Hugging Face's logo

Godcat252
/
Besttop361

Text Generation
Transformers
Safetensors
deepseek_v3
conversational
text-generation-inference
Model card Files
xet
 Community
Godcat252 commited on
Commit
d0625e7
·
verified ·
1 Parent(s): e144a4c

Thank you first commit

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. LICENSE +73 -0
  3. README.md +692 -0
  4. assets/logo/kanana.png +3 -0
  5. chat_template.jinja +112 -0
  6. config.json +48 -0
  7. generation_config.json +7 -0
  8. model-00001-of-00013.safetensors +3 -0
  9. model-00002-of-00013.safetensors +3 -0
  10. model-00003-of-00013.safetensors +3 -0
  11. model-00004-of-00013.safetensors +3 -0
  12. model-00005-of-00013.safetensors +3 -0
  13. model-00006-of-00013.safetensors +3 -0
  14. model-00007-of-00013.safetensors +3 -0
  15. model-00008-of-00013.safetensors +3 -0
  16. model-00009-of-00013.safetensors +3 -0
  17. model-00010-of-00013.safetensors +3 -0
  18. model-00011-of-00013.safetensors +3 -0
  19. model-00012-of-00013.safetensors +3 -0
  20. model-00013-of-00013.safetensors +3 -0
  21. model.safetensors.index.json +0 -0
  22. tokenizer.json +0 -0
  23. tokenizer_config.json +2063 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ assets/logo/kanana.png filter=lfs diff=lfs merge=lfs -text
LICENSE ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ KANANA LICENSE AGREEMENT
2
+
3
+ Kanana Release Date: July 17, 2025
4
+
5
+ This KANANA LICENSE AGREEMENT (this “Agreement”) is made by and between you and Kakao Corp. (“KAKAO”) that governs your use of Kanana Materials that KAKAO provides to you.
6
+ By using, copying, modifying, distributing, performing, or displaying all or part of Kanana Materials, or otherwise accepting the terms and conditions of this Agreement, you agree to be bound by this Agreement. You hereby represent and warrant that (i) you are legally authorized to enter into this Agreement, and (ii) if you are entering into this Agreement on behalf of a legal entity, you have the authority to legally and validly bind such entity.
7
+
8
+ 1. Definition
9
+ 1.1 “Agreement” means the terms and conditions for use, copying, distribution and modification of Kanana Materials as set forth herein.
10
+ 1.2 “KAKAO” means Kakao Corp.
11
+ 1.3 “You” means an individual or legal entity that enters into this Agreement with KAKAO and exercises its rights hereunder or uses Kanana Materials for any purpose. If you enter into this Agreement on behalf of a legal entity, “you” shall include such entity.
12
+ 1.4 “Kanana” means the basic large-scale language model, software, and algorithms distributed by KAKAO under this Agreement, including parameters (such as Model Weights and optimizer status), machine learning model codes, inference/learning/fine-tuning codes, and other related elements.
13
+ 1.5 “Documentation” means the specifications, manuals, and other documentation accompanying Kanana distributed by KAKAO.
14
+ 1.6 “Kanana Materials” means, collectively, Kanana and Documentation, including any portions or components thereof.
15
+ 1.7 “Outputs” means information content generated by operating or otherwise using Kanana Materials.
16
+ 1.8 “Derivative Works” means (i) any modifications to Kanana, (ii) any work of authorship based on Kanana, or (iii) any other designed machine learning models that either directly use the patterns of Model Weights, parameters, operations, and/or outputs or incorporate a substantial part of Kanana’s performance or functional characteristics through methods including, but not limited to, transfer learning, fine-tuning, or knowledge distillation. This includes distillation methods using Kanana’s intermediate data representations or a method based on the synthetic data outputs generated by Kanana; provided, however, that Outputs shall not be deemed to be Derivative Works.
17
+ 1.9 “Model Weights” means a set of numerical parameter values generated during Kanana’s learning process, representing the result of substantial investment and effort by KAKAO.
18
+
19
+ 2. Grant of License and Use Policy
20
+ 2.1 Grant of License. Subject to the terms and conditions of this Agreement, you are granted a non-exclusive, worldwide, non-transferrable, royalty-free limited license under KAKAO’s intellectual property or other rights owned by KAKAO that enables you to access, download, install, copy, use, reproduce, distribute, create Derivative Works of, and make modifications to Kanana Materials.
21
+ 2.2 Policy on Prohibited Use. Your use of Kanana Materials and Derivative Works must comply with applicable laws and regulations and adhere to KAKAO’s Guidelines For Responsible AI (https://www.kakaocorp.com/page/responsible/detail/guidelinesForResponsibleAI), which is hereby incorporated into this Agreement.
22
+ 2.3 This Agreement applies solely to Kanana-*** and shall not apply to any other models distributed by KAKAO under separate licenses. Licenses applicable to such other models shall not apply to Kanana-***.
23
+ 2.4 The license terms applicable to a specific version of Kanana applies exclusively to that version and shall not extend to any other versions. Each version shall be deemed as an independent and separate work of authorship.
24
+ 2.5 You may use each version of Kanana only in accordance with the license terms expressly specified for that version, and you shall not claim that the license terms applicable to one version apply to any other version.
25
+ 2.6 You shall not combine different versions of Kanana versions that are subject to different license terms in order to circumvent any applicable license terms.
26
+
27
+ 3. Redistribution
28
+ 3.1 You may copy, distribute or disclose Kanana, Derivative Works, or any products or services that contain Kanana or Derivative Works; provided, however, that you shall:
29
+ (i) incorporate the compliance obligation set forth in the Policy on Prohibited Use provision of Section 2.2 in any agreement for use and distribution and notify subsequent users that such use restrictions apply;
30
+ (ii) provide any recipients of Kanana Materials or Derivative Works a copy of this Agreement;
31
+ (iii) expressly indicate in any files you have modified that it has been modified by you;
32
+ (iv) include a “Notice” text file that includes the following notice:
33
+ “Kanana is licensed in accordance with the Kanana License Agreement. Copyright © KAKAO Corp. All Rights Reserved.”; and
34
+ (v) clearly display the phrase “Powered by Kanana” on related websites, user interfaces, blog posts, introduction pages, or product documentation in a manner that is easily recognizable to users. In addition, if you use Kanana Materials or their outputs to create, train, improve, or enhance other AI models and distribute them, you must include ‘Kanana’ as a prefix to the name of such AI models.
35
+ 3.2 You may add your own copyright statement to your modifications of Kanana Materials and may provide additional or different license terms and conditions; provided, however, that such additional or different license terms and conditions shall not violate or conflict with any provisions of this Agreement.
36
+
37
+ 4. Additional Commercial Terms
38
+ 4.1 If you wish to engage in any of the following activities using Kanana Materials or any Derivative Works, you must obtain a separate commercial license expressly granted by KAKAO:
39
+ (i) Offering or (re)selling to third parties access to Kanana Materials or any Derivative Works through API, cloud platforms, or other remote access services;
40
+ (ii) Offering or (re)selling to third parties Kanana Materials or any Derivative Works in whole or in part, as part of a system integration (SI) or on-premise deployment solution; or
41
+ (iii) Offering or (re)selling to third parties Kanana Materials or any Derivative Works embedded in an on-device domains.
42
+ 4.2 If, as of Kanana Release Date, the number of monthly active users of the products or services provided by you and/or your affiliates, is greater than 10 million in the preceding calendar month, you must obtain a separate commercial license expressly granted by KAKAO.
43
+ 4.3 For clarity, unless your activities or conditions fall within those specified in Sections 4.1 and 4.2 above, you may use Kanana Materials or any Derivative Works for the development and operation of your own services without obtaining a commercial license from KAKAO.
44
+ 4.4 The grant of any commercial license under Sections 4.1 and 4.2 shall be at KAKAO’s sole discretion
45
+
46
+ 5. Outputs
47
+ KAKAO will not claim any rights to Outputs you generate using Kanana Materials. You shall be solely responsible for Outputs and the use thereof.
48
+
49
+ 6. Disclaimer of Warranty
50
+ Unless required by law, Kanana Materials are provided on an “AS IS” basis, and KAKAO disclaims all warranties of any kind, both express and implied, including, without limitation, any warranties of title, non-infringement, merchantability, or fitness for a particular purpose.
51
+
52
+ 7. Limitation on Liability
53
+ Unless required by law, in no event shall KAKAO be liable to you for damages, including any direct, indirect, special, consequential, incidental, and punitive damages of any character arising out of the use or inability to use Kanana Materials, Derivative Works, or Outputs, even if KAKAO has been advised of the possibility of such damages.
54
+
55
+ 8. Indemnification
56
+ You shall indemnify and hold KAKAO harmless from and against any and all claims that may be filed by a third party as a result of your infringement of any third party’s rights or violation of any applicable law, to the extent caused by your use or distribution of Kanana Materials, Derivative Works, or Outputs; provided, however, that the foregoing shall not apply to claims resulting from KAKAO’s willful or gross negligence.
57
+
58
+ 9. Intellectual Property
59
+ 9.1 This Agreement does not grant you any rights to use KAKAO’s trademarks, service marks, or product names. However, on a limited basis and solely for the purpose of complying with Section 3.1(v), KAKAO authorizes you to use the Kanana trademark, provided that KAKAO may require you to discontinue such use at any time if you impair the value of the Kanana trademark.
60
+ 9.2 KAKAO retains ownership of Kanana Materials and Derivative Works created by KAKAO, but you will retain ownership of any Derivative Works and modifications made by you.
61
+ 9.3 If you bring any legal action or proceeding against KAKAO or a third party alleging that the Kanana Materials, Derivative Works, or Outputs infringe your intellectual property rights, your rights under this Agreement shall automatically terminate as of the date such action is filed.
62
+ 9.4 You acknowledge that Model Weights are a valuable asset of KAKAO. You shall not extract, copy, distribute, modify Model Weights or use them to train new models, except as expressly permitted under this Agreement.
63
+ 9.5 The protections under this Agreement apply to all components of Kanana Materials (irrespective of whether it is recognized as a work of authorship), including, but not limited to, Model Weights, parameters, algorithms, or structures. You may exercise your rights in these components only to the extent expressly permitted under this Agreement.
64
+
65
+ 10. Term and Termination
66
+ The term of this Agreement will commence upon your acceptance of this Agreement or access to Kanana Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. KAKAO may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of Kanana Materials and Derivative Works. Sections 5, 6, 7, 8, 10 and 11 shall survive the termination of this Agreement.
67
+
68
+ 11. Governing Law and Arbitration
69
+ 11.1 This Agreement will be governed and construed under the laws of the Republic of Korea, without regard to its conflicts of laws principles.
70
+ 11.2 Any disputes arising out of or in connection with this Agreement shall be finally settled by arbitration in accordance with the International Arbitration Rules of the Korean Commercial Arbitration Board. The number of arbitrators shall be one. The seat, or legal place, of arbitral proceedings shall be Seoul, Republic of Korea. The language to be used in the arbitral proceedings shall be English. Either party may seek interim or provisional relief from a court of competent jurisdiction, which shall not be considered a waiver of any provision in this Section. The arbitral tribunal also has the authority to issue orders for interim or provisional relief.
71
+
72
+ 12. No Waiver
73
+ KAKAO’s failure or delay in exercising any of its rights under this Agreement shall not constitute a waiver of such rights.
README.md ADDED
@@ -0,0 +1,692 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license_name: "kanana"
4
+ license_link: LICENSE
5
+ pipeline_tag: text-generation
6
+ model_id: kakaocorp/kanana-2-30b-a3b-instruct-2601
7
+ repo: kakaocorp/kanana-2-30b-a3b-instruct-2601
8
+ developers: Kanana LLM
9
+ base_model:
10
+ - kakaocorp/kanana-2-30b-a3b-mid-2601
11
+ ---
12
+
13
+ <p align="center">
14
+ <img src="./assets/logo/kanana.png" width="60%" alt="Kanana">
15
+ </p>
16
+
17
+ <p align="center">
18
+ 🤗 <a href="https://huggingface.co/collections/kakaocorp/kanana-2">HF Models</a> &nbsp | &nbsp
19
+ 📕 <a href="https://tech.kakao.com/posts/807">Pre-Training Blog</a> &nbsp | &nbsp
20
+ 📕 <a href="https://tech.kakao.com/posts/808">Post-Training Blog</a> &nbsp | &nbsp
21
+ 📕 <a href="https://tech.kakao.com/posts/804">Teaser Blog</a> &nbsp
22
+ </p>
23
+ <br><br>
24
+
25
+ ## News 🔥
26
+
27
+ - `2026/01/15`: 🤗 Released `kanana-2-30b-a3b-2601` HF model weights.
28
+ - `2026/01/15`: 📕 Published blog posts ([pre-training](https://tech.kakao.com/posts/807), [post-training](https://tech.kakao.com/posts/808)) about the development of `Kanana-2` models.
29
+ - `2025/12/19`: 🤗 Released `kanana-2-30b-a3b` HF model weights and publised a [teaser blog](https://tech.kakao.com/posts/804).
30
+
31
+ <br>
32
+
33
+ # Kanana-2 Highlights
34
+
35
+ **Kanana-2**, the latest open-source evolution of the Kanana model family, is designed specifically for **Agentic AI**, presenting substantial enhancements in **tool calling, complex instruction following, and logical reasoning**. This new version adopts a cutting-edge architecture featuring MLA (Multi-head Latent Attention) and MoE (Mixture of Experts). These innovations allow the model to utilize significantly fewer active parameters compared to the previous 32.5B model while delivering superior performance and ensuring high throughput. Furthermore, the model **natively supports context lengths of up to 32,768 tokens**, enabling it to maintain coherence when handling extensive documents or long-context interactions.
36
+
37
+ In addition, Kanana-2 now supports 6 languages, covering **Korean, English, Japanese, Chinese, Thai, and Vietnamese**. To support this expansion, Kanana-2 utilizes a newly trained tokenizer that demonstrates superior tokenization efficiency across these languages, including an improvement of over 30% specifically for Korean. Finally, to address advanced problem-solving needs, Kanana-2 introduces **reasoning models** capable of deliberate thinking and reasoning, achieving significantly enhanced performance in downstream tasks, especially when tackling hard problems.
38
+
39
+ > [!NOTE]
40
+ > No Kakao user data was used for either pre-training or post-training.
41
+
42
+ <br>
43
+
44
+ ## Model Overview
45
+
46
+ **kanana-2-30b-a3b** series has the following features:
47
+ - Total Parameters: 30B
48
+ - Activated Parameters: 3B
49
+ - Number of Layers: 48
50
+ - Number of Dense Layers: 1
51
+ - Number of Experts: 128
52
+ - Number of Selected Experts: 6
53
+ - Number of Shared Experts: 2
54
+ - Attention Mechanism: MLA
55
+ - Vocabulary Size: 128256
56
+ - Context Length: 32,768
57
+
58
+ <br>
59
+
60
+ ## Model Downloads
61
+
62
+ <div align="left">
63
+
64
+ | **Model** | **Download** |
65
+ | :------------: | :------------: |
66
+ | kanana-2-30b-a3b-base-2601<sup>*</sup> | [🤗 HuggingFace](https://huggingface.co/kakaocorp/kanana-2-30b-a3b-base-2601) |
67
+ | kanana-2-30b-a3b-mid-2601<sup>*</sup> | [🤗 HuggingFace](https://huggingface.co/kakaocorp/kanana-2-30b-a3b-mid-2601) |
68
+ | kanana-2-30b-a3b-instruct-2601 | [🤗 HuggingFace](https://huggingface.co/kakaocorp/kanana-2-30b-a3b-instruct-2601) |
69
+ | kanana-2-30b-a3b-thinking-2601 | [🤗 HuggingFace](https://huggingface.co/kakaocorp/kanana-2-30b-a3b-thinking-2601) |
70
+
71
+ <sub>
72
+ <sup>*</sup> We are releasing the <code><small>kanana-2-30b-a3b-base-2601</small></code> (prior to mid-training) checkpoint to contribute to the research community.<br>
73
+ &nbsp&nbspNote: <code><small>kanana-2-30b-a3b-mid-2601</small></code> is identical to <a href="https://huggingface.co/kakaocorp/kanana-2-30b-a3b-base">kanana-2-30b-a3b-base</a>.
74
+ </sub>
75
+
76
+ </div>
77
+
78
+ <br>
79
+
80
+ ## Performance
81
+
82
+ ### Base model evaluation results
83
+
84
+
85
+ <table>
86
+ <thead>
87
+ <tr>
88
+ <th align="center">Benchmark</th>
89
+ <th align="center">Metric</th>
90
+ <th align="center">Shot</th>
91
+ <th align="center">kanana-2-30b-a3b-mid-2601</th>
92
+ <th align="center">kanana-2-30b-a3b-base-2601</th>
93
+ <th align="center">kanana-1.5-32.5b-base</th>
94
+ <th align="center">Qwen3-30B-A3B-Base<sup>*</sup></th>
95
+ </tr>
96
+ </thead>
97
+ <tbody>
98
+ <tr>
99
+ <td align="center" colspan="7">General Tasks</td>
100
+ </tr>
101
+ <tr>
102
+ <td align="center">MMLU</td>
103
+ <td align="center">acc</td>
104
+ <td align="center">5</td>
105
+ <td align="center">75.44</td>
106
+ <td align="center">74.83</td>
107
+ <td align="center">76.76</td>
108
+ <td align="center">81.14</td>
109
+ </tr>
110
+ <tr>
111
+ <td align="center">MMLU-Pro</td>
112
+ <td align="center">acc</td>
113
+ <td align="center">5</td>
114
+ <td align="center">56.14</td>
115
+ <td align="center">52.61</td>
116
+ <td align="center">52.40</td>
117
+ <td align="center">61.83</td>
118
+ </tr>
119
+ <tr>
120
+ <td align="center">BBH</td>
121
+ <td align="center">acc</td>
122
+ <td align="center">3</td>
123
+ <td align="center">79.76</td>
124
+ <td align="center">76.46</td>
125
+ <td align="center">81.54</td>
126
+ <td align="center">79.97</td>
127
+ </tr>
128
+ <tr>
129
+ <td align="center">SimpleQA<sup>†</sup></td>
130
+ <td align="center">acc</td>
131
+ <td align="center">5</td>
132
+ <td align="center">29.70</td>
133
+ <td align="center">29.13</td>
134
+ <td align="center">26.95</td>
135
+ <td align="center">26.47</td>
136
+ </tr>
137
+ <tr>
138
+ <td align="center" colspan="7">Mathematics Tasks</td>
139
+ </tr>
140
+ <tr>
141
+ <td align="center">MATH</td>
142
+ <td align="center">em</td>
143
+ <td align="center">4</td>
144
+ <td align="center">54.40</td>
145
+ <td align="center">48.86</td>
146
+ <td align="center">47.68</td>
147
+ <td align="center">62.58</td>
148
+ </tr>
149
+ <tr>
150
+ <td align="center">GSM8K</td>
151
+ <td align="center">em</td>
152
+ <td align="center">8</td>
153
+ <td align="center">82.71</td>
154
+ <td align="center">76.57</td>
155
+ <td align="center">85.14</td>
156
+ <td align="center">88.10</td>
157
+ </tr>
158
+ <tr>
159
+ <td align="center" colspan="7">Coding Tasks</td>
160
+ </tr>
161
+ <tr>
162
+ <td align="center">HumanEval</td>
163
+ <td align="center">pass@1</td>
164
+ <td align="center">0</td>
165
+ <td align="center">75.29</td>
166
+ <td align="center">71.34</td>
167
+ <td align="center">75.59</td>
168
+ <td align="center">53.32</td>
169
+ </tr>
170
+ <tr>
171
+ <td align="center">MBPP</td>
172
+ <td align="center">pass@1</td>
173
+ <td align="center">3</td>
174
+ <td align="center">62.39</td>
175
+ <td align="center">60.21</td>
176
+ <td align="center">65.96</td>
177
+ <td align="center">72.58</td>
178
+ </tr>
179
+ <tr>
180
+ <td align="center" colspan="7">Korean Tasks</td>
181
+ </tr>
182
+ <tr>
183
+ <td align="center">KMMLU</td>
184
+ <td align="center">acc</td>
185
+ <td align="center">5</td>
186
+ <td align="center">62.15</td>
187
+ <td align="center">61.98</td>
188
+ <td align="center">61.56</td>
189
+ <td align="center">62.25</td>
190
+ </tr>
191
+ <tr>
192
+ <td align="center">KoSimpleQA<sup>†</sup></td>
193
+ <td align="center">acc</td>
194
+ <td align="center">5</td>
195
+ <td align="center">49.70</td>
196
+ <td align="center">49.40</td>
197
+ <td align="center">45.70</td>
198
+ <td align="center">26.33</td>
199
+ </tr>
200
+ <tr>
201
+ <td align="center">HAE-RAE Bench (v1.0)</td>
202
+ <td align="center">acc</td>
203
+ <td align="center">5</td>
204
+ <td align="center">88.73</td>
205
+ <td align="center">88.91</td>
206
+ <td align="center">90.65</td>
207
+ <td align="center">72.04</td>
208
+ </tr>
209
+ <tr>
210
+ <td align="center">MATH-Ko<sup>‡</sup></td>
211
+ <td align="center">em</td>
212
+ <td align="center">4</td>
213
+ <td align="center">54.07</td>
214
+ <td align="center">45.58</td>
215
+ <td align="center">47.42</td>
216
+ <td align="center">58.20</td>
217
+ </tr>
218
+ <tr>
219
+ <td align="center">GSM8K-Ko<sup>‡</sup></td>
220
+ <td align="center">em</td>
221
+ <td align="center">8</td>
222
+ <td align="center">77.48</td>
223
+ <td align="center">70.43</td>
224
+ <td align="center">81.43</td>
225
+ <td align="center">88.10</td>
226
+ </tr>
227
+ <tr>
228
+ <td align="center">MBPP-Ko<sup>§</sup></td>
229
+ <td align="center">pass@1</td>
230
+ <td align="center">3</td>
231
+ <td align="center">61.55</td>
232
+ <td align="center">57.29</td>
233
+ <td align="center">65.41</td>
234
+ <td align="center">66.84</td>
235
+ </tr>
236
+ <tr>
237
+ <td align="center" colspan="7">Long Context Tasks</td>
238
+ </tr>
239
+ <tr>
240
+ <td align="center">RULER-4K</td>
241
+ <td align="center">acc</td>
242
+ <td align="center">0</td>
243
+ <td align="center">93.09</td>
244
+ <td align="center">92.49</td>
245
+ <td align="center">86.39</td>
246
+ <td align="center">94.32</td>
247
+ </tr>
248
+ <tr>
249
+ <td align="center">RULER-8K</td>
250
+ <td align="center">acc</td>
251
+ <td align="center">0</td>
252
+ <td align="center">92.29</td>
253
+ <td align="center">92.14</td>
254
+ <td align="center">90.16</td>
255
+ <td align="center">92.16</td>
256
+ </tr>
257
+ <tr>
258
+ <td align="center">RULER-16K</td>
259
+ <td align="center">acc</td>
260
+ <td align="center">0</td>
261
+ <td align="center">90.73</td>
262
+ <td align="center">90.01</td>
263
+ <td align="center">85.88</td>
264
+ <td align="center">91.28</td>
265
+ </tr>
266
+ <tr>
267
+ <td align="center">RULER-32K</td>
268
+ <td align="center">acc</td>
269
+ <td align="center">0</td>
270
+ <td align="center">88.63</td>
271
+ <td align="center">87.92</td>
272
+ <td align="center">81.62</td>
273
+ <td align="center">88.32</td>
274
+ </tr>
275
+ </tbody>
276
+ </table>
277
+
278
+ <sub>
279
+ <sup>*</sup> Evaluated using an internal evaluation toolkit.<br>
280
+ <sup>†</sup> Evaluated in Multiple Choice Question Answering (MCQA) format with 10 options.<br>
281
+ <sup>‡</sup> Subsets from <a href="https://huggingface.co/datasets/HAERAE-HUB/HRM8K">HRM8K</a> (MATH, GSM8K).<br>
282
+ <sup>§</sup> Internally translated to Korean.
283
+ </sub>
284
+
285
+ <br>
286
+
287
+ ### Instruct model evaluation results
288
+
289
+ <table>
290
+ <thead>
291
+ <tr>
292
+ <th align="center">Benchmark</th>
293
+ <th align="center">Metric</th>
294
+ <th align="center">kanana-2-30b-a3b-instruct-2601</th>
295
+ <th align="center">kanana-2-30b-a3b-instruct</th>
296
+ <th align="center">kanana-1.5-32.5b-instruct</th>
297
+ <th align="center">Qwen3-30B-A3B-Instruct-2507<sup>*</sup></th>
298
+ <th align="center">Qwen3-30B-A3B<br>(non-thinking)<sup>*</sup></th>
299
+ </tr>
300
+ </thead>
301
+ <tbody>
302
+ <tr>
303
+ <td align="center" colspan="7">Chat</td>
304
+ </tr>
305
+ <tr>
306
+ <td align="center">MT-Bench</td>
307
+ <td align="center">judge<sup>†</sup></td>
308
+ <td align="center">8.30</td>
309
+ <td align="center">8.42</td>
310
+ <td align="center">8.23</td>
311
+ <td align="center">8.71</td>
312
+ <td align="center">8.38</td>
313
+ </tr>
314
+ <tr>
315
+ <td align="center">KoMT-Bench</td>
316
+ <td align="center">judge<sup>†</sup></td>
317
+ <td align="center">8.21</td>
318
+ <td align="center">8.24</td>
319
+ <td align="center">7.94</td>
320
+ <td align="center">8.49</td>
321
+ <td align="center">7.89</td>
322
+ </tr>
323
+ <tr>
324
+ <td align="center" colspan="7">Instruction Following</td>
325
+ </tr>
326
+ <tr>
327
+ <td align="center">IFEval</td>
328
+ <td align="center">prompt strict</td>
329
+ <td align="center">87.25</td>
330
+ <td align="center">84.47</td>
331
+ <td align="center">79.48</td>
332
+ <td align="center">82.62</td>
333
+ <td align="center">84.10</td>
334
+ </tr>
335
+ <tr>
336
+ <td align="center">IFBench</td>
337
+ <td align="center">prompt strict</td>
338
+ <td align="center">48.30</td>
339
+ <td align="center">41.84</td>
340
+ <td align="center">38.78</td>
341
+ <td align="center">30.27</td>
342
+ <td align="center">29.25</td>
343
+ </tr>
344
+ <tr>
345
+ <td align="center">Multi-IF (EN)</td>
346
+ <td align="center">acc</td>
347
+ <td align="center">77.88</td>
348
+ <td align="center">75.81</td>
349
+ <td align="center">68.51</td>
350
+ <td align="center">77.93</td>
351
+ <td align="center">81.03</td>
352
+ </tr>
353
+ <tr>
354
+ <td align="center">Multi-Challenge</td>
355
+ <td align="center">acc</td>
356
+ <td align="center">35.16</td>
357
+ <td align="center">34.80</td>
358
+ <td align="center">19.05</td>
359
+ <td align="center">41.76</td>
360
+ <td align="center">27.84</td>
361
+ </tr>
362
+ <tr>
363
+ <td align="center" colspan="7">Tool Calling</td>
364
+ </tr>
365
+ <tr>
366
+ <td align="center">BFCL-v3<br>(Live<sup>‡</sup>)</td>
367
+ <td align="center">pass@1</td>
368
+ <td align="center">76.66</td>
369
+ <td align="center">74.30</td>
370
+ <td align="center">68.74</td>
371
+ <td align="center">73.93</td>
372
+ <td align="center">69.14</td>
373
+ </tr>
374
+ <tr>
375
+ <td align="center">BFCL-v3<br>(Multi-Turn<sup>‡</sup>)</td>
376
+ <td align="center">pass@1</td>
377
+ <td align="center">38.63</td>
378
+ <td align="center">35.38</td>
379
+ <td align="center">11.38</td>
380
+ <td align="center">38.77</td>
381
+ <td align="center">11.88</td>
382
+ </tr>
383
+ <tr>
384
+ <td align="center" colspan="7">Code Generation</td>
385
+ </tr>
386
+ <tr>
387
+ <td align="center">HumanEval+</td>
388
+ <td align="center">pass@1</td>
389
+ <td align="center">81.10</td>
390
+ <td align="center">79.88</td>
391
+ <td align="center">79.88</td>
392
+ <td align="center">86.59</td>
393
+ <td align="center">87.20</td>
394
+ </tr>
395
+ <tr>
396
+ <td align="center">MBPP+</td>
397
+ <td align="center">pass@1</td>
398
+ <td align="center">73.02</td>
399
+ <td align="center">73.81</td>
400
+ <td align="center">71.96</td>
401
+ <td align="center">75.13</td>
402
+ <td align="center">75.13</td>
403
+ </tr>
404
+ <tr>
405
+ <td align="center" colspan="7">Mathematics</td>
406
+ </tr>
407
+ <tr>
408
+ <td align="center">GSM8K</td>
409
+ <td align="center">em</td>
410
+ <td align="center">93.10</td>
411
+ <td align="center">91.89</td>
412
+ <td align="center">91.58</td>
413
+ <td align="center">93.56</td>
414
+ <td align="center">93.33</td>
415
+ </tr>
416
+ <tr>
417
+ <td align="center">MATH</td>
418
+ <td align="center">acc</td>
419
+ <td align="center">88.56</td>
420
+ <td align="center">86.26</td>
421
+ <td align="center">77.92</td>
422
+ <td align="center">90.96</td>
423
+ <td align="center">87.20</td>
424
+ </tr>
425
+ <tr>
426
+ <td align="center" colspan="7">Reasoning & Knowledge</td>
427
+ </tr>
428
+ <tr>
429
+ <td align="center">MMLU</td>
430
+ <td align="center">em</td>
431
+ <td align="center">81.61</td>
432
+ <td align="center">80.80</td>
433
+ <td align="center">82.75</td>
434
+ <td align="center">87.13</td>
435
+ <td align="center">85.60</td>
436
+ </tr>
437
+ <tr>
438
+ <td align="center">KMMLU</td>
439
+ <td align="center">em</td>
440
+ <td align="center">68.26</td>
441
+ <td align="center">67.32</td>
442
+ <td align="center">65.75</td>
443
+ <td align="center">67.56</td>
444
+ <td align="center">63.49</td>
445
+ </tr>
446
+ <tr>
447
+ <td align="center">GPQA Diamond</td>
448
+ <td align="center">pass@1</td>
449
+ <td align="center">52.53</td>
450
+ <td align="center">42.93</td>
451
+ <td align="center">42.42</td>
452
+ <td align="center">54.55</td>
453
+ <td align="center">50.51</td>
454
+ </tr>
455
+ <tr>
456
+ <td align="center">HAERAE-Bench (v1.0)</td>
457
+ <td align="center">em</td>
458
+ <td align="center">75.57</td>
459
+ <td align="center">75.57</td>
460
+ <td align="center">65.34</td>
461
+ <td align="center">53.41</td>
462
+ <td align="center">57.39</td>
463
+ </tr>
464
+ </tbody>
465
+ </table>
466
+
467
+ <sub>
468
+ <sup>*</sup> Evaluated using an internal evaluation toolkit.<br>
469
+ <sup>†</sup> Evaluated using <code><small>gpt-4o-2024-08-06</small></code> as the judge model.<br>
470
+ <sup>‡</sup> <code><small>Live</small></code> denotes the average score of 6 live benchmarks, and <code><small>Multi-Turn</small></code> denotes the average score of 4 multi-turn benchmarks.
471
+ </sub>
472
+
473
+ <br>
474
+
475
+ ### Reasoning model evaluation results
476
+
477
+ <table>
478
+ <thead>
479
+ <tr>
480
+ <th align="center">Benchmark</th>
481
+ <th align="center">Metric</th>
482
+ <th align="center">kanana-2-30b-a3b-thinking-2601</th>
483
+ <th align="center">kanana-2-30b-a3b-thinking</th>
484
+ <th align="center">Qwen3-30B-A3B-Thinking-2507<sup>*</sup></th>
485
+ <th align="center">Qwen3-30B-A3B<br>(thinking)<sup>*</sup></th>
486
+ </tr>
487
+ </thead>
488
+ <tbody>
489
+ <tr>
490
+ <td align="center" colspan="6">Reasoning & Knowledge</td>
491
+ </tr>
492
+ <tr>
493
+ <td align="center">MMLU-Pro</td>
494
+ <td align="center">pass@1</td>
495
+ <td align="center">74.2</td>
496
+ <td align="center">75.3</td>
497
+ <td align="center">80.8</td>
498
+ <td align="center">78.5</td>
499
+ </tr>
500
+ <tr>
501
+ <td align="center">GPQA Diamond</td>
502
+ <td align="center">pass@1</td>
503
+ <td align="center">57.8</td>
504
+ <td align="center">61.3</td>
505
+ <td align="center">70.6</td>
506
+ <td align="center">62.6</td>
507
+ </tr>
508
+ <tr>
509
+ <td align="center" colspan="6">Competition Math</td>
510
+ </tr>
511
+ <tr>
512
+ <td align="center">AIME 2025</td>
513
+ <td align="center">pass@1</td>
514
+ <td align="center">74.0</td>
515
+ <td align="center">72.7</td>
516
+ <td align="center">82.3</td>
517
+ <td align="center">70.7</td>
518
+ </tr>
519
+ <tr>
520
+ <td align="center">AIME 2024</td>
521
+ <td align="center">pass@1</td>
522
+ <td align="center">79.0</td>
523
+ <td align="center">78.3</td>
524
+ <td align="center">91.0</td>
525
+ <td align="center">82.7</td>
526
+ </tr>
527
+ <tr>
528
+ <td align="center">AIME 2024-Ko<sup>†</sup></td>
529
+ <td align="center">pass@1</td>
530
+ <td align="center">75.0</td>
531
+ <td align="center">25.3</td>
532
+ <td align="center">80.3</td>
533
+ <td align="center">72.3</td>
534
+ </tr>
535
+ <tr>
536
+ <td align="center" colspan="6">Code Generation</td>
537
+ </tr>
538
+ <tr>
539
+ <td align="center">LiveCodeBench</td>
540
+ <td align="center">pass@1</td>
541
+ <td align="center">58.8</td>
542
+ <td align="center">60.8</td>
543
+ <td align="center">68.3</td>
544
+ <td align="center">62.3</td>
545
+ </tr>
546
+ <tr>
547
+ <td align="center">LiveCodeBench-Ko<sup>‡</sup></td>
548
+ <td align="center">pass@1</td>
549
+ <td align="center">51.2</td>
550
+ <td align="center">9.4</td>
551
+ <td align="center">66.3<sup>¶</sup></td>
552
+ <td align="center">61.5<sup>¶</sup></td>
553
+ </tr>
554
+ <tr>
555
+ <td align="center" colspan="6">Instruction Following</td>
556
+ </tr>
557
+ <tr>
558
+ <td align="center">IFEval</td>
559
+ <td align="center">prompt strict</td>
560
+ <td align="center">82.2</td>
561
+ <td align="center">82.2</td>
562
+ <td align="center">87.8</td>
563
+ <td align="center">86.1</td>
564
+ </tr>
565
+ <tr>
566
+ <td align="center">IFBench</td>
567
+ <td align="center">prompt strict</td>
568
+ <td align="center">47.8</td>
569
+ <td align="center">42.3</td>
570
+ <td align="center">47.6</td>
571
+ <td align="center">36.7</td>
572
+ </tr>
573
+ <tr>
574
+ <td align="center" colspan="6">Tool Calling</td>
575
+ </tr>
576
+ <tr>
577
+ <td align="center">BFCL-v3<br>(Live<sup>§</sup>)</td>
578
+ <td align="center">pass@1</td>
579
+ <td align="center">75.9</td>
580
+ <td align="center">75.6</td>
581
+ <td align="center">82.9</td>
582
+ <td align="center">80.3</td>
583
+ </tr>
584
+ <tr>
585
+ <td align="center">BFCL-v3<br>(Multi-Turn<sup>§</sup>)</td>
586
+ <td align="center">pass@1</td>
587
+ <td align="center">43.7</td>
588
+ <td align="center">34.3</td>
589
+ <td align="center">53.6</td>
590
+ <td align="center">35.6</td>
591
+ </tr>
592
+ </tbody>
593
+ </table>
594
+
595
+ <sub>
596
+ <sup>*</sup> Evaluated using an internal evaluation toolkit.<br>
597
+ <sup>†</sup> Korean translation of AIME 2024 sourced from <a href="https://huggingface.co/datasets/amphora/MCLM">MCLM</a>.<br>
598
+ <sup>‡</sup> Internally translated to Korean.<br>
599
+ <sup>§</sup> <code><small>Live</small></code> denotes the average score of 6 live benchmarks, and <code><small>Multi-Turn</small></code> denotes the average score of 4 multi-turn benchmarks.<br>
600
+ <sup>¶</sup> Most responses were generated in English.
601
+ </sub>
602
+
603
+ <br>
604
+
605
+ ## Deployment
606
+
607
+ > [!NOTE]
608
+ > For optimal results with the reasoning model, please adhere to the default parameters: `temperature=0.6`, `top_p=0.95`, `top_k=20`. **We strongly advise against greedy decoding**, as it may lead to performance degradation and infinite repetition loops.
609
+
610
+ ### vLLM
611
+ [vLLM](https://github.com/vllm-project/vllm) is a fast and memory-optimized engine designed for high-performance LLM inference and serving.
612
+
613
+ For kanana-2-30b-a3b-instruct-2601,
614
+ ```shell
615
+ vllm serve kakaocorp/kanana-2-30b-a3b-instruct-2601 --enable-auto-tool-choice --tool-call-parser hermes
616
+ ```
617
+
618
+ For kanana-2-30b-a3b-thinking-2601,
619
+ ```shell
620
+ vllm serve kakaocorp/kanana-2-30b-a3b-thinking-2601 --reasoning-parser deepseek_r1 --enable-auto-tool-choice --tool-call-parser hermes
621
+ ```
622
+
623
+ ### SGLang
624
+ [SGLang](https://github.com/sgl-project/sglang) is a high-efficiency framework for serving LLMs and VLMs, enabling easy deployment of OpenAI-compatible API servers.
625
+
626
+ For kanana-2-30b-a3b-instruct-2601,
627
+ ```shell
628
+ python3 -m sglang.launch_server --model-path kakaocorp/kanana-2-30b-a3b-instruct-2601 --tool-call-parser qwen
629
+ ```
630
+
631
+ For kanana-2-30b-a3b-thinking-2601,
632
+ ```shell
633
+ python3 -m sglang.launch_server --model-path kakaocorp/kanana-2-30b-a3b-thinking-2601 --reasoning-parser deepseek-r1 --tool-call-parser qwen
634
+ ```
635
+
636
+ <br>
637
+
638
+ ## Processing 32K+ Length
639
+ Currently, the `config.json` uploaded to HuggingFace is configured for token lengths of 32,768 or less. To process tokens beyond this length, YaRN must be applied. By updating the `config.json` with the following parameters, you can apply YaRN to handle token sequences up to 128K in length:
640
+ ```json
641
+ "rope_scaling": {
642
+ "beta_fast": 32,
643
+ "beta_slow": 1,
644
+ "factor": 4.0,
645
+ "mscale": 1.0,
646
+ "mscale_all_dim": 1.0,
647
+ "original_max_position_embeddings": 32768,
648
+ "type": "yarn",
649
+ },
650
+ ```
651
+
652
+ Passing command line arguments for deployment:
653
+
654
+ - `vllm`
655
+ ```shell
656
+ vllm serve ... --hf-overrides '{"max_position_embeddings": 131072, "rope_scaling": {"rope_type":"deepseek_yarn","factor":4.0,"beta_fast":32,"beta_slow":1,"mscale":1.0,"mscale_all_dim":1.0,"original_max_position_embeddings":32768}}'
657
+ ```
658
+
659
+ - `sglang`
660
+ ```shell
661
+ python3 -m sglang.launch_server ... --json-model-override-args '{"max_position_embeddings":131072, "rope_scaling":{"rope_type":"deepseek_yarn","factor":4.0,"beta_fast":32,"beta_slow":1,"mscale":1.0,"mscale_all_dim":1.0,"original_max_position_embeddings":32768}}'
662
+ ```
663
+
664
+ > [!NOTE]
665
+ > Most leading open-source implementations of static YaRN apply a constant scaling factor, which can negatively impact performance on shorter texts. To ensure optimal performance:
666
+ > * **Enable `rope_scaling` only when necessary** for processing long contexts.
667
+ > * **Adjust the `factor` based on your specific needs** (e.g., set `factor` to 2.0 for a 65,536-token context)."
668
+
669
+ <br>
670
+
671
+ ## License
672
+
673
+ The model weights are released under the [Kanana License](./LICENSE).
674
+
675
+ <br>
676
+
677
+ ## Citation
678
+
679
+ ```
680
+ @article{,
681
+ title={Kanana-2 LLM},
682
+ author={Kanana LLM},
683
+ year={2025},
684
+ url={https://huggingface.co/collections/kakaocorp/kanana-2}
685
+ }
686
+ ```
687
+
688
+ <br>
689
+
690
+ ## Contact
691
+ - Kanana LLM Team Technical Support: kanana-llm@kakaocorp.com
692
+ - Business & Partnership Contact: alpha.k@kakaocorp.com
assets/logo/kanana.png ADDED

Git LFS Details

  • SHA256: 52b7b1de0b928150c7b8fe3517a7b86b4116271f2f0f0108bf2520281d6bac52
  • Pointer size: 131 Bytes
  • Size of remote file: 110 kB
chat_template.jinja ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- macro render_content(msg) -%}
2
+ {%- set c = msg.get('content') -%}
3
+ {%- if c is string -%}
4
+ {{ c }}
5
+ {%- elif c is not none -%}
6
+ {% for content in c -%}
7
+ {% if content['type'] == 'image' or content['type'] == 'image_url' -%}
8
+ <|media_begin|>image<|media_content|><|media_pad|><|media_end|>
9
+ {% elif content['type'] == 'video' or content['type']== 'video_url'-%}
10
+ <|kimi_k25_video_placeholder|>
11
+ {% else -%}
12
+ {{ content['text'] }}
13
+ {%- endif -%}
14
+ {%- endfor -%}
15
+ {%- endif -%}
16
+ {%- endmacro -%}
17
+
18
+ {% macro set_roles(message) -%}
19
+ {%- set role_name = message.get('name') or message['role'] -%}
20
+ {%- if message['role'] == 'user' -%}
21
+ <|im_user|>{{role_name}}<|im_middle|>
22
+ {%- elif message['role'] == 'assistant' -%}
23
+ <|im_assistant|>{{role_name}}<|im_middle|>
24
+ {%- else -%}
25
+ <|im_system|>{{role_name}}<|im_middle|>
26
+ {%- endif -%}
27
+ {%- endmacro -%}
28
+
29
+
30
+ {%- macro render_toolcalls(message) -%}
31
+ <|tool_calls_section_begin|>
32
+ {%- for tool_call in message['tool_calls'] -%}
33
+ {%- set formatted_id = tool_call['id'] -%}
34
+ <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
35
+ {%- endfor -%}
36
+ <|tool_calls_section_end|>
37
+ {%- endmacro -%}
38
+
39
+
40
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
41
+ {# Find last non-tool-call assistant message. If preserve_thinking, keep -1 so hist is empty and all msgs use suffix (retain reasoning). #}
42
+ {%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}
43
+ {%- if not preserve_thinking -%}
44
+ {%- for idx in range(messages|length-1, -1, -1) -%}
45
+ {%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}
46
+ {%- set ns.last_non_tool_call_assistant_msg = idx -%}
47
+ {%- break -%}
48
+ {%- endif -%}
49
+ {%- endfor -%}
50
+ {%- endif -%}
51
+
52
+ {# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}
53
+ {%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}
54
+ {%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}
55
+
56
+ {%- if tools -%}
57
+ {%- if tools_ts_str -%}
58
+ <|im_system|>tool_declare<|im_middle|>{{ tools_ts_str }}<|im_end|>
59
+ {%- else -%}
60
+ <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
61
+ {%- endif -%}
62
+ {%- endif -%}
63
+
64
+
65
+ {%- for message in hist_msgs -%}
66
+ {{set_roles(message)}}
67
+ {%- if message['role'] == 'assistant' -%}
68
+ <think></think>{{render_content(message)}}
69
+ {%- if message.get('tool_calls') -%}
70
+ {{render_toolcalls(message)}}
71
+ {%- endif -%}
72
+ {%- elif message['role'] == 'tool' -%}
73
+ {%- set tool_call_id = message.tool_call_id -%}
74
+ ## Return of {{ tool_call_id }}
75
+ {{render_content(message)}}
76
+ {%- elif message['content'] is not none -%}
77
+ {{render_content(message)}}
78
+ {%- endif -%}
79
+ <|im_end|>
80
+ {%- endfor -%}
81
+
82
+ {%- for message in suffix_msgs -%}
83
+ {{set_roles(message)}}
84
+ {%- if message['role'] == 'assistant' -%}
85
+ {%- if thinking is defined and thinking is false and preserve_thinking is false -%}
86
+ <think></think>{{render_content(message)}}
87
+ {%- else -%}
88
+ {%- set rc = message.get('reasoning', message.get('reasoning_content', '')) -%}
89
+ <think>{{rc}}</think>{{render_content(message)}}
90
+ {%- endif -%}
91
+ {%- if message.get('tool_calls') -%}
92
+ {{render_toolcalls(message)}}
93
+ {%- endif -%}
94
+ {%- elif message['role'] == 'tool' -%}
95
+ {%- set tool_call_id = message.tool_call_id -%}
96
+ ## Return of {{ tool_call_id }}
97
+ {{render_content(message)}}
98
+ {%- elif message['content'] is not none -%}
99
+ {{render_content(message)}}
100
+ {%- endif -%}
101
+ <|im_end|>
102
+ {%- endfor -%}
103
+
104
+
105
+ {%- if add_generation_prompt -%}
106
+ <|im_assistant|>assistant<|im_middle|>
107
+ {%- if thinking is defined and thinking is false -%}
108
+ <think></think>
109
+ {%- else -%}
110
+ <think>
111
+ {%- endif -%}
112
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128010,
10
+ "first_k_dense_replace": 1,
11
+ "head_dim": 64,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 6144,
16
+ "kv_lora_rank": 512,
17
+ "max_position_embeddings": 32768,
18
+ "model_type": "deepseek_v3",
19
+ "moe_intermediate_size": 768,
20
+ "moe_layer_freq": 1,
21
+ "n_group": 1,
22
+ "n_routed_experts": 128,
23
+ "n_shared_experts": 2,
24
+ "norm_topk_prob": true,
25
+ "num_attention_heads": 32,
26
+ "num_experts_per_tok": 6,
27
+ "num_hidden_layers": 48,
28
+ "num_key_value_heads": 32,
29
+ "pad_token_id": 128001,
30
+ "pretraining_tp": 1,
31
+ "q_lora_rank": null,
32
+ "qk_head_dim": 192,
33
+ "qk_nope_head_dim": 128,
34
+ "qk_rope_head_dim": 64,
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_interleave": true,
37
+ "rope_scaling": null,
38
+ "rope_theta": 1000000,
39
+ "routed_scaling_factor": 2.448,
40
+ "scoring_func": "sigmoid",
41
+ "tie_word_embeddings": false,
42
+ "topk_group": 1,
43
+ "topk_method": "noaux_tc",
44
+ "transformers_version": "4.57.3",
45
+ "use_cache": true,
46
+ "v_head_dim": 128,
47
+ "vocab_size": 163840
48
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": 128010,
5
+ "pad_token_id": 128001,
6
+ "transformers_version": "4.57.3"
7
+ }
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c672949ff907e3e7997d173f1d1fa4c96fb82f36a8512a6868c486e7eaff40
3
+ size 5145305090
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d352964cba8c4740688e4c68f7ddf44230abcd1d5689eca3714abf46dd4a6d
3
+ size 4997741139
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfae1cac374ca54d02168d05294544165614dc249642a8356f2554116d073a7d
3
+ size 4997742004
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b595fcbd3d8114b62499f634fd741cab711cd3c902b6007781d499c454514837
3
+ size 4997742689
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b16c2b305e7f56880f810ecabd4a206a82871be981de66e8418107f47baffb9d
3
+ size 4982800368
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17e279abbcb7dab30925e0ac312118948d9f8b07f945e1780057ea596e54fca
3
+ size 4997209812
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac0a90a91288176f18a120cdbe6b255b478c278ffcb791d67721c2faa1f2ca2e
3
+ size 4997742645
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb344100c1439932c7e6bcc3af0db6edf327f6ea3a3ca1fbad7a427f9aeab9bc
3
+ size 4997742672
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b41d24e719cec6dc946a6e5832d17af18ce8e43064dae7e400a15c3bf37741
3
+ size 4997742684
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:670bd75580fa758252ae51ea74403c81e7f83e2c9e5449af03735b4e24f8f138
3
+ size 4997742684
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ddf0a72277403a74ed636105c7415646a8f6eb60f555347ea62eaf9cdf372e
3
+ size 4997742684
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197357af7076c06d98776e5e7e0daa8b8819c63e74f31a2efd6ad10ce4c59c01
3
+ size 4997742684
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2ae33f785557b8b2559788c403c86d24d07f0be0e0dbd30e571d59a97bc704
3
+ size 1530443437
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|start_header_id|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|end_header_id|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|eot_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|eom_id|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|python_tag|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|NONE|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|endoftext|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|im_start|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|im_end|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|object_ref_start|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|object_ref_end|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|box_start|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|box_end|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|quad_start|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|quad_end|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|vision_start|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|vision_end|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|vision_pad|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|image_pad|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|video_pad|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<tool_call>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "128023": {
188
+ "content": "</tool_call>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "128024": {
196
+ "content": "<|fim_prefix|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|fim_middle|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|fim_suffix|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|fim_pad|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|repo_name|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|file_sep|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<tool_response>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "128031": {
252
+ "content": "</tool_response>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "128032": {
260
+ "content": "<think>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "128033": {
268
+ "content": "</think>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "128034": {
276
+ "content": "<|pad|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_35|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_36|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_37|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_38|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_39|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_40|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_41|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_42|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_43|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_44|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_45|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_46|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_47|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_48|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_49|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_50|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_51|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_52|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_53|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_54|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_55|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_56|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_57|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_58|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_59|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_60|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_61|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_62|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_63|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_64|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_65|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_66|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_67|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_68|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_69|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_70|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_71|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_72|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_73|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_74|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_75|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_76|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_77|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_78|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_79|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_80|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_81|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_82|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_83|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_84|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_85|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_86|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_87|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_88|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_89|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_90|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_91|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_92|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_93|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_94|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_95|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_96|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_97|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_98|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_99|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_100|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_101|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_102|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_103|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_104|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_105|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_106|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_107|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_108|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_109|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_110|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_111|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_112|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_113|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_114|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_115|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_116|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_117|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_118|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_119|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_120|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_121|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_122|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_123|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_124|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_125|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_126|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_127|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_128|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_129|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_130|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_131|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_132|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_133|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_134|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_135|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_136|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_137|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_138|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_139|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_140|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_141|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_142|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_143|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_144|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_145|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_146|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_147|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_148|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_149|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_150|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_151|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_152|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_153|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_154|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_155|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_156|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_157|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_158|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_159|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_160|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_161|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_162|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_163|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_164|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_165|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_166|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_167|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_168|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_169|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_170|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_171|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_172|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_173|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_174|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_175|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_176|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_177|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_178|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_179|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_180|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_181|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_182|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_183|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_184|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_185|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_186|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_187|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_188|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_189|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_190|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_191|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_192|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_193|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_194|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_195|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_196|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_197|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_198|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_199|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_200|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_201|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_202|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_203|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_204|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_205|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_206|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_207|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_208|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_209|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_210|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_211|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_212|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_213|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_214|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_215|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_216|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_217|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_218|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_219|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_220|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_221|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_222|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_223|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_224|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_225|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_226|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_227|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_228|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_229|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_230|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_231|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_232|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_233|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_234|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_235|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_236|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_237|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_238|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_239|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_240|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_241|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_242|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_243|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_244|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_245|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_246|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_247|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_248|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_249|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_250|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_251|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_252|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_253|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_254|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_255|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|im_end|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }