zjw49246 commited on
Commit
3e1e8f9
·
0 Parent(s):

Apex-35B-V1.0

Browse files
.gitattributes ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
+ *.png filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
LICENSE ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright 2026 Alibaba Cloud
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
README.md ADDED
@@ -0,0 +1,423 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ license_link: https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0/blob/main/LICENSE
4
+ library_name: transformers
5
+ pipeline_tag: text-generation
6
+ base_model: Qwen/Qwen3.6-35B-A3B
7
+ base_model_relation: finetune
8
+ tags:
9
+ - mixture-of-experts
10
+ - agent
11
+ - research
12
+ ---
13
+
14
+ <div align="center">
15
+ <picture>
16
+ <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0/resolve/main/assets/apex-intelligence-logo-dark.svg">
17
+ <img src="https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0/resolve/main/assets/apex-intelligence-logo.png" width="200" height="200" alt="Apex Intelligence">
18
+ </picture>
19
+ </div>
20
+
21
+ <hr>
22
+
23
+ <div align="center" style="line-height: 1;">
24
+ <a href="https://www.apexin.com/"><img alt="Homepage: Apex Intelligence" src="https://img.shields.io/static/v1?label=Homepage&amp;message=Apex+Intelligence&amp;color=2684FF&amp;labelColor=555555&amp;style=flat" height="20"></a>
25
+ <a href="https://github.com/apexin-ai/Apex-35B-V1.0"><img alt="GitHub: Apex-35B-V1.0" src="https://img.shields.io/static/v1?label=GitHub&amp;message=Apex-35B-V1.0&amp;color=E5E7EB&amp;labelColor=555555&amp;style=flat&amp;logo=github&amp;logoColor=white" height="20"></a>
26
+ <a href="https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0"><img alt="Hugging Face: Apexintelligence-AI" src="https://img.shields.io/static/v1?label=Hugging+Face&amp;message=Apexintelligence-AI&amp;color=FFC107&amp;labelColor=555555&amp;style=flat&amp;logo=huggingface&amp;logoColor=white" height="20"></a>
27
+ </div>
28
+ <div align="center" style="line-height: 1;">
29
+ <!-- Placeholder blog URL; replace when the article is published. -->
30
+ <a href="https://www.apexin.com/blog/apex-35b-v1"><img alt="Blog: Apex-35B-V1.0" src="https://img.shields.io/static/v1?label=Blog&amp;message=Apex-35B-V1.0&amp;color=7C3AED&amp;labelColor=555555&amp;style=flat&amp;logo=readme&amp;logoColor=white" height="20"></a>
31
+ <a href="https://x.com/apexin_ai"><img alt="Twitter: apexin_ai" src="https://img.shields.io/static/v1?label=Twitter&amp;message=apexin_ai&amp;color=E5E7EB&amp;labelColor=555555&amp;style=flat&amp;logo=x&amp;logoColor=white" height="20"></a>
32
+ <a href="https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0/blob/main/LICENSE"><img alt="License: Apache 2.0" src="https://img.shields.io/static/v1?label=License&amp;message=Apache+2.0&amp;color=2EA44F&amp;labelColor=555555&amp;style=flat" height="20"></a>
33
+ </div>
34
+
35
+ ## Model Introduction
36
+
37
+ **Apex-35B-V1.0** is the first model from **Apex Intelligence**, developed for both general-purpose use and research and supported by the [**Claude Code**](https://github.com/anthropics/claude-code) (v2.1.280 preferred) harness. It combines coding, tool use, question answering, and deep search with research tasks in AI, computational science, and robotics simulation.
38
+
39
+ Built on [Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B), the model is further trained on proprietary datasets and research trajectories. Its development incorporates recursive self-improvement (RSI) through **Apex Research**, an automated research system that contributes to training-data construction, automated experiments, training-recipe exploration, GPU kernel optimization, and inference optimization. Validated results from this process feed into subsequent development.
40
+
41
+ ### Key Features
42
+
43
+ - **General and research capabilities.** Covers everyday coding, question answering, search, and agentic tasks, alongside scientific and engineering research workflows.
44
+ - **Research through computation and feedback.** Plans computations, writes and runs programs, and uses results or execution feedback to revise its approach, including in fluid dynamics and robotics simulation.
45
+ - **Self-improving development.** Apex Research generated training data for the model's weak areas, refined the training recipe based on experimental feedback, and optimized the training and inference infrastructure.
46
+ - **Dynamic thinking.** Determines whether to reason and how long to reason on each turn, without manual mode switching.
47
+ - **Sparse architecture and long context.** Uses 35B total parameters with approximately 3B activated per token, and a context window of 262,144 tokens shared by input and output, supporting large code repositories and long multi-turn tool interactions.
48
+
49
+ ## Evaluation Results
50
+
51
+ ### Performance Overview
52
+
53
+ The chart below summarizes performance across four task categories and three internal benchmarks. Apex-35B-V1.0 is highlighted in blue.
54
+
55
+ - **Category averages:** Research, Agentic Tasks, Coding, and Reasoning show weighted averages of the benchmark scores within each category.
56
+ - **Internal benchmarks:** RoboRSI and Real2Sim show individual benchmark scores; CFD-Bench shows wins, draws, and losses against Qwen3.6-35B-A3B.
57
+
58
+ <p align="center">
59
+ <a href="https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0/resolve/main/assets/evaluation-overview.png"><img src="https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0/resolve/main/assets/evaluation-overview.png" alt="Apex-35B-V1.0 evaluation overview" width="100%"></a>
60
+ </p>
61
+
62
+ ### Detailed Benchmark Results
63
+
64
+ The table below provides the per-benchmark breakdown, grouped by task category, followed by the three internal benchmarks.
65
+
66
+ - **SciCode:** The two scores are **Main Problem / Subproblem**, in that order.
67
+ - **CFD-Bench:** Values are **Wins / Draws / Losses** against Qwen3.6-35B-A3B. **N/A** marks the baseline model for this comparison.
68
+
69
+ <div align="center" style="max-width: 100%; overflow-x: auto;">
70
+ <table align="center" style="margin-left: auto; margin-right: auto;">
71
+ <thead>
72
+ <tr>
73
+ <th align="left" scope="col" width="168" style="vertical-align: middle; text-align: left;">Benchmark</th>
74
+ <th align="center" scope="col" width="92" nowrap title="Apex-35B-V1.0 — 35B parameters" style="vertical-align: middle; text-align: center;">Apex-35B<br><sub>V1.0 · Ours</sub><br><sub>35B</sub></th>
75
+ <th align="center" scope="col" width="92" nowrap title="Qwen3.6-35B-A3B — 35B parameters" style="vertical-align: middle; text-align: center;">Qwen3.6<br><sub>35B-A3B</sub><br><sub>35B</sub></th>
76
+ <th align="center" scope="col" width="92" nowrap title="Recursive Flint — 39.8B parameters" style="vertical-align: middle; text-align: center;">Recursive<br><sub>Flint</sub><br><sub>39.8B</sub></th>
77
+ <th align="center" scope="col" width="92" nowrap title="GLM-5.3 — 753B parameters" style="vertical-align: middle; text-align: center;">GLM<br><sub>5.3</sub><br><sub>753B</sub></th>
78
+ <th align="center" scope="col" width="92" nowrap title="GLM-5.3-Flash — 320B parameters" style="vertical-align: middle; text-align: center;">GLM<br><sub>5.3-Flash</sub><br><sub>320B</sub></th>
79
+ <th align="center" scope="col" width="92" nowrap title="DeepSeek-V4.1-Flash-1017 — 552B backbone + 196B Engram memory parameters" style="vertical-align: middle; text-align: center;">DeepSeek<br><sub>V4.1-Flash-1017</sub><br><sub>552B&nbsp;+&nbsp;196B</sub></th>
80
+ </tr>
81
+ </thead>
82
+ <tbody>
83
+ <tr><th colspan="7" align="center" style="vertical-align: middle; text-align: center;">Research</th></tr>
84
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">SciCode<br><sub>Main Problem /<br>Subproblem</sub></td><td align="center" style="vertical-align: middle; text-align: center;"><strong>62.6 /<br>75.6</strong></td><td align="center" style="vertical-align: middle; text-align: center;">37.5 /<br>60.6</td><td align="center" style="vertical-align: middle; text-align: center;">26.6 /<br>46.0</td><td align="center" style="vertical-align: middle; text-align: center;">79.2 /<br>91.3</td><td align="center" style="vertical-align: middle; text-align: center;">76.6 /<br>86.8</td><td align="center" style="vertical-align: middle; text-align: center;">68.8 /<br>81.9</td></tr>
85
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">FrontierScience</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>40.0</strong></td><td align="center" style="vertical-align: middle; text-align: center;">21.7</td><td align="center" style="vertical-align: middle; text-align: center;">5.0</td><td align="center" style="vertical-align: middle; text-align: center;">30.7</td><td align="center" style="vertical-align: middle; text-align: center;">50.0</td><td align="center" style="vertical-align: middle; text-align: center;">61.7</td></tr>
86
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">ASI-Bench</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>22.5</strong></td><td align="center" style="vertical-align: middle; text-align: center;">16.3</td><td align="center" style="vertical-align: middle; text-align: center;">17.5</td><td align="center" style="vertical-align: middle; text-align: center;">33.1</td><td align="center" style="vertical-align: middle; text-align: center;">37.4</td><td align="center" style="vertical-align: middle; text-align: center;">38.9</td></tr>
87
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">BioMysteryBench<br><sub>Human-solvable</sub></td><td align="center" style="vertical-align: middle; text-align: center;"><strong>76.7</strong></td><td align="center" style="vertical-align: middle; text-align: center;">53.4</td><td align="center" style="vertical-align: middle; text-align: center;">49.3</td><td align="center" style="vertical-align: middle; text-align: center;">85.6</td><td align="center" style="vertical-align: middle; text-align: center;">87.7</td><td align="center" style="vertical-align: middle; text-align: center;">86.3</td></tr>
88
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">BioMysteryBench<br><sub>Human-difficult</sub></td><td align="center" style="vertical-align: middle; text-align: center;"><strong>35.3</strong></td><td align="center" style="vertical-align: middle; text-align: center;">11.8</td><td align="center" style="vertical-align: middle; text-align: center;">5.9</td><td align="center" style="vertical-align: middle; text-align: center;">39.1</td><td align="center" style="vertical-align: middle; text-align: center;">41.2</td><td align="center" style="vertical-align: middle; text-align: center;">29.4</td></tr>
89
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">PaperBench</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>60.9</strong></td><td align="center" style="vertical-align: middle; text-align: center;">45.8</td><td align="center" style="vertical-align: middle; text-align: center;">29.3</td><td align="center" style="vertical-align: middle; text-align: center;">42.5</td><td align="center" style="vertical-align: middle; text-align: center;">81.8</td><td align="center" style="vertical-align: middle; text-align: center;">87.1</td></tr>
90
+ <tr><th colspan="7" align="center" style="vertical-align: middle; text-align: center;">Agentic Tasks</th></tr>
91
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">BrowseComp</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>69.4</strong></td><td align="center" style="vertical-align: middle; text-align: center;">42.1</td><td align="center" style="vertical-align: middle; text-align: center;">23.2</td><td align="center" style="vertical-align: middle; text-align: center;">80.9</td><td align="center" style="vertical-align: middle; text-align: center;">81.0</td><td align="center" style="vertical-align: middle; text-align: center;">90.5</td></tr>
92
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">WideSearch</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>69.9</strong></td><td align="center" style="vertical-align: middle; text-align: center;">60.9</td><td align="center" style="vertical-align: middle; text-align: center;">48.3</td><td align="center" style="vertical-align: middle; text-align: center;">78.4</td><td align="center" style="vertical-align: middle; text-align: center;">81.1</td><td align="center" style="vertical-align: middle; text-align: center;">79.8</td></tr>
93
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">BFCL V4</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>84.0</strong></td><td align="center" style="vertical-align: middle; text-align: center;">75.2</td><td align="center" style="vertical-align: middle; text-align: center;">65.4</td><td align="center" style="vertical-align: middle; text-align: center;">75.8</td><td align="center" style="vertical-align: middle; text-align: center;">73.9</td><td align="center" style="vertical-align: middle; text-align: center;">75.0</td></tr>
94
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">AutomationBench</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>49.3</strong></td><td align="center" style="vertical-align: middle; text-align: center;">10.0</td><td align="center" style="vertical-align: middle; text-align: center;">9.8</td><td align="center" style="vertical-align: middle; text-align: center;">50.2</td><td align="center" style="vertical-align: middle; text-align: center;">48.8</td><td align="center" style="vertical-align: middle; text-align: center;">60.5</td></tr>
95
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">APEX-Agents</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>64.6</strong></td><td align="center" style="vertical-align: middle; text-align: center;">41.7</td><td align="center" style="vertical-align: middle; text-align: center;">33.8</td><td align="center" style="vertical-align: middle; text-align: center;">68.2</td><td align="center" style="vertical-align: middle; text-align: center;">73.3</td><td align="center" style="vertical-align: middle; text-align: center;">74.2</td></tr>
96
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">Agents’ Last Exam<br><sub>(ALE)</sub></td><td align="center" style="vertical-align: middle; text-align: center;"><strong>19.1</strong></td><td align="center" style="vertical-align: middle; text-align: center;">12.4</td><td align="center" style="vertical-align: middle; text-align: center;">19.1</td><td align="center" style="vertical-align: middle; text-align: center;">28.5</td><td align="center" style="vertical-align: middle; text-align: center;">26.3</td><td align="center" style="vertical-align: middle; text-align: center;">35.4</td></tr>
97
+ <tr><th colspan="7" align="center" style="vertical-align: middle; text-align: center;">Coding</th></tr>
98
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">Terminal-Bench 2.1</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>65.2</strong></td><td align="center" style="vertical-align: middle; text-align: center;">46.1</td><td align="center" style="vertical-align: middle; text-align: center;">59.6</td><td align="center" style="vertical-align: middle; text-align: center;">89.9</td><td align="center" style="vertical-align: middle; text-align: center;">84.3</td><td align="center" style="vertical-align: middle; text-align: center;">90.6</td></tr>
99
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">SWE-bench Pro v2</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>92.4</strong></td><td align="center" style="vertical-align: middle; text-align: center;">72.4</td><td align="center" style="vertical-align: middle; text-align: center;">85.2</td><td align="center" style="vertical-align: middle; text-align: center;">95.8</td><td align="center" style="vertical-align: middle; text-align: center;">94.7</td><td align="center" style="vertical-align: middle; text-align: center;">97.5</td></tr>
100
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">SWE-bench Verified<br><sub>No Internet</sub></td><td align="center" style="vertical-align: middle; text-align: center;"><strong>73.4</strong></td><td align="center" style="vertical-align: middle; text-align: center;">63.8</td><td align="center" style="vertical-align: middle; text-align: center;">74.8</td><td align="center" style="vertical-align: middle; text-align: center;">79.8</td><td align="center" style="vertical-align: middle; text-align: center;">72.2</td><td align="center" style="vertical-align: middle; text-align: center;">82.0</td></tr>
101
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">LiveCodeBench v6</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>82.3</strong></td><td align="center" style="vertical-align: middle; text-align: center;">84.5</td><td align="center" style="vertical-align: middle; text-align: center;">85.1</td><td align="center" style="vertical-align: middle; text-align: center;">78.3</td><td align="center" style="vertical-align: middle; text-align: center;">75.3</td><td align="center" style="vertical-align: middle; text-align: center;">95.7</td></tr>
102
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">SWE-Atlas QnA</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>33.1</strong></td><td align="center" style="vertical-align: middle; text-align: center;">12.1</td><td align="center" style="vertical-align: middle; text-align: center;">16.1</td><td align="center" style="vertical-align: middle; text-align: center;">48.7</td><td align="center" style="vertical-align: middle; text-align: center;">45.2</td><td align="center" style="vertical-align: middle; text-align: center;">50.8</td></tr>
103
+ <tr><th colspan="7" align="center" style="vertical-align: middle; text-align: center;">Reasoning</th></tr>
104
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">MMLU-Pro</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>87.2</strong></td><td align="center" style="vertical-align: middle; text-align: center;">79.0</td><td align="center" style="vertical-align: middle; text-align: center;">70.8</td><td align="center" style="vertical-align: middle; text-align: center;">88.2</td><td align="center" style="vertical-align: middle; text-align: center;">85.5</td><td align="center" style="vertical-align: middle; text-align: center;">68.3</td></tr>
105
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">AA-LCR</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>77.0</strong></td><td align="center" style="vertical-align: middle; text-align: center;">74.0</td><td align="center" style="vertical-align: middle; text-align: center;">59.0</td><td align="center" style="vertical-align: middle; text-align: center;">80.0</td><td align="center" style="vertical-align: middle; text-align: center;">79.0</td><td align="center" style="vertical-align: middle; text-align: center;">87.0</td></tr>
106
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">HLE</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>47.2</strong></td><td align="center" style="vertical-align: middle; text-align: center;">36.2</td><td align="center" style="vertical-align: middle; text-align: center;">18.2</td><td align="center" style="vertical-align: middle; text-align: center;">61.3</td><td align="center" style="vertical-align: middle; text-align: center;">55.3</td><td align="center" style="vertical-align: middle; text-align: center;">42.6</td></tr>
107
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">GPQA Diamond</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>83.3</strong></td><td align="center" style="vertical-align: middle; text-align: center;">75.8</td><td align="center" style="vertical-align: middle; text-align: center;">66.2</td><td align="center" style="vertical-align: middle; text-align: center;">88.4</td><td align="center" style="vertical-align: middle; text-align: center;">84.9</td><td align="center" style="vertical-align: middle; text-align: center;">90.9</td></tr>
108
+ <tr><th colspan="7" align="center" style="vertical-align: middle; text-align: center;">Internal Benchmarks</th></tr>
109
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">RoboRSI</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>44.5</strong></td><td align="center" style="vertical-align: middle; text-align: center;">35.0</td><td align="center" style="vertical-align: middle; text-align: center;">30.0</td><td align="center" style="vertical-align: middle; text-align: center;">58.4</td><td align="center" style="vertical-align: middle; text-align: center;">52.4</td><td align="center" style="vertical-align: middle; text-align: center;">74.7</td></tr>
110
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">Real2Sim</td><td align="center" style="vertical-align: middle; text-align: center;"><strong>21.6</strong></td><td align="center" style="vertical-align: middle; text-align: center;">2.1</td><td align="center" style="vertical-align: middle; text-align: center;">2.3</td><td align="center" style="vertical-align: middle; text-align: center;">25.6</td><td align="center" style="vertical-align: middle; text-align: center;">21.4</td><td align="center" style="vertical-align: middle; text-align: center;">36.3</td></tr>
111
+ <tr><td align="left" style="vertical-align: middle; text-align: left;">CFD-Bench<br><sub>Wins / Draws / Losses<br>vs. Qwen3.6-35B-A3B</sub></td><td align="center" style="vertical-align: middle; text-align: center;"><strong>79&nbsp;/&nbsp;0&nbsp;/&nbsp;21</strong></td><td align="center" style="vertical-align: middle; text-align: center;">N/A</td><td align="center" style="vertical-align: middle; text-align: center;">54&nbsp;/&nbsp;2&nbsp;/&nbsp;44</td><td align="center" style="vertical-align: middle; text-align: center;">99&nbsp;/&nbsp;0&nbsp;/&nbsp;1</td><td align="center" style="vertical-align: middle; text-align: center;">98&nbsp;/&nbsp;0&nbsp;/&nbsp;2</td><td align="center" style="vertical-align: middle; text-align: center;">100&nbsp;/&nbsp;0&nbsp;/&nbsp;0</td></tr>
112
+ </tbody>
113
+ </table>
114
+ </div>
115
+
116
+ ## Model Summary
117
+
118
+ <div align="center">
119
+ <table align="center">
120
+ <tbody>
121
+ <tr><th align="center" scope="row">Architecture</th><td align="center">Sparse mixture-of-experts (MoE)</td></tr>
122
+ <tr><th align="center" scope="row">Parameters</th><td align="center">35B total · 3B active per token</td></tr>
123
+ <tr><th align="center" scope="row">Context Length</th><td align="center">262,144 tokens (input + output)</td></tr>
124
+ <tr><th align="center" scope="row">Input / Output</th><td align="center">Text / Text</td></tr>
125
+ <tr><th align="center" scope="row">Thinking Mode</th><td align="center">Dynamic</td></tr>
126
+ <tr><th align="center" scope="row">Weight Precision</th><td align="center">BF16</td></tr>
127
+ </tbody>
128
+ </table>
129
+ </div>
130
+
131
+ ## Deployment
132
+
133
+ ### Download Model
134
+
135
+ <div align="center" style="max-width: 100%; overflow-x: auto;">
136
+ <table align="center" style="margin-left: auto; margin-right: auto;">
137
+ <thead>
138
+ <tr><th align="center">Model</th><th align="center">Download</th><th align="center">Parameters</th><th align="center">Format</th></tr>
139
+ </thead>
140
+ <tbody>
141
+ <tr><td align="center">Apex-35B-V1.0</td><td align="center"><a href="https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0">🤗 Hugging Face</a></td><td align="center">35B in total, 3B activated</td><td align="center">BF16 safetensors (about 72 GB)</td></tr>
142
+ <tr><td align="center">Apex-35B-V1.0-GGUF</td><td align="center"><a href="https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0-GGUF">🤗 Hugging Face</a></td><td align="center">35B in total, 3B activated</td><td align="center">GGUF: BF16, Q8_0, Q6_K, Q5_K_M, Q4_K_M</td></tr>
143
+ </tbody>
144
+ </table>
145
+ </div>
146
+
147
+ ```bash
148
+ pip install -U huggingface_hub # provides the hf command
149
+ hf download Apexintelligence-AI/Apex-35B-V1.0 --local-dir Apex-35B-V1.0
150
+ ```
151
+
152
+ ### Serving Apex-35B-V1.0
153
+
154
+ Apex-35B-V1.0 can be served with popular inference frameworks through an OpenAI-compatible API. The commands below start an endpoint at `http://localhost:8000/v1` and, except for `transformers serve` and llama.cpp (see their sections), set the served model name to `Apex-35B-V1.0`, which the examples use as `model`. To use local weights, replace `Apexintelligence-AI/Apex-35B-V1.0` with the local directory; the served model name stays the same.
155
+
156
+ > [!Important]
157
+ > The checkpoint includes its own chat template (`chat_template.jinja`). Every framework below loads it automatically (llama.cpp with `--jinja`). Do not pass `--chat-template`, and do not replace it with the Qwen3.6 template: Apex-35B-V1.0 expects the generation prompt to end with `<think>`.
158
+
159
+ > [!Important]
160
+ > The model has a context length of 262,144 tokens, shared by input and output. The BF16 weights take about 72 GB. One GPU with 141 GB or more (for example H20-3e, H200, or B200) runs the model with tensor parallel size 1 and the full context. On H100 NVL (94 GB) we ran SGLang and vLLM with tensor parallel size 2, and TokenSpeed with tensor parallel size 1; on A100 (40 GB) we ran SGLang and vLLM with tensor parallel size 4. On other GPUs with less memory, increase the tensor parallel size. A shorter context saves little memory: the KV cache for the full 262,144 tokens takes about 5.4 GB.
161
+
162
+ > [!Note]
163
+ > The install commands below install CUDA 13 builds (PyTorch for SGLang and Transformers, and the vLLM wheel). We ran them with NVIDIA drivers 580 and 595. On a machine with 4 × A100 40 GB and driver 570 (CUDA 12.8) we observed:
164
+ > - vLLM started after reinstalling its CUDA 12.9 build: `uv pip install "vllm==0.32.0+cu129" --extra-index-url https://wheels.vllm.ai/0.32.0/cu129 --reinstall-package vllm`.
165
+ > - SGLang and Transformers stopped with "The NVIDIA driver on your system is too old" and ran only after loading NVIDIA's CUDA 13 forward-compatibility package (`cuda-compat-13-0`).
166
+ > - SGLang with MTP started, but its first request failed while FlashInfer compiled its kernels; we did not find a fix. We did not test driver 570 on Hopper or Blackwell GPUs.
167
+
168
+ > [!Tip]
169
+ > Install each framework in its own virtual environment. We tested with Python 3.12 (all frameworks) and 3.13 (vLLM and TokenSpeed), for example:
170
+ > ```bash
171
+ > uv venv --python 3.12 --seed .venv-sglang && source .venv-sglang/bin/activate
172
+ > ```
173
+ > `--seed` adds `pip` to the environment. Both the `pip install` and the `uv pip install` commands below install into the active environment.
174
+
175
+ #### SGLang
176
+
177
+ [SGLang](https://github.com/sgl-project/sglang) `>=0.5.22` is recommended:
178
+
179
+ ```bash
180
+ uv pip install "sglang[all]>=0.5.22"
181
+ ```
182
+
183
+ - **Standard launch:**
184
+
185
+ ```bash
186
+ python -m sglang.launch_server --model-path Apexintelligence-AI/Apex-35B-V1.0 --served-model-name Apex-35B-V1.0 --port 8000 --tp-size 1 --context-length 262144 --reasoning-parser qwen3 --tool-call-parser qwen3_coder
187
+ ```
188
+
189
+ - **Multi-Token Prediction (MTP):**
190
+
191
+ ```bash
192
+ python -m sglang.launch_server --model-path Apexintelligence-AI/Apex-35B-V1.0 --served-model-name Apex-35B-V1.0 --port 8000 --tp-size 1 --context-length 262144 --reasoning-parser qwen3 --tool-call-parser qwen3_coder --speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
193
+ ```
194
+
195
+ The first request after startup can take about one minute; later requests are fast.
196
+
197
+ #### vLLM
198
+
199
+ [vLLM](https://github.com/vllm-project/vllm) `>=0.32.0` is recommended:
200
+
201
+ ```bash
202
+ uv pip install "vllm>=0.32.0" --torch-backend=auto
203
+ ```
204
+
205
+ - **Standard launch:**
206
+
207
+ ```bash
208
+ vllm serve Apexintelligence-AI/Apex-35B-V1.0 --served-model-name Apex-35B-V1.0 --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder
209
+ ```
210
+
211
+ - **Multi-Token Prediction (MTP):**
212
+
213
+ ```bash
214
+ vllm serve Apexintelligence-AI/Apex-35B-V1.0 --served-model-name Apex-35B-V1.0 --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --speculative-config '{"method":"mtp","num_speculative_tokens":2}'
215
+ ```
216
+
217
+ vLLM returns the thinking in the `reasoning` field instead of `reasoning_content`. The first start can download and compile kernels, which needs internet access and several minutes.
218
+
219
+ #### TokenSpeed
220
+
221
+ [TokenSpeed](https://github.com/lightseekorg/tokenspeed) supports NVIDIA Hopper and Blackwell GPUs with CUDA 13. Install the tested nightly build:
222
+
223
+ ```bash
224
+ pip install "tokenspeed==0.1.1.post20261025" --extra-index-url https://lightseek.org/whl/nightly --extra-index-url https://lightseek.org/whl/nightly/cu130
225
+ ```
226
+
227
+ - **Standard launch:**
228
+
229
+ ```bash
230
+ tokenspeed serve Apexintelligence-AI/Apex-35B-V1.0 --served-model-name Apex-35B-V1.0 --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --reasoning-parser qwen3 --tool-call-parser qwen_coder
231
+ ```
232
+
233
+ - **Multi-Token Prediction (MTP):**
234
+
235
+ ```bash
236
+ tokenspeed serve Apexintelligence-AI/Apex-35B-V1.0 --served-model-name Apex-35B-V1.0 --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --reasoning-parser qwen3 --tool-call-parser qwen_coder --speculative-algorithm MTP --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
237
+ ```
238
+
239
+ This is the nightly build we tested (2026-10-25); later builds may behave differently. The pin covers only the `tokenspeed` package; its dependencies come from the nightly index on the day you install. With `uv pip install`, add `--index-strategy unsafe-best-match` so that uv takes packages from both indexes. In TokenSpeed the tool-call parser is named `qwen_coder`, not `qwen3_coder`. Without the two parser flags, the thinking and the tool calls stay in `content`. The first start compiles kernels, which can take 15 to 25 minutes; later starts reuse the cache. During startup each GPU process used about 280 GiB (300 GB) of host memory in our tests, so tensor parallel size 2 needs about 560 GiB (600 GB) or more. On H100 NVL, tensor parallel size 2 stopped at startup with "an illegal memory access was encountered" in our test; tensor parallel size 1 on one H100 NVL worked.
240
+
241
+ #### KTransformers
242
+
243
+ [KTransformers](https://github.com/kvcache-ai/ktransformers) runs the experts on the CPU and the rest of the model on the GPU. Install it as described in its [deployment guide](https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/Qwen3.5.md), download the weights to a local directory, and add the reasoning and tool-call parsers to the launch command:
244
+
245
+ ```bash
246
+ python -m sglang.launch_server --model /path/to/Apex-35B-V1.0 --kt-weight-path /path/to/Apex-35B-V1.0 --kt-cpuinfer 32 --kt-threadpool-count 2 --kt-num-gpu-experts 1 --kt-method BF16 --attention-backend triton --trust-remote-code --mem-fraction-static 0.9 --chunked-prefill-size 4096 --max-running-requests 8 --max-total-tokens 32000 --enable-mixed-chunk --tensor-parallel-size 1 --disable-shared-experts-fusion --reasoning-parser qwen3 --tool-call-parser qwen3_coder --served-model-name Apex-35B-V1.0 --port 8000
247
+ ```
248
+
249
+ This command is based on the KTransformers guide, with the parsers, served model name and port added. `--max-total-tokens 32000` limits the KV cache to about 32,000 tokens, so a request cannot use the 65,536-token output budget from the examples. For longer prompts and outputs, raise `--max-total-tokens` or lower `max_tokens` in the request.
250
+
251
+ With `kt-kernel` / `sglang-kt` 0.7.2 we also needed these packages:
252
+
253
+ ```bash
254
+ pip install nvidia-cudnn-cu12==9.16.0.29
255
+ # Hopper and Ampere GPUs (tested: H20, H200, H100 NVL, A100):
256
+ pip install --no-deps sgl-kernel==0.3.21
257
+ # Blackwell GPUs (tested: B200); also add --moe-runner-backend triton to the launch command:
258
+ pip install ktransformers==0.7.2
259
+ ```
260
+
261
+ #### Hugging Face Transformers
262
+
263
+ [Transformers](https://github.com/huggingface/transformers) includes a lightweight server for quick tests:
264
+
265
+ ```bash
266
+ pip install "transformers[serving]>=5.21.0" pillow torchvision
267
+ transformers serve Apexintelligence-AI/Apex-35B-V1.0 --port 8000
268
+ ```
269
+
270
+ `pillow` and `torchvision` are needed to load the processor files shipped with the checkpoint. `transformers serve` has no served-model-name option: set `model` in the examples to the path or repository ID that you passed to it. It rejects the `top_k` request field, so remove it from `extra_body`. It does not pass the thinking of earlier turns back to the model; for multi-turn and agent use, prefer SGLang, vLLM, or TokenSpeed. If `GET /v1/models` returns HTTP 500 (`CacheNotFound`), create the `hub` folder under `$HF_HOME`; chat requests are not affected.
271
+
272
+ #### llama.cpp and Unsloth
273
+
274
+ GGUF builds (BF16, Q8_0, Q6_K, Q5_K_M, Q4_K_M) for llama.cpp, Unsloth, and other local runtimes are in [Apex-35B-V1.0-GGUF](https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0-GGUF). For example, with a recent [llama.cpp](https://github.com/ggml-org/llama.cpp) build (`llama-server` on `PATH`):
275
+
276
+ ```bash
277
+ hf download Apexintelligence-AI/Apex-35B-V1.0-GGUF Apex-35B-V1.0-Q4_K_M.gguf --local-dir .
278
+ llama-server -m Apex-35B-V1.0-Q4_K_M.gguf --jinja -ngl 99 -c 32768 --port 8000 --temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0
279
+ ```
280
+
281
+ `--jinja` is required: it applies the chat template embedded in the file. `-c` sets the context for the prompt and the output together; with `-c 32768`, a long thinking can be cut off before the 65,536-token budget of the examples, so raise `-c` if you have the memory. For Unsloth and the other files, see the [GGUF model card](https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0-GGUF).
282
+
283
+ ### Using Apex-35B-V1.0 via the Chat Completions API
284
+
285
+ The chat completions API is accessible through standard HTTP requests or the OpenAI SDK. Install the SDK in a separate environment from the server (SGLang 0.5.22 and sglang-kt 0.7.2 require `openai==2.6.1`; upgrading `openai` there breaks that requirement) and configure the endpoint:
286
+
287
+ ```bash
288
+ pip install -U openai
289
+
290
+ # Set the following accordingly
291
+ export OPENAI_BASE_URL="http://localhost:8000/v1"
292
+ export OPENAI_API_KEY="EMPTY"
293
+ ```
294
+
295
+ > [!Tip]
296
+ > We recommend `temperature=1.0`, `top_p=0.95`, `top_k=20`, and `max_tokens=65536` (the output budget includes the thinking). The first three values are also the defaults in `generation_config.json`.
297
+
298
+ > [!Important]
299
+ > Apex-35B-V1.0 decides on each turn whether to think and for how long. The thinking is returned in `reasoning_content` (`reasoning` in vLLM) and the answer in `content`. For multi-turn conversations and tool calls, append the complete assistant message to `messages`, for example with `msg.model_dump(exclude_none=True)`, and pass `extra_body={"chat_template_kwargs": {"preserve_thinking": True}}` to keep the thinking of earlier turns. With SGLang, `model_dump()` can print a Pydantic serializer warning about the `metadata` field; it does not change the result.
300
+
301
+ #### Chat
302
+
303
+ ```python
304
+ from openai import OpenAI
305
+
306
+ client = OpenAI() # reads OPENAI_BASE_URL and OPENAI_API_KEY
307
+
308
+ questions = [
309
+ "Water flows through a pipe with an inner diameter of 5 cm at a mean velocity of 2 m/s. Take the kinematic viscosity as 1.0×10⁻⁶ m²/s. "
310
+ "What is the Reynolds number, and is the flow laminar or turbulent? Please answer briefly.",
311
+ "What if the velocity drops to 2 cm/s?",
312
+ ]
313
+
314
+ messages = []
315
+ for q in questions:
316
+ messages.append({"role": "user", "content": q})
317
+ resp = client.chat.completions.create(
318
+ model="Apex-35B-V1.0",
319
+ messages=messages,
320
+ temperature=1.0,
321
+ top_p=0.95,
322
+ max_tokens=65536,
323
+ extra_body={
324
+ "top_k": 20,
325
+ "chat_template_kwargs": {"preserve_thinking": True},
326
+ },
327
+ )
328
+ choice = resp.choices[0]
329
+ msg = choice.message
330
+ text = (msg.content or "").strip()
331
+ print("Q:", q)
332
+ if choice.finish_reason == "length" or not text:
333
+ print("A: (no complete answer: the output was cut off or empty)")
334
+ break
335
+ print("A:", text, "\n")
336
+ messages.append(msg.model_dump(exclude_none=True))
337
+ ```
338
+
339
+ #### Tool Calling
340
+
341
+ The model calls tools in the Qwen XML format; the tool-call parser of each framework converts the calls into standard `tool_calls`. Return each tool result with `role="tool"` and its `tool_call_id`:
342
+
343
+ ```python
344
+ import json
345
+ from openai import OpenAI
346
+
347
+ client = OpenAI()
348
+
349
+ # kinematic viscosity at 20 °C (m²/s), approximate example values; glycerol means pure glycerol
350
+ VISCOSITY = {"water": 1.0e-6, "glycerol": 1.12e-3, "air": 1.5e-5}
351
+
352
+
353
+ def get_fluid_properties(fluid):
354
+ if fluid not in VISCOSITY:
355
+ return {"error": f"unknown fluid: {fluid}", "available": list(VISCOSITY)}
356
+ return {"fluid": fluid, "temperature_C": 20, "kinematic_viscosity_m2_s": VISCOSITY[fluid]}
357
+
358
+
359
+ tools = [{
360
+ "type": "function",
361
+ "function": {
362
+ "name": "get_fluid_properties",
363
+ "description": "Look up the kinematic viscosity of a fluid at 20 °C",
364
+ "parameters": {
365
+ "type": "object",
366
+ "properties": {"fluid": {"type": "string", "enum": list(VISCOSITY)}},
367
+ "required": ["fluid"],
368
+ },
369
+ },
370
+ }]
371
+
372
+ messages = [{"role": "user", "content": (
373
+ "A pipe has an inner diameter of 5 cm and a mean flow velocity of 0.5 m/s. Is the flow laminar or turbulent "
374
+ "when it carries water at 20 °C, and when it carries glycerol at 20 °C? Use get_fluid_properties to look up "
375
+ "the kinematic viscosity, then compute the Reynolds numbers and explain briefly. Answer in plain text, without LaTeX."
376
+ )}]
377
+ for _ in range(8): # at most 8 model requests
378
+ resp = client.chat.completions.create(
379
+ model="Apex-35B-V1.0",
380
+ messages=messages,
381
+ tools=tools,
382
+ tool_choice="auto",
383
+ temperature=1.0,
384
+ top_p=0.95,
385
+ max_tokens=65536,
386
+ extra_body={"top_k": 20, "chat_template_kwargs": {"preserve_thinking": True}},
387
+ )
388
+ choice = resp.choices[0]
389
+ msg = choice.message
390
+ messages.append(msg.model_dump(exclude_none=True))
391
+ if choice.finish_reason == "length": # cut off: do not run partial tool calls
392
+ print("(no complete answer: the output was cut off)")
393
+ break
394
+ if not msg.tool_calls: # no tool call: require a nonempty final answer
395
+ text = (msg.content or "").strip()
396
+ if not text:
397
+ print("(no complete answer: the output was empty)")
398
+ else:
399
+ print(text)
400
+ break
401
+ for call in msg.tool_calls:
402
+ args = call.function.arguments
403
+ if call.function.name != "get_fluid_properties":
404
+ result = {"error": "unknown tool: " + call.function.name}
405
+ else:
406
+ try:
407
+ args = json.loads(args or "{}")
408
+ result = get_fluid_properties(**args)
409
+ except (json.JSONDecodeError, TypeError) as exc:
410
+ result = {"error": "invalid tool arguments: " + str(exc)}
411
+ print("[tool]", call.function.name, args, "->", result)
412
+ messages.append({"role": "tool", "tool_call_id": call.id, "content": json.dumps(result)})
413
+ else:
414
+ print("(reached the limit of 8 requests without a final answer)")
415
+ ```
416
+
417
+ ## License
418
+
419
+ Apex-35B-V1.0, including its model weights, code examples, and documentation, is licensed under the [Apache License 2.0](https://huggingface.co/Apexintelligence-AI/Apex-35B-V1.0/blob/main/LICENSE).
420
+
421
+ ## Contact
422
+
423
+ If you have any questions, please reach out at [contact@apexin.ai](mailto:contact@apexin.ai).
assets/apex-intelligence-logo-dark.svg ADDED
assets/apex-intelligence-logo.png ADDED

Git LFS Details

  • SHA256: 3a691c1bec9b49a53ffceb573e401a9401e496e5130b9e189debb322daac1676
  • Pointer size: 131 Bytes
  • Size of remote file: 295 kB
assets/evaluation-overview.png ADDED

Git LFS Details

  • SHA256: 2012527221f39b64e6afdec9d0455ec4e555a4d8e4f7ba4f5aa7ddae843d34ef
  • Pointer size: 131 Bytes
  • Size of remote file: 362 kB
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>' }}
153
+ {%- endif %}
154
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 248056,
6
+ "model_type": "qwen3_5_moe",
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attn_output_gate": true,
11
+ "bos_token_id": 248044,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 248044,
14
+ "full_attention_interval": 4,
15
+ "head_dim": 256,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 2048,
18
+ "initializer_range": 0.02,
19
+ "layer_types": [
20
+ "linear_attention",
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "full_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "full_attention",
56
+ "linear_attention",
57
+ "linear_attention",
58
+ "linear_attention",
59
+ "full_attention"
60
+ ],
61
+ "linear_conv_kernel_dim": 4,
62
+ "linear_key_head_dim": 128,
63
+ "linear_num_key_heads": 16,
64
+ "linear_num_value_heads": 32,
65
+ "linear_value_head_dim": 128,
66
+ "mamba_ssm_dtype": "float32",
67
+ "max_position_embeddings": 262144,
68
+ "model_type": "qwen3_5_moe_text",
69
+ "moe_intermediate_size": 512,
70
+ "mtp_num_hidden_layers": 1,
71
+ "mtp_use_dedicated_embeddings": false,
72
+ "num_attention_heads": 16,
73
+ "num_experts": 256,
74
+ "num_experts_per_tok": 8,
75
+ "num_hidden_layers": 40,
76
+ "num_key_value_heads": 2,
77
+ "output_router_logits": false,
78
+ "pad_token_id": null,
79
+ "partial_rotary_factor": 0.25,
80
+ "rms_norm_eps": 1e-06,
81
+ "rope_parameters": {
82
+ "mrope_interleaved": true,
83
+ "mrope_section": [
84
+ 11,
85
+ 11,
86
+ 10
87
+ ],
88
+ "partial_rotary_factor": 0.25,
89
+ "rope_theta": 10000000,
90
+ "rope_type": "default"
91
+ },
92
+ "router_aux_loss_coef": 0.001,
93
+ "shared_expert_intermediate_size": 512,
94
+ "tie_word_embeddings": false,
95
+ "use_cache": true,
96
+ "vocab_size": 248320
97
+ },
98
+ "tie_word_embeddings": false,
99
+ "transformers_version": "5.8.1",
100
+ "video_token_id": 248057,
101
+ "vision_config": {
102
+ "deepstack_visual_indexes": [],
103
+ "depth": 27,
104
+ "hidden_act": "gelu_pytorch_tanh",
105
+ "hidden_size": 1152,
106
+ "in_channels": 3,
107
+ "initializer_range": 0.02,
108
+ "intermediate_size": 4304,
109
+ "model_type": "qwen3_5_moe_vision",
110
+ "num_heads": 16,
111
+ "num_position_embeddings": 2304,
112
+ "out_hidden_size": 2048,
113
+ "patch_size": 16,
114
+ "spatial_merge_size": 2,
115
+ "temporal_patch_size": 2
116
+ },
117
+ "vision_end_token_id": 248054,
118
+ "vision_start_token_id": 248053
119
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.8.1",
13
+ "trust_remote_code": true
14
+ }
model-00001-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c011bb5f799f23cdef47df594482658dd740ae1fa8ac22c1d3c217a62a1b31f
3
+ size 3996199680
model-00002-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99368924df1c95660c50b72dc823df6ea8489d748a4cd4983db1dff9c23ed99c
3
+ size 1284907672
model-00003-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35850acf20d8d8ec149b5f3171d89d3655f11e938cf36d2ee6aafe4f2082a5c9
3
+ size 3357898328
model-00004-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28adc9a178997a45d4f712fe3e8034c78fd3979793fdef4199490e09b5b8a6ab
3
+ size 3370808680
model-00005-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1b6c79ea4aef1926440b39782dcd18d9ced40fed7963da73c8c7b222d05713
3
+ size 3357898328
model-00006-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75119540d12356de40497d34c86ef90fd58c9ee36028e796389c7a363b07ed97
3
+ size 3959424872
model-00007-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47713f8237dba861981935e5a21d0826758c6ef1650632e952942bf110f485d0
3
+ size 1096788200
model-00008-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b3a3e9f33dc639d0a02083472e190a2fa63693fdb2940a813a0c6f2fad5cfc5
3
+ size 3946841976
model-00009-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f5ffda6662ed9d33ee0a916f6223e80faac891c154c1887fc6529d5d1fb5ff5
3
+ size 1096460816
model-00010-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d7725e44f625255bba89ed91d99983bc1676e37c261c103017f4f383fde2bdd
3
+ size 3946841960
model-00011-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7bb150391a672d2ca44049e6f8916d51f0c46f4f1f7dffba7b1d2af1853d1f
3
+ size 1096460720
model-00012-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e782915f96b32ada5a2d78e543fa9787fef10f361b955ed715736a817661e610
3
+ size 3409971048
model-00013-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df27df450e3058d0f275f54fe22dc18ac769375edafcd791d29f1a0b3995280
3
+ size 1633331632
model-00014-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e9acd72165607051af00cdde65acf5a4197571bf055b88341af2814086c950
3
+ size 3422553840
model-00015-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb691cda4a98986b8a5efcf35501e0999186d5f5ed9e78c99bdd7f1ce39688a4
3
+ size 1633659192
model-00016-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e72940e34adce1926862f0ee4c408a896063d316d23b2ca345522552e45e9f
3
+ size 3946842104
model-00017-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81dffed7c1a33333ab7903c5522c0efdd4545758676f60042e676b8cded97aa3
3
+ size 1096460576
model-00018-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7c680fbb6a0ce8688e47b87761cd269974b70b26329c270a9cd51639ef6979d
3
+ size 3946841960
model-00019-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052d4d4d02394bf295c5fa962cb2c4cf3b9c0b2c8ad6b108f7efca1ed10270ec
3
+ size 1096460776
model-00020-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a2574a36ad84f979f0ecab1ba3ee0e934ff925a82661183dea983f3d1acd075
3
+ size 3409971040
model-00021-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd9df11165b54120dec125bbdd3f778a7ea3659483ead43dc13004df3c2fc334
3
+ size 1633331712
model-00022-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d37c80c24fcc3377ef05613ea79790e94ea73f1f43d0e76f8878908e98252df
3
+ size 3370808720
model-00023-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77778394cfc876bb81435ab89bdacdb84945a4671dc7a5f2ec792dcea9926516
3
+ size 3357898360
model-00024-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a87010ad7c50bee594f03cff0de900454bc54a2bebce0ab9fdc03af13596099
3
+ size 3370808720
model-00025-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962dc99cb9a6cc272bb8836553f5e6da24da9b65995c5b15d366486db794bff7
3
+ size 3832888224
model-00026-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:062eef6449f7c606af24310b1aeda036cc1516899602e6d9e01f6639114ac9a0
3
+ size 2231416816
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "merge_size": 2,
18
+ "patch_size": 16,
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "longest_edge": 16777216,
23
+ "shortest_edge": 65536
24
+ },
25
+ "temporal_patch_size": 2
26
+ }
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982
tokenizer_config.json ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "248044": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "248045": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "248046": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "248047": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "248048": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "248049": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "248050": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "248051": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "248052": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "248053": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "248054": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "248055": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "248056": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "248057": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "248058": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "248059": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "248060": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "248061": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "248062": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "248063": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "248064": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "248065": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "248066": {
181
+ "content": "<tool_response>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "248067": {
189
+ "content": "</tool_response>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "248068": {
197
+ "content": "<think>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "248069": {
205
+ "content": "</think>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "248070": {
213
+ "content": "<|audio_start|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "248071": {
221
+ "content": "<|audio_end|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "248072": {
229
+ "content": "<tts_pad>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "248073": {
237
+ "content": "<tts_text_bos>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "248074": {
245
+ "content": "<tts_text_eod>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "248075": {
253
+ "content": "<tts_text_bos_single>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "248076": {
261
+ "content": "<|audio_pad|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ }
268
+ },
269
+ "additional_special_tokens": [
270
+ "<|im_start|>",
271
+ "<|im_end|>",
272
+ "<|object_ref_start|>",
273
+ "<|object_ref_end|>",
274
+ "<|box_start|>",
275
+ "<|box_end|>",
276
+ "<|quad_start|>",
277
+ "<|quad_end|>",
278
+ "<|vision_start|>",
279
+ "<|vision_end|>",
280
+ "<|vision_pad|>",
281
+ "<|image_pad|>",
282
+ "<|video_pad|>"
283
+ ],
284
+ "bos_token": null,
285
+ "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>' }}\n {%- endif %}\n{%- endif %}",
286
+ "clean_up_tokenization_spaces": false,
287
+ "eos_token": "<|im_end|>",
288
+ "errors": "replace",
289
+ "model_max_length": 262144,
290
+ "pad_token": "<|endoftext|>",
291
+ "split_special_tokens": false,
292
+ "tokenizer_class": "TokenizersBackend",
293
+ "unk_token": null,
294
+ "add_bos_token": false,
295
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
296
+ "extra_special_tokens": {
297
+ "audio_bos_token": "<|audio_start|>",
298
+ "audio_eos_token": "<|audio_end|>",
299
+ "audio_token": "<|audio_pad|>",
300
+ "image_token": "<|image_pad|>",
301
+ "video_token": "<|video_pad|>",
302
+ "vision_bos_token": "<|vision_start|>",
303
+ "vision_eos_token": "<|vision_end|>"
304
+ }
305
+ }