Text Generation
Transformers
Safetensors
qwen3_5_moe
image-text-to-text
mixture-of-experts
agent
research
conversational
Instructions to use Apexintelligence-AI/Apex-35B-V1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Apexintelligence-AI/Apex-35B-V1.0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Apexintelligence-AI/Apex-35B-V1.0") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Apexintelligence-AI/Apex-35B-V1.0") model = AutoModelForMultimodalLM.from_pretrained("Apexintelligence-AI/Apex-35B-V1.0", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Apexintelligence-AI/Apex-35B-V1.0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Apexintelligence-AI/Apex-35B-V1.0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Apexintelligence-AI/Apex-35B-V1.0", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Apexintelligence-AI/Apex-35B-V1.0
- SGLang
How to use Apexintelligence-AI/Apex-35B-V1.0 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Apexintelligence-AI/Apex-35B-V1.0" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Apexintelligence-AI/Apex-35B-V1.0", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Apexintelligence-AI/Apex-35B-V1.0" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Apexintelligence-AI/Apex-35B-V1.0", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Apexintelligence-AI/Apex-35B-V1.0 with Docker Model Runner:
docker model run hf.co/Apexintelligence-AI/Apex-35B-V1.0
Commit ·
3e1e8f9
0
Parent(s):
Apex-35B-V1.0
Browse files- .gitattributes +37 -0
- LICENSE +202 -0
- README.md +423 -0
- assets/apex-intelligence-logo-dark.svg +0 -0
- assets/apex-intelligence-logo.png +3 -0
- assets/evaluation-overview.png +3 -0
- chat_template.jinja +154 -0
- config.json +119 -0
- generation_config.json +14 -0
- model-00001-of-00026.safetensors +3 -0
- model-00002-of-00026.safetensors +3 -0
- model-00003-of-00026.safetensors +3 -0
- model-00004-of-00026.safetensors +3 -0
- model-00005-of-00026.safetensors +3 -0
- model-00006-of-00026.safetensors +3 -0
- model-00007-of-00026.safetensors +3 -0
- model-00008-of-00026.safetensors +3 -0
- model-00009-of-00026.safetensors +3 -0
- model-00010-of-00026.safetensors +3 -0
- model-00011-of-00026.safetensors +3 -0
- model-00012-of-00026.safetensors +3 -0
- model-00013-of-00026.safetensors +3 -0
- model-00014-of-00026.safetensors +3 -0
- model-00015-of-00026.safetensors +3 -0
- model-00016-of-00026.safetensors +3 -0
- model-00017-of-00026.safetensors +3 -0
- model-00018-of-00026.safetensors +3 -0
- model-00019-of-00026.safetensors +3 -0
- model-00020-of-00026.safetensors +3 -0
- model-00021-of-00026.safetensors +3 -0
- model-00022-of-00026.safetensors +3 -0
- model-00023-of-00026.safetensors +3 -0
- model-00024-of-00026.safetensors +3 -0
- model-00025-of-00026.safetensors +3 -0
- model-00026-of-00026.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +26 -0
- processor_config.json +60 -0
- tokenizer.json +3 -0
- tokenizer_config.json +305 -0
.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&message=Apex+Intelligence&color=2684FF&labelColor=555555&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&message=Apex-35B-V1.0&color=E5E7EB&labelColor=555555&style=flat&logo=github&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&message=Apexintelligence-AI&color=FFC107&labelColor=555555&style=flat&logo=huggingface&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&message=Apex-35B-V1.0&color=7C3AED&labelColor=555555&style=flat&logo=readme&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&message=apexin_ai&color=E5E7EB&labelColor=555555&style=flat&logo=x&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&message=Apache+2.0&color=2EA44F&labelColor=555555&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 + 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 / 0 / 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 / 2 / 44</td><td align="center" style="vertical-align: middle; text-align: center;">99 / 0 / 1</td><td align="center" style="vertical-align: middle; text-align: center;">98 / 0 / 2</td><td align="center" style="vertical-align: middle; text-align: center;">100 / 0 / 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
|
assets/evaluation-overview.png
ADDED
|
Git LFS Details
|
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 |
+
}
|