态理解
+
+![多模态理解评测结果](assets/bench_cn2.png)
+
+## 模型链接
+
+| 模型名称 | 简介 | Hugging Face | ModelScope |
+| --- | --- | --- | --- |
+| dots3-note-prev | 预览版多模态模型 | 🤗 [模型](https://huggingface.co/dots-studio/dots3-note-prev) | <span style="white-space: nowrap;"><img src="https://modelscope.cn/favicon.ico" width="16" alt="ModelScope" style="display: inline-block; vertical-align: middle; margin: 0;" />&nbsp;<a href="https://modelscope.cn/models/dots-studio/dots3-note-prev">模型</a></span> |
+| dots3-note-prev-fp8 | FP8 量化预览版多模态模型 | 🤗 [模型](https://huggingface.co/dots-studio/dots3-note-prev-fp8) | <span style="white-space: nowrap;"><img src="https://modelscope.cn/favicon.ico" width="16" alt="ModelScope" style="display: inline-block; vertical-align: middle; margin: 0;" />&nbsp;<a href="https://modelscope.cn/models/dots-studio/dots3-note-prev-fp8">模型</a></span> |
+
+## 快速开始
+
+建议使用 [SGLang](#sglang) 或 [vLLM](#vllm)，在单个 8 卡节点上部署 FP8 权重。
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://127.0.0.1:8000/v1", api_key="EMPTY")
+
+response = client.chat.completions.create(
+    model="dots3-note-prev",
+    messages=[
+        {"role": "user", "content": "你好！请简单介绍一下你自己。"},
+    ],
+    temperature=1.0,
+    top_p=0.95,
+    max_tokens=256,
+    # 启用推理时设置 enable_thinking=True；设置为 False 时直接回复。
+    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
+)
+print(response.choices[0].message.content)
+```
+
+如需发起多模态请求，可将 `messages` 替换为以下任一公开示例：
+
+```python
+examples = {
+    "image": [
+        {"type": "image_url", "image_url": {"url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png"}},
+        {"type": "text", "text": "这张图片中有几只猫？"},
+    ],
+    "audio": [
+        {"type": "audio_url", "audio_url": {"url": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mary_had_lamb.mp3"}},
+        {"type": "text", "text": "请转写这段童谣。"},
+    ],
+    "video": [
+        {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
+        {"type": "text", "text": "请描述这场表演以及视频中可以听到的内容。"},
+    ],
+}
+messages = [{"role": "user", "content": examples["image"]}]
+```
+
+如果视频包含音轨，模型也会同时处理其中的音频。
+
+## 部署
+
+以下命令面向单个 8 卡节点上的 FP8 部署。BF16 需要更多显存，请根据可用显存、并发量和输入模态调整上下文长度。
+
+[vLLM](https://recipes.vllm.ai/dots-studio/dots3-note-prev) 的 `main` 分支已原生支持 dots3-note preview。[Transformers #47844](https://github.com/huggingface/transformers/pull/47844) 和 [SGLang #33829](https://github.com/sgl-project/sglang/pull/33829) 仍在审核中；合并前请使用下文指定的 PR 版本。
+
+### Transformers
+
+请先安装 NVIDIA 驱动支持且相互兼容的 [PyTorch 和 torchvision](https://pytorch.org/get-started/locally/) 版本。若需处理音频和视频，还应安装与 PyTorch 兼容的 `torchcodec`（包含在下方命令中），并通过系统包管理器安装 FFmpeg。随后安装 [Transformers #47844](https://github.com/huggingface/transformers/pull/47844)：
+
+```bash
+pip install accelerate pillow torchcodec kernels==0.16.0 "transformers @ git+https://github.com/huggingface/transformers.git@refs/pull/47844/head"
+```
+
+运行最小化本地推理示例：
+
+```python
+from transformers import AutoModelForMultimodalLM, AutoProcessor
+
+model_id = "dots-studio/dots3-note-prev-fp8"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForMultimodalLM.from_pretrained(model_id, dtype="auto", device_map="auto")
+
+messages = [
+    {"role": "user", "content": "你好！请简单介绍一下你自己。"},
+]
+inputs = processor.tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt",
+    return_dict=True,
+    enable_thinking=False,
+).to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=128)
+print(processor.decode(outputs[0, inputs.input_ids.shape[1] :], skip_special_tokens=True))
+```
+
+如需提供多 GPU、兼容 OpenAI API 的服务，请使用 SGLang 或 vLLM。
+
+### SGLang
+
+推荐使用发布镜像 [lmsysorg/sglang:dev-dots3-note](https://hub.docker.com/r/lmsysorg/sglang/tags)。完整的单节点部署方案和调优说明请参阅 [Dots3-Note cookbook](https://github.com/sgl-project/sglang/blob/main/docs/cookbook/autoregressive/RedNote/Dots3-Note.mdx)。源码支持进展请参阅 [SGLang #33829](https://github.com/sgl-project/sglang/pull/33829)。
+
+Docker 部署（首次运行时，镜像会从 Hugging Face 下载模型权重）：
+
+```bash
+docker run --gpus all --ipc=host -p 8000:8000 \
+  lmsysorg/sglang:dev-dots3-note \
+  sglang serve \
+    --model-path dots-studio/dots3-note-prev-fp8 \
+    --served-model-name dots3-note-prev \
+    --host 0.0.0.0 \
+    --port 8000 \
+    --context-length 524288 \
+    --enable-dp-attention \
+    --dp-size 8 \
+    --tp-size 8 \
+    --ep-size 8 \
+    --moe-dense-tp-size 1 \
+    --page-size 64 \
+    --trust-remote-code \
+    --attention-backend fa3 \
+    --moe-a2a-backend deepep \
+    --enable-multimodal \
+    --speculative-algorithm NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4 \
+    --speculative-draft-model-path dots-studio/dots3-note-prev-fp8
+```
+
+也可以从源码或相应 PR 安装，并在本地使用相同的 `sglang serve` 参数。`--attention-backend fa3` 会设置预填充、解码以及启用投机解码时的草稿模型注意力后端。MTP/NEXTN（`--speculative-algorithm NEXTN` 及相关参数）为可选功能，可将 TPOT 降低 50% 以上。目前尚不支持预填充阶段的 CUDA Graph。
+
+可选功能：
+
+```bash
+# 仅加载语言模型
+--language-only
+
+# 启用兼容 OpenAI API 的工具调用
+--tool-call-parser dots
+```
+
+### vLLM
+
+[vLLM](https://recipes.vllm.ai/dots-studio/dots3-note-prev) 的 `main` 分支已原生支持 dots3-note preview。在该功能进入稳定版本前，请使用较新的 nightly build。
+
+以下示例使用 8 张 NVIDIA H100 GPU，以 TP=8、EP=8 部署 FP8 权重：
+
+```bash
+vllm serve dots-studio/dots3-note-prev-fp8 \
+  --served-model-name dots3-note-prev \
+  --host 0.0.0.0 \
+  --tensor-parallel-size 8 \
+  --enable-expert-parallel \
+  --moe-backend deep_gemm \
+  --max-model-len 262144
+```
+
+可选功能：
+
+```bash
+# 仅加载语言模型
+--language-model-only
+
+# 启用 3-token MTP 投机解码
+--speculative-config '{"method":"mtp","num_speculative_tokens":3}'
+
+# 启用兼容 OpenAI API 的自动工具调用
+--enable-auto-tool-choice --tool-call-parser dots
+```
+
+## 评测附录
+
+![通用推理与智能体评测附录](assets/benchmark_appendix_cn_reasoning.png)
+
+![多模态评测附录](assets/benchmark_appendix_cn_multimodal.png)
+
+## 许可证
+
+Copyright (c) 2026 Xiaohongshu.
+
+由 dots studio 开发并发布。
+
+本仓库中的 dots3-note preview 模型权重和建模代码基于 Apache License 2.0 发布。
+
+详情请参阅 LICENSE 文件。
+
+Transformers、SGLang、vLLM 及其他第三方软件适用其各自的许可证。
+
+## 联系我们
+
+如有问题或反馈，请通过以下方式联系我们：
+
+- 邮箱：dots-model-feedback@xiaohongshu.com
+
+---
+
+<p align="center">
+
+<i>dots3-note preview is developed and released by dots studio.</i>
+
+</p>

added_tokens.json

@@ -0,0 +1,87 @@
+{
+  "<|alttext|>": 151711,
+  "<|assistant|>": 151667,
+  "<|audio_comp_end|>": 151719,
+  "<|audio_comp_pad|>": 151720,
+  "<|audio_comp_start|>": 151718,
+  "<|audio_gen_end|>": 151716,
+  "<|audio_gen_pad|>": 151717,
+  "<|audio_gen_start|>": 151715,
+  "<|box_end|>": 151670,
+  "<|box_start|>": 151669,
+  "<|discarddensecaption|>": 151712,
+  "<|endofalttext|>": 151713,
+  "<|endofassistant|>": 151668,
+  "<|endofexecution|>": 151655,
+  "<|endofimg|>": 151662,
+  "<|endofobservation|>": 151653,
+  "<|endofpdfmeta|>": 151710,
+  "<|endofresponse|>": 151649,
+  "<|endofslice|>": 151678,
+  "<|endofsystemprompt|>": 151664,
+  "<|endofsystem|>": 151651,
+  "<|endoftext|>": 151643,
+  "<|endofurl|>": 151708,
+  "<|endofuserprompt|>": 151647,
+  "<|endofuser|>": 151666,
+  "<|execution|>": 151654,
+  "<|im_end>": 151659,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|imgpad|>": 151660,
+  "<|imgrowend|>": 151679,
+  "<|img|>": 151661,
+  "<|observation|>": 151652,
+  "<|pdfmeta|>": 151709,
+  "<|pictotext|>": 151676,
+  "<|pic|>": 151674,
+  "<|polygon_end|>": 151682,
+  "<|polygon_start|>": 151681,
+  "<|ref_end|>": 151672,
+  "<|ref_start|>": 151671,
+  "<|reject-unknown|>": 151656,
+  "<|response|>": 151648,
+  "<|sec-cot|>": 151657,
+  "<|sec-end-cot|>": 151658,
+  "<|slice|>": 151677,
+  "<|systemprompt|>": 151663,
+  "<|system|>": 151650,
+  "<|task:doc layout with format json|>": 151700,
+  "<|task:image captioning|>": 151701,
+  "<|task:image en-captioning|>": 151683,
+  "<|task:image en-concept|>": 151689,
+  "<|task:image en-dense-captioning|>": 151687,
+  "<|task:image grounding|>": 151691,
+  "<|task:image orientation|>": 151692,
+  "<|task:image zh-captioning|>": 151684,
+  "<|task:image zh-concept|>": 151690,
+  "<|task:image zh-dense-captioning|>": 151688,
+  "<|task:object detection|>": 151685,
+  "<|task:ocr of chart with format matplotlib|>": 151697,
+  "<|task:ocr of chart with format mermaid|>": 151698,
+  "<|task:ocr of molecule with format molgrapher|>": 151695,
+  "<|task:ocr of staff with format ekern|>": 151696,
+  "<|task:ocr with format html|>": 151705,
+  "<|task:ocr with format image captioning|>": 151703,
+  "<|task:ocr with format json|>": 151694,
+  "<|task:ocr with format latex|>": 151693,
+  "<|task:ocr with nodes,lines and circle|>": 151704,
+  "<|task:ocr-detection and recognition|>": 151699,
+  "<|task:ocr|>": 151686,
+  "<|task:table captioning|>": 151702,
+  "<|task:video captioning|>": 151706,
+  "<|text|>": 151675,
+  "<|to_think|>": 151714,
+  "<|url|>": 151707,
+  "<|userprompt|>": 151646,
+  "<|user|>": 151665,
+  "<|video_pad|>": 151680,
+  "[SEP]": 151673,
+  "<think>": 151721,
+  "</think>": 151722,
+  "<no_think>": 151723,
+  "<dots_function_call>": 151724,
+  "</dots_function_call>": 151725,
+  "<dots_function_response>": 151726,
+  "</dots_function_response>": 151727
+}

chat_template.jinja

@@ -0,0 +1,144 @@
+{%- if enable_thinking is not defined -%}
+    {%- set enable_thinking = true -%}
+{%- endif -%}
+{%- if clear_thinking is not defined -%}
+    {%- set clear_thinking = false -%}
+{%- endif -%}
+
+{%- set image_count = namespace(value=0) -%}
+{%- set audio_count = namespace(value=0) -%}
+{%- set video_count = namespace(value=0) -%}
+{%- set last_user_index = namespace(value=-1) -%}
+
+{%- macro render_content(content) -%}
+    {%- if not content -%}
+        {{- '' -}}
+    {%- elif content is string -%}
+        {{- content -}}
+    {%- else -%}
+        {%- for item in content -%}
+            {%- if item['type'] == 'image' or 'image' in item or 'image_url' in item -%}
+                {%- set image_count.value = image_count.value + 1 -%}
+                {%- if not loop.first -%}{{- '\n' -}}{%- endif -%}
+                {%- if add_vision_id -%}Picture {{ image_count.value }}: {% endif -%}
+                <|img|><|imgpad|><|endofimg|>
+            {%- elif item['type'] == 'video' or 'video' in item or 'video_url' in item -%}
+                {%- set video_count.value = video_count.value + 1 -%}
+                {%- if not loop.first -%}{{- '\n' -}}{%- endif -%}
+                {%- if add_vision_id -%}Video {{ video_count.value }}: {% endif -%}
+                <|video_pad|>
+            {%- elif item['type'] == 'audio' or 'audio' in item or 'audio_url' in item -%}
+                {%- set audio_count.value = audio_count.value + 1 -%}
+                {%- if not loop.first -%}{{- '\n' -}}{%- endif -%}
+                {%- if add_vision_id -%}Audio {{ audio_count.value }}: {% endif -%}
+                <|audio_comp_start|><|audio_comp_pad|><|audio_comp_end|>
+            {%- elif 'text' in item -%}
+                {{- item['text'] -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- if tools -%}
+    {{- '<|system|>' -}}
+    {%- if messages[0]['role'] == 'system' -%}
+        {{- render_content(messages[0]['content']) -}}
+    {%- else -%}
+        {{- 'You are a helpful assistant.' -}}
+    {%- endif -%}
+    {{- "\n\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>" -}}
+    {%- for tool in tools -%}
+        {{- "\n" -}}
+        {{- tool | tojson -}}
+    {%- endfor -%}
+    {{- "\n</tools>\n\nWhen making tool calls, use XML format to invoke tools and pass parameters:\n\n<dots_function_call>\n<invoke name=\"tool-name-1\">\n<parameter name=\"param-key-1\">\nparam-value-1\n</parameter>\n<parameter name=\"param-key-2\">\nparam-value-2\n</parameter>\n...\n</invoke>\n</dots_function_call><|endofsystem|>" -}}
+{%- else -%}
+    {%- if messages[0]['role'] == 'system' -%}
+        {{- '<|system|>' -}}
+        {{- render_content(messages[0]['content']) -}}
+        {{- '<|endofsystem|>' -}}
+    {%- else -%}
+        {{- '<|system|>You are a helpful assistant.<|endofsystem|>' -}}
+    {%- endif -%}
+{%- endif -%}
+
+{%- for m in messages -%}
+    {%- if m['role'] == 'user' -%}
+        {%- set last_user_index.value = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- for message in messages -%}
+    {%- set content = render_content(message['content']) -%}
+    {%- if (message['role'] == 'user') or (message['role'] == 'system' and not loop.first) -%}
+        {{- '<|user|>' -}}
+        {{- content -}}
+        {%- if message['role'] == 'user' and enable_thinking is false and not content.endswith('<no_think>') -%}
+            {{- '<no_think>' -}}
+        {%- endif -%}
+        {{- '<|endofuser|>' -}}
+    {%- elif message['role'] == 'assistant' -%}
+        {%- set reasoning_content = '' -%}
+        {%- if message.reasoning_content is string -%}
+            {%- set reasoning_content = message.reasoning_content -%}
+        {%- else -%}
+            {%- if '</think>' in content -%}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') -%}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') -%}
+            {%- endif -%}
+        {%- endif -%}
+        {%- set reasoning_content = reasoning_content|trim -%}
+        {{- '<|assistant|>' -}}
+        {%- if enable_thinking is false -%}
+            {{- '<think>\n\n</think>\n\n' + content -}}
+        {%- elif clear_thinking and loop.index0 < last_user_index.value -%}
+            {{- '<think>\n\n</think>\n\n' + content -}}
+        {%- elif reasoning_content -%}
+            {{- '<think>\n' + reasoning_content + '\n</think>\n\n' + content -}}
+        {%- else -%}
+            {{- content -}}
+        {%- endif -%}
+        {%- if message.get('tool_calls') -%}
+            {%- for tool_call in message['tool_calls'] -%}
+                {%- if tool_call.function is defined -%}
+                    {%- set tool_call = tool_call.function -%}
+                {%- endif -%}
+                {{- '\n<dots_function_call>\n<invoke name="' -}}
+                {{- tool_call.name -}}
+                {{- '">' -}}
+                {%- for arg_name, arg_value in tool_call.arguments.items() -%}
+                    {{- '\n<parameter name="' -}}
+                    {{- arg_name -}}
+                    {{- '">' -}}
+                    {{- '\n' -}}
+                    {%- if arg_value is string -%}
+                        {{- arg_value -}}
+                    {%- else -%}
+                        {{- arg_value|tojson -}}
+                    {%- endif -%}
+                    {{- '\n' -}}
+                    {{- '</parameter>' -}}
+                {%- endfor -%}
+                {{- '\n</invoke>\n</dots_function_call>' -}}
+            {%- endfor -%}
+        {%- endif -%}
+        {{- '<|endofassistant|>' -}}
+    {%- elif message['role'] == 'tool' -%}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1]['role'] != 'tool') -%}
+            {{- '<|user|>' -}}
+        {%- endif -%}
+        {{- '\n<dots_function_response>\n' -}}
+        {{- content -}}
+        {{- '\n</dots_function_response>' -}}
+        {%- if loop.last or (messages[loop.index0 + 1]['role'] != 'tool') -%}
+            {{- '<|endofuser|>' -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {{- '<|assistant|>' -}}
+    {%- if enable_thinking is false -%}
+        {{- '<think>\n\n</think>\n\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,209 @@
+{
+  "architectures": [
+    "Dots3NoteForCausalLM"
+  ],
+  "apply_mla_qkv_lora_rescale": true,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_gate_type": "headwise",
+  "bos_token_id": 151643,
+  "eos_token_id": 151668,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "index_head_dim": 128,
+  "index_n_heads": 64,
+  "index_topk": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "kv_lora_rank": 512,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 524288,
+  "model_type": "dots3_note",
+  "moe_intermediate_size": 1536,
+  "moe_layer_freq": 1,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 128,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1024,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 80000000.0,
+  "routed_scaling_factor": 1.0,
+  "scoring_func": "sigmoid",
+  "sliding_window_size": 513,
+  "swa_attention_gate_type": "headwise",
+  "swa_kv_lora_rank": 1024,
+  "swa_num_attention_heads": 64,
+  "swa_num_key_value_heads": 64,
+  "swa_q_lora_rank": 1024,
+  "swa_qk_nope_head_dim": 192,
+  "swa_qk_rope_head_dim": 64,
+  "swa_rope_theta": 50000.0,
+  "swa_v_head_dim": 128,
+  "tie_word_embeddings": false,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 152064,
+  "vision_config": {
+    "embed_dim": 1536,
+    "hidden_size": 5120,
+    "intermediate_size": 4224,
+    "moe_intermediate_size": 2112,
+    "num_hidden_layers": 42,
+    "num_attention_heads": 24,
+    "num_channels": 3,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 1,
+    "rms_norm_eps": 1e-05,
+    "use_bias": false,
+    "use_qk_norm": true,
+    "attn_implementation": "flash_attention_3",
+    "initializer_range": 0.02,
+    "is_causal": false,
+    "post_norm": true,
+    "pre_pixel_shuffle": true,
+    "pyramid_num_routed": [
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      -1,
+      4,
+      8,
+      12,
+      16,
+      20,
+      24,
+      28,
+      32,
+      36,
+      40,
+      44,
+      48,
+      52,
+      56,
+      60,
+      64,
+      64
+    ],
+    "capacity_factor": 2,
+    "router_scoring_func": "sigmoid",
+    "router_scale": 1.0,
+    "adapter_type": "patch_merger",
+    "adapter_in_dim": 1536,
+    "adapter_out_dim": 5120,
+    "adapter_merge_size": 2
+  },
+  "audio_config": {
+    "encoder_type": "dots",
+    "whisper_config": {
+      "d_model": 1280,
+      "encoder_attention_heads": 20,
+      "encoder_ffn_dim": 5120,
+      "encoder_layers": 32,
+      "num_mel_bins": 128,
+      "max_source_positions": 6000,
+      "activation_function": "swiglu"
+    },
+    "use_conv2d_stem": true,
+    "use_rope": true,
+    "use_rms_norm": true,
+    "use_causal": false,
+    "downsample_hidden_size": 480,
+    "conv_chunksize": 500,
+    "conv_stem_gradient_checkpointing": true,
+    "conv_bucket_step": 10,
+    "conv_bucket_max_elements": 20000,
+    "rope_parameters": {
+      "partial_rotary_factor": 0.5,
+      "rope_theta": 10000.0
+    },
+    "merge_factor": 1,
+    "chunk_seconds": 60,
+    "whisper_adapter_in_dim": 1280,
+    "whisper_adapter_out_dim": 5120,
+    "sampling_rate": 16000,
+    "audio_comp_start": "<|audio_comp_start|>",
+    "audio_comp_span": "<|audio_comp_pad|>",
+    "audio_comp_end": "<|audio_comp_end|>"
+  }
+}

generation_config.json

@@ -0,0 +1,3 @@
+{
+  "eos_token_id": [151643, 151668]
+}

model-00001-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a36e362e81b9098dacf446f0d8b935b5334aeea115f2e64e4d68a05c9cedfc4
+size 4293953752

model-00002-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc71944d3df6fbac4f81fa9240de3a79931b121e8371975d7ea7a41c0f4737a2
+size 4288708792

model-00003-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ecd0e31e75ef8e20f75de95f66d2ba0baf1bc167d3164ea3d53e816f2ba203
+size 4283464768

model-00004-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef137e2b3968f5176be6d43eed5a56595df9fd3bfa23181261fa3bb802cf62f
+size 4293951256

model-00005-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a5c2a65a18a21b96b44abb68192e62cbb57d33278d22f6b3bceb717dd51f0e
+size 4290806048

model-00006-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315bf17f5fe8b324e74babcfce0e8a916dbd84a433b7ce108c52b1cff1231846
+size 4293952288

model-00007-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828e6c8429968135a7ee584c4598998a2fc2a0349a0b7fbefdadd7fb6a2e6593
+size 4293952272

model-00008-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4d0556d81c94fa3ec48f73a8b557ed6363802d71c0e659f881f01cae9dc743
+size 4279927712

model-00009-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97cca3004dcb95e0f35201c5fe7631599670ceb6a2ec68a7521cb9d7918377d2
+size 4284515208

model-00010-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af032403973ac963beb7762aca5aff7567b330e0bf0e1763226bb6ff336ff1d0
+size 4281239136

model-00011-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bbc13a782f9192561503f3224b1a20f7716c7928f91dbc432fb3011e7d66ebc
+size 4288972024

model-00012-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ecc94aae23704fc9d7d49be572b4245c19044dddae95ca67f6f3e964f7187f
+size 4294608520

model-00013-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e268cd2e7e5f58a23fd23fed692bc26512aefc61bfe6abfaf99d98064becab
+size 4289758704

model-00014-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:803403d72995ddcb6c930981364553659e6538b2ce02952daddcc01535b469da
+size 4288710080

model-00015-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c57e59147cfa8d86a3d787bdd35d80aa98dd31b8bd535f0e4ee199efb4144a
+size 4290020944

model-00016-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82795d86ac1f0779b2c8a6685f0b1e543b1e0edf676c79417d178228af146232
+size 4282812328

model-00017-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa652e918a342b3c56931c9746622cc64ccd2c86391f102da8611bf9bee1e31d
+size 4280846504

model-00018-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d356ef291d51b0b5e27bf1d02360b89ab3cf46fd53f44661ba62bbe47c7df9f
+size 4283488768

model-00019-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9703d86bf8ba7887bf85209766a22916555774de3890f90e2ed761e231853e37
+size 4289469016

model-00020-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ddc124b579f0e9819c1ecca9c03051326a9e78c475ab0ffd233dc73179b319
+size 4294007416

model-00021-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80911353e7cf208d167e31d7bacb9301b341ba2487a2ba781e75bd0edfa72c81
+size 4293972616

model-00022-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f535d4ae795faf3bc59773285794fcbf48a08670ee164199bfc650370bd5cf7
+size 4288719544

model-00023-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c35cbdcc1b02ef936ff564130124eb4fdd8623a844da6cff9dd90c56fc2f20
+size 4293956176

model-00024-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1605b657a1744f5ab243626529d6044a3e47657906155641f74650d69e4008
+size 4290807120

model-00025-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89787c5d9fd2234d674fb2036615c5c64b78b38f1ddd1821ce28d4c6d1a3bec8
+size 4288708840

model-00026-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8387cd2f96053303bf7a8d1f90507cc2b3d4b90282676c07c322215f228a5d89
+size 4288707776

model-00027-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e777b72a304c5096ae978b1a14ff5b49f04c5b79abf2efb99d917a37a96b01a
+size 4293952472

model-00028-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5d2a1efadf0bdb34fa6440f13806faecfbea7ed6c6177bc391e5849cea7aa2
+size 4288708384

model-00029-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb4de92fee1c0fb8b479d8e8c16119388b50b5a2373fafc918498e922d5baf4
+size 4284515136

model-00030-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd29b3d64eb4778b94648dd8c86fd5caabf4759a2cf3a546df95cc1286087958
+size 4288709456

model-00031-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf907a2cd1e0d2f64a94353fdb2ab0e22d3ccc65c732a06d5d619c286f1e6b58
+size 4293952320

model-00032-of-00131.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725f643a1a27c417b052d29156a855b66d60b32ed742a7f552db635f9c1a539c
+size 4284515296