初始化项目，由ModelHub XC社区提供模型

Model: OpenOneRec/OneRec-1.7B-pro
Source: Original Platform

.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
+assets/framework.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/benchmark.png filter=lfs diff=lfs merge=lfs -text
+assets/onerec.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 2026 OneRec Team
+
+   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 +1,206 @@
+---
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/OpenOneRec/OneRec-8B/blob/main/LICENSE
+---
+
+<div align="center">
+  <h1>OpenOneRec</h1>
+  <p align="center">
+    <strong>An Open Foundation Model and Benchmark to Accelerate Generative Recommendation</strong>
+  </p>
+  <p align="center">
+    <a href="https://huggingface.co/OpenOneRec">
+        <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-OneRec-ffc107?color=ffc107&logoColor=white" />
+    </a>
+    <a href="https://github.com/Kuaishou-OneRec/OpenOneRec">
+        <img alt="GitHub Code" src="https://img.shields.io/badge/GitHub-OpenOneRec-black?logo=github" />
+    </a>
+     <a href="https://arxiv.org/pdf/2512.24762">
+        <img alt="Paper" src="https://img.shields.io/badge/Paper-ArXiv-b31b1b?logo=arxiv" />
+    </a>
+    <a href="#license">
+        <img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-green" />
+    </a>
+  </p>
+</div>
+<br>
+
+## 📖 Introduction
+
+**OpenOneRec** is an open-source framework designed to bridge the gap between traditional recommendation systems and Large Language Models (LLMs). While Generative Recommendation has shown promise, existing models often struggle with isolated data silos and a lack of reasoning capabilities.
+
+To address this, we introduce a unified framework that comprises:
+* **RecIF-Bench**: The first holistic Recommendation Instruction-Following Benchmark, containing **100M interactions** from 200k users across heterogeneous domains (Short Video, Ads, Product).
+* **OneRec-Foundation Models**: A family of models (1.7B & 8B) built on the Qwen3 backbone. The series includes **Standard** versions trained on our open-source dataset and **Pro** versions enhanced with a hundred-billion-token industrial corpus from Kuaishou.
+* **Full-Stack Pipeline**: We open-source our comprehensive training pipeline, including data processing, co-pretraining, and post-training, to ensure full reproducibility and facilitate scaling law research in recommendation.
+
+## 🔥 News
+
+* **[2026.1.1]** 📑 The technical report has been released.
+* **[2026.1.1]** 🎉 **OneRec-Foundation** models (1.7B, 8B) are now available on Hugging Face!
+* **[2026.1.1]** 🚀 **RecIF-Bench** dataset and evaluation scripts are open-sourced.
+* **[2026.1.5]** 🔡 **OneRec-Tokenizer** is open-sourced to support SID generation for new domains.
+
+## 📊 RecIF-Bench
+
+We propose **RecIF-Bench** to rigorously assess the synergy between instruction following and domain-specific recommendation. It organizes 8 distinct tasks into a four-layer capability hierarchy:
+
+* **Layer 0: Semantic Alignment** (Item Understanding) 
+* **Layer 1: Fundamental Prediction** (Short Video Rec, Ad Rec, Product Rec, Label Prediction) 
+* **Layer 2: Instruction Following** (Interactive Rec, Label-Conditional Rec) 
+* **Layer 3: Reasoning** (Recommendation Explanation) 
+
+The benchmark aggregates data from three domains: **Short Video** (Content), **Ads** (Commercial), and **Product** (E-commerce).
+
+## 🤖 Model Zoo
+
+The OpenOneRec-Foundation series is built upon the Qwen architecture, enhanced with **Itemic Tokens** for modality alignment and trained via a multi-stage protocol.
+
+| Model | Backbone | Parameters | Description | Link |
+| :--- | :--- | :--- | :--- | :--- |
+| **OneRec-1.7B** | Qwen3-1.7B | 1.7B | Standard version trained on open-source data (~33B tokens) | [HuggingFace](https://huggingface.co/OpenOneRec/OneRec-1.7B) |
+| **OneRec-8B** | Qwen3-8B | 8B | Standard version trained on open-source data (~33B tokens) | [HuggingFace](https://huggingface.co/OpenOneRec/OneRec-8B) |
+| **OneRec-1.7B-Pro** | Qwen3-1.7B | 1.7B | Scaled-up version with expanded datasets (~130B tokens) | [HuggingFace](https://huggingface.co/OpenOneRec/OneRec-1.7B-pro) |
+| **OneRec-8B-Pro** | Qwen3-8B | 8B | Scaled-up version with expanded datasets (~130B tokens) | [HuggingFace](https://huggingface.co/OpenOneRec/OneRec-8B-pro) |
+
+## 🏗️ Method & Architecture
+
+OpenOneRec reframes recommendation as a general-purpose sequence modeling paradigm.
+
+### 1. Items as Tokens
+To bridge the modality gap, we treat items as a distinct modality using **Itemic Tokens** derived from hierarchical vector quantization. This allows the LLM to process interaction history as a cohesive context sequence.
+
+### 2. Training Pipeline
+Our framework utilizes the following recipe:
+* **Pre-Training**: Integrates collaborative signals via Itemic-Text Alignment and Full-Parameter Co-Pretraining.
+* **Post-Training**:
+    * *Stage 1*: Multi-task Supervised Fine-tuning for basic instruction following.
+    * *Stage 2*: On-policy Distillation to restore general reasoning performance.
+    * *Stage 3*: Reinforcement Learning to enhance recommendation capabilities.
+
+<div align="center">
+  <img src="assets/framework.png" width="80%" alt="OpenOneRec Overall Framework" />
+  <br>
+  <em>Figure: The Overall Framework of OpenOneRec.</em>
+</div>
+
+## 📈 Performance
+
+### Results on RecIF-Bench
+OpenOneRec-Foundation achieves **State-of-the-Art (SOTA)** results across RecIF-Bench tasks, significantly outperforming baselines like LC-Rec and TIGER.
+
+| Task | Metric | SASRec | TIGER | LC-Rec | OneRec-1.7B | OneRec-8B | OneRec-1.7B-Pro | **OneRec-8B-Pro** |
+| :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- |
+| **Short Video Rec** | Recall@32 | 0.0119 | 0.0132 | 0.0180 | 0.0272 | 0.0355 | 0.0274 | **0.0369** |
+| **Ad Rec** | Recall@32 | 0.0293 | 0.0581 | 0.0723 | 0.0707 | 0.0877 | 0.0735 | **0.0964** |
+| **Product Rec** | Recall@32 | 0.0175 | 0.0283 | 0.0416 | 0.0360 | 0.0470 | 0.0405 | **0.0538** |
+| **Label-Cond. Rec** | Recall@32 | 0.0140 | 0.0123 | 0.0170 | 0.0184 | 0.0228 | 0.0182 | **0.0235** |
+| **Label Pred.** | AUC | 0.6244 | 0.6675 | 0.6139 | 0.6184 | 0.6615 | 0.6071 | **0.6912** |
+| **Interactive Rec** | Recall@32 | -- | -- | 0.2394 | 0.1941 | 0.3032 | 0.2024 | **0.3458** |
+| **Item Und.** | LLM Score | -- | -- | 0.2517 | 0.3175 | 0.3202 | 0.3133 | **0.3209** |
+| **Rec. Explanation** | LLM Score | -- | -- | 3.9350 | 3.3540 | 3.6774 | 3.5060 | **4.0381** |
+
+<div align="center">
+  <img src="assets/benchmark.png" width="80%" alt="Holistic Performance Overview of OpenOneRec." />
+  <br>
+  <em>Holistic Performance Overview of OpenOneRec.</em>
+</div>
+
+### Cross-Domain Transferability
+On the **Amazon Benchmark** (10 datasets), OpenOneRec demonstrates exceptional zero-shot/few-shot transfer capabilities, achieving an average **26.8% improvement** in Recall@10 over the second-best method.
+
+| Domain | SASRec | TIGER | LC-Rec | **Ours** |
+| :--- | :--- | :--- | :--- | :--- |
+| Baby | 0.0381 | 0.0318 | 0.0344 | **0.0513** |
+| Beauty | 0.0639 | 0.0628 | 0.0764 | **0.0924** |
+| Cell Phones | 0.0782 | 0.0786 | 0.0883 | **0.1036** |
+| Grocery | 0.0789 | 0.0691 | 0.0790 | **0.1029** |
+| Health | 0.0506 | 0.0534 | 0.0616 | **0.0768** |
+| Home | 0.0212 | 0.0216 | 0.0293 | **0.0390** |
+| Pet Supplies | 0.0607 | 0.0542 | 0.0612 | **0.0834** |
+| Sports | 0.0389 | 0.0331 | 0.0418 | **0.0547** |
+| Tools | 0.0437 | 0.0344 | 0.0438 | **0.0593** |
+| Toys | 0.0658 | 0.0527 | 0.0549 | **0.0953** |
+
+*Metric: Recall@10. Ours refers to OneRec-Foundation with text-augmented itemic tokens strategy.*
+
+## 🚀 Quick Start
+
+*Code release and detailed usage instructions are coming soon.*
+
+Currently, you can load our models using `transformers>=4.51.0`:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "OpenOneRec/OneRec-8B"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+# case - prompt with itemic tokens
+prompt = "这是一个视频：<|sid_begin|><s_a_340><s_b_6566><s_c_5603><|sid_end|>，帮我总结一下这个视频讲述了什么内容"
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+# Note: In our experience, default decoding settings may be unstable for small models.
+# For 1.7B, we suggest: top_p=0.95, top_k=20, temperature=0.75 (during 0.6 to 0.8)
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+# parsing thinking content
+try:
+    # rindex finding 151668 (</think>)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+
+print("thinking content:", thinking_content)
+print("content:", content)
+```
+
+## 📜 Citation
+If you find our work helpful, please cite our technical report:
+
+```bibtex
+@article{openonerec2025,
+  title={An Open Foundation Model and Benchmark to Accelerate Generative Recommendation},
+  author={OneRec Team},
+  journal={arXiv preprint},
+  year={2025}
+}
+```
+## 🛡️ License
+The code in this repository is licensed under the Apache 2.0 License. The model weights are subject to their specific license agreements.
+
+## 🙏 Acknowledgements
+
+OpenOneRec is built upon and inspired by the open-source ecosystem. We would like to thank:
+
+- **Qwen3**: for providing the base architecture and model initialization that OpenOneRec builds upon.
+- **General-domain data sources**: for the public corpora referenced in [`data/general_text`](https://github.com/Kuaishou-OneRec/OpenOneRec/tree/main/data/general_text) used for mixed-domain training.
+- **VeRL & PyTorch distributed training**: for the training infrastructure and scalable primitives (e.g., **FSDP**) used in post-training and large-scale runs.
+
+We sincerely thank these projects for their outstanding work.

assets/benchmark.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d37d8deb51486c75745cbbc1223cc3a90c0c0a1ce29e450aeb06babccbf29018
+size 516381

assets/framework.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428b5244d4e0d8049c2e7991995b525772334dafb9e7187f9442969b8a8b858b
+size 572024

assets/onerec.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c70fd0d371127c78dbbdf52a81b991bcd890bb181fb09acdbf15da8db5fc3a5
+size 173199

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "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": "4.53.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 176384
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.53.0"
+}

model-00000-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e1711ee090fb25c11abb6b0467f5c95de8170992b4b21b72b2091fa4e8a0e9d
+size 4263793656

model.safetensors.index.json

@@ -0,0 +1,318 @@
+{
+  "metadata": {
+    "total_size": 4263757824
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.norm.weight": "model-00000-of-00001.safetensors",
+    "lm_head.weight": "model-00000-of-00001.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccf4231869d9f8755b55133c211b48521a298a86cddf8b59ba9fe0481ecd9ba
+size 16015414