Javier commited on
Javi0.3 release
Browse files- .gitattributes +2 -0
- LICENSE +202 -0
- README.md +155 -0
- chat_template.jinja +154 -0
- config.json +98 -0
- generation_config.json +13 -0
- javi03-cover.png +3 -0
- merges.txt +0 -0
- model.safetensors-00001-of-00001.safetensors +3 -0
- model.safetensors.index.json +639 -0
- preprocessor_config.json +21 -0
- processor_config.json +60 -0
- tokenizer.json +3 -0
- tokenizer_config.json +300 -0
- video_preprocessor_config.json +21 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
javi03-cover.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
CHANGED
|
@@ -1,3 +1,158 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model: Qwen/Qwen3.5-2B
|
| 6 |
+
base_model_relation: finetune
|
| 7 |
+
pipeline_tag: image-text-to-text
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- unsloth
|
| 11 |
+
- lora
|
| 12 |
+
- qwen3.5
|
| 13 |
+
- tool-use
|
| 14 |
+
- agent
|
| 15 |
+
- distillation
|
| 16 |
+
- dgx-spark
|
| 17 |
---
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
# Javi0.3-2B
|
| 22 |
+
|
| 23 |
+
The tiny Javi: a 2B agent model trained to think from first principles and use its tools effectively to find the answer to your prompt, or, when the tools can't get there, to guide you to it. It's trained to never guess: if it can't verify something or doesn't know, it says so. When a tool fails, it works out why and takes another route instead of looping. Fine-tuned from [Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) to work inside coding and research agents ([grok build](https://x.ai), [omp](https://www.npmjs.com/package/@oh-my-pi/pi-coding-agent), [opencode](https://opencode.ai)) with their own system prompts and tools.
|
| 24 |
+
|
| 25 |
+
This repo holds the merged bf16 weights. For llama.cpp or [lmswitch](https://github.com/jvr0x/lmswitch), use [Javi0.3-2B-GGUF](https://huggingface.co/jvr0x/Javi0.3-2B-GGUF). Bigger sibling: [Javi0.3-4B](https://huggingface.co/jvr0x/Javi0.3-4B).
|
| 26 |
+
|
| 27 |
+
What it does, all measured in [Results](#results):
|
| 28 |
+
|
| 29 |
+
- **Beats its base model clearly.** Core pass 0.35 vs 0.23 for base Qwen3.5-2B (+0.12, 95% interval +0.08 to +0.17), and 0.35 vs 0.17 for Javi0.2, a model twice its size.
|
| 30 |
+
- **Always looks up time-sensitive questions.** It answered one from memory in 1% of cases (base: 36%).
|
| 31 |
+
- **Short, grounded answers.** 378 characters on average (base: 724).
|
| 32 |
+
- **Rarely invents links.** 1.7% of answers cite a link no tool returned, counting bare ones without `https://` (base: 3.0%).
|
| 33 |
+
- **Doesn't loop.** It repeats an identical call in 4% of tasks (base: 17%).
|
| 34 |
+
|
| 35 |
+
## Files
|
| 36 |
+
|
| 37 |
+
The merged model in bf16 safetensors (one shard, 4.5 GB), with the base model's tokenizer, processor files and chat template. The LoRA touched the language model only; the vision tower is the base model's, unchanged, and Javi was never trained or evaluated on images.
|
| 38 |
+
|
| 39 |
+
## Run it
|
| 40 |
+
|
| 41 |
+
Javi was trained and evaluated with thinking off. Send `"chat_template_kwargs": {"enable_thinking": false}` with each request, and use a low temperature (0.2, top-p 0.8, top-k 20) so tool calls stay well formed.
|
| 42 |
+
|
| 43 |
+
**vLLM**
|
| 44 |
+
|
| 45 |
+
```bash
|
| 46 |
+
vllm serve jvr0x/Javi0.3-2B --max-model-len 131072 \
|
| 47 |
+
--reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
+
Add `--language-model-only` to skip the vision tower and save memory.
|
| 51 |
+
|
| 52 |
+
**SGLang**
|
| 53 |
+
|
| 54 |
+
```bash
|
| 55 |
+
python -m sglang.launch_server --model-path jvr0x/Javi0.3-2B --context-length 131072 \
|
| 56 |
+
--reasoning-parser qwen3 --tool-call-parser qwen3_coder
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
Then point any OpenAI-compatible agent at the server. Javi is built for agents with tools (web search, page fetch, a shell). In a plain chat with no tools it answers from what it knows and tells you when a question needs a lookup.
|
| 60 |
+
|
| 61 |
+
**Transformers**
|
| 62 |
+
|
| 63 |
+
```python
|
| 64 |
+
from transformers import AutoModelForImageTextToText, AutoProcessor
|
| 65 |
+
|
| 66 |
+
model_id = "jvr0x/Javi0.3-2B"
|
| 67 |
+
processor = AutoProcessor.from_pretrained(model_id)
|
| 68 |
+
model = AutoModelForImageTextToText.from_pretrained(model_id, dtype="auto", device_map="auto")
|
| 69 |
+
|
| 70 |
+
tools = [{"type": "function", "function": {
|
| 71 |
+
"name": "web_search", "description": "Search the web.",
|
| 72 |
+
"parameters": {"type": "object", "properties": {"query": {"type": "string"}}, "required": ["query"]}}}]
|
| 73 |
+
messages = [{"role": "user", "content": [{"type": "text", "text": "What's the latest stable Rust release?"}]}]
|
| 74 |
+
|
| 75 |
+
inputs = processor.apply_chat_template(messages, tools=tools, add_generation_prompt=True, enable_thinking=False,
|
| 76 |
+
tokenize=True, return_dict=True, return_tensors="pt").to(model.device)
|
| 77 |
+
out = model.generate(**inputs, max_new_tokens=512, do_sample=True, temperature=0.2, top_p=0.8, top_k=20)
|
| 78 |
+
print(processor.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
|
| 79 |
+
```
|
| 80 |
+
|
| 81 |
+
With a search tool available it should answer with a `web_search` call rather than a version from memory; run the tool, append the result as a `tool` message, and generate again.
|
| 82 |
+
|
| 83 |
+
## Results
|
| 84 |
+
|
| 85 |
+
**Eval v3:** 175 held-out questions, each run 3 times inside real client formats (grok, omp, opencode, a bare OpenAI format and a plain chat) with tools: web search (frozen cache and pinned date, so runs compare), page fetches, and a sandboxed shell over small code projects. Some questions force tool failures. Two judges grade every answer, DeepSeek-V4.1-Flash and MiMo-V2.6-Flash. **Core pass** means grounded (2/2), honest (2/2), the task at least partly solved, and no `https://` link that no tool returned (checked from the transcript, not by the judge). The eval ran the Q8_0 GGUF of these weights.
|
| 86 |
+
|
| 87 |
+
| Core pass | Base Qwen3.5-2B | Javi0.2-4B | **Javi0.3-2B** |
|
| 88 |
+
|---|---|---|---|
|
| 89 |
+
| Both judges | 0.23 | 0.17 | **0.35** |
|
| 90 |
+
| DeepSeek-V4.1-Flash | 0.26 | 0.21 | 0.48 |
|
| 91 |
+
| MiMo-V2.6-Flash | 0.20 | 0.13 | 0.23 |
|
| 92 |
+
|
| 93 |
+
Against the base model, Javi0.3-2B is ahead by 0.12, with a 95% interval of +0.08 to +0.17.
|
| 94 |
+
|
| 95 |
+
**Behavior**, counted from all 525 transcripts:
|
| 96 |
+
|
| 97 |
+
| | Base Qwen3.5-2B | **Javi0.3-2B** |
|
| 98 |
+
|---|---|---|
|
| 99 |
+
| Finished | 85% | 98% |
|
| 100 |
+
| Answered a time-sensitive question without a tool | 36% | 1% |
|
| 101 |
+
| Cited a link no tool returned, with or without `https://` | 3.0% | 1.7% |
|
| 102 |
+
| Repeated an identical call | 17% | 4% |
|
| 103 |
+
| Said what failed before the next call | 27% | 76% |
|
| 104 |
+
| Recovered after a forced failure | 96% | 55% |
|
| 105 |
+
| Tool calls per task | 3.6 | 1.8 |
|
| 106 |
+
| Average answer | 724 chars | 378 chars |
|
| 107 |
+
|
| 108 |
+
**Held-out failures:** 24 more questions whose failures are types it never trained on (429 rate limits, timeouts), 3 runs each.
|
| 109 |
+
|
| 110 |
+
| | Base Qwen3.5-2B | **Javi0.3-2B** |
|
| 111 |
+
|---|---|---|
|
| 112 |
+
| Core pass | 0.06 | 0.33 |
|
| 113 |
+
| Recovered | 75% | 56% |
|
| 114 |
+
| Repeated an identical call | 42% | 4% |
|
| 115 |
+
|
| 116 |
+
**By category** (core pass, Javi0.3-2B vs base): ahead on lookups (0.37 vs 0.11), unknowable questions (0.55 vs 0.28), recovery questions (0.35 vs 0.05), every route broken (0.33 vs 0.10) and false premises (0.29 vs 0.09); slightly behind on chat (0.33 vs 0.41), code (0.20 vs 0.31) and reasoning puzzles (0.70 vs 0.74).
|
| 117 |
+
|
| 118 |
+
## How it was made
|
| 119 |
+
|
| 120 |
+
**Teacher inside the harness.** [GLM-5.3-Flash](https://huggingface.co/Mia-AiLab/GLM-5.3-Flash-EXL3-4bpw-TensorFold) answered seed questions inside each client's exact format (system prompts of 15-25k tokens, 10-27 tools) with real tools: web search through a local SearXNG, page fetches, and a Docker sandbox. Its working rules were in the teacher's prompt only: reason from first principles, look up anything time-sensitive, diagnose a failed call before the next one, and when everything fails still give a labeled best answer and name where to check. Training rows keep the client's own prompt, so the student learns the behavior, not the instructions.
|
| 121 |
+
|
| 122 |
+
**Data.** Javi0.2's rows with made-up links removed, plus two rounds of recovery practice on 480 questions, each round giving every question a different failure and client: the first search or page fetch fails once (blocked, empty, 403, 404) or, in the second round, keeps failing for a third of them (offline, a route blocked for good).
|
| 123 |
+
|
| 124 |
+
**Filters.** DeepSeek-V4.1-Flash judged every episode. Code checks dropped anything unfinished, any time-sensitive answer without a tool, repeated calls, links no tool returned (with or without `https://`), and any call after a failure that didn't say what failed. A recovery stayed only if a different route worked, or if two routes failed and the answer stopped honestly.
|
| 125 |
+
|
| 126 |
+
**Concise rewrite.** The teacher rewrote every answer over 500 characters answer-first, keeping only facts a tool returned, with sources named instead of linked (median answer 646 → 357 characters). A rewrite was kept only if it was shorter, had no URL, changed no code block and added no number. This one change took the 2B from 0.24 to 0.35.
|
| 127 |
+
|
| 128 |
+
**Training: LoRA SFT with Unsloth on 1,307 rows.**
|
| 129 |
+
|
| 130 |
+
| Setting | Value |
|
| 131 |
+
|---|---|
|
| 132 |
+
| Method | LoRA on the bf16 base |
|
| 133 |
+
| Rank / alpha / dropout | 16 / 16 / 0 |
|
| 134 |
+
| Target modules | q, k, v, o, gate, up, down |
|
| 135 |
+
| Epochs / steps | 1 / 327 |
|
| 136 |
+
| Effective batch | 4 (1 × 4 grad accum) |
|
| 137 |
+
| Learning rate | 1e-4, linear decay, 3 warmup steps |
|
| 138 |
+
| Max sequence length | 73,728 tokens |
|
| 139 |
+
| Loss on | the first reply to each user message, every final answer, and the turn right after each failed tool call |
|
| 140 |
+
| Hardware / time | 1× DGX Spark (GB10), 1h40m |
|
| 141 |
+
|
| 142 |
+
**Merge:** the adapter was merged into the bf16 base with Unsloth.
|
| 143 |
+
|
| 144 |
+
The story of every round, including each way it broke along the way, is on X: [@jvr0x](https://x.com/jvr0x).
|
| 145 |
+
|
| 146 |
+
## Limitations
|
| 147 |
+
|
| 148 |
+
- **Recovery after a failure is 55%** (base: 96%). It doesn't give up, but its second route often fails too.
|
| 149 |
+
- **It's a 2B model.** It misreads tool results more often than the 4B, and it is weaker on code and reasoning puzzles than its base.
|
| 150 |
+
- The later 4B recipe (search-first routes, a de-hedge pass) did not help at 2B, so this is the earlier, concise-only recipe.
|
| 151 |
+
- **Images:** the vision tower is untouched and untested with Javi's training.
|
| 152 |
+
- It's built for agent clients with tools. Without tools it can't look anything up.
|
| 153 |
+
- The judges are LLMs, not people, and they disagree on some answers (Cohen's kappa 0.56).
|
| 154 |
+
- Trained mostly on English.
|
| 155 |
+
|
| 156 |
+
## License
|
| 157 |
+
|
| 158 |
+
Apache 2.0, inherited from [Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B).
|
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 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 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 true %}
|
| 150 |
+
{{- '<think>\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 248056,
|
| 6 |
+
"model_type": "qwen3_5",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"attn_output_gate": true,
|
| 11 |
+
"bos_token_id": null,
|
| 12 |
+
"torch_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 |
+
"intermediate_size": 6144,
|
| 20 |
+
"layer_types": [
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention"
|
| 45 |
+
],
|
| 46 |
+
"linear_conv_kernel_dim": 4,
|
| 47 |
+
"linear_key_head_dim": 128,
|
| 48 |
+
"linear_num_key_heads": 16,
|
| 49 |
+
"linear_num_value_heads": 16,
|
| 50 |
+
"linear_value_head_dim": 128,
|
| 51 |
+
"mamba_ssm_dtype": "float32",
|
| 52 |
+
"max_position_embeddings": 262144,
|
| 53 |
+
"mlp_only_layers": [],
|
| 54 |
+
"model_type": "qwen3_5_text",
|
| 55 |
+
"mtp_num_hidden_layers": 1,
|
| 56 |
+
"mtp_use_dedicated_embeddings": false,
|
| 57 |
+
"num_attention_heads": 8,
|
| 58 |
+
"num_hidden_layers": 24,
|
| 59 |
+
"num_key_value_heads": 2,
|
| 60 |
+
"pad_token_id": null,
|
| 61 |
+
"partial_rotary_factor": 0.25,
|
| 62 |
+
"rms_norm_eps": 1e-06,
|
| 63 |
+
"rope_parameters": {
|
| 64 |
+
"mrope_interleaved": true,
|
| 65 |
+
"mrope_section": [
|
| 66 |
+
11,
|
| 67 |
+
11,
|
| 68 |
+
10
|
| 69 |
+
],
|
| 70 |
+
"partial_rotary_factor": 0.25,
|
| 71 |
+
"rope_theta": 10000000,
|
| 72 |
+
"rope_type": "default"
|
| 73 |
+
},
|
| 74 |
+
"tie_word_embeddings": true,
|
| 75 |
+
"use_cache": true,
|
| 76 |
+
"vocab_size": 248320
|
| 77 |
+
},
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"video_token_id": 248057,
|
| 80 |
+
"vision_config": {
|
| 81 |
+
"deepstack_visual_indexes": [],
|
| 82 |
+
"depth": 24,
|
| 83 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 84 |
+
"hidden_size": 1024,
|
| 85 |
+
"in_channels": 3,
|
| 86 |
+
"initializer_range": 0.02,
|
| 87 |
+
"intermediate_size": 4096,
|
| 88 |
+
"model_type": "qwen3_5",
|
| 89 |
+
"num_heads": 16,
|
| 90 |
+
"num_position_embeddings": 2304,
|
| 91 |
+
"out_hidden_size": 2048,
|
| 92 |
+
"patch_size": 16,
|
| 93 |
+
"spatial_merge_size": 2,
|
| 94 |
+
"temporal_patch_size": 2
|
| 95 |
+
},
|
| 96 |
+
"vision_end_token_id": 248054,
|
| 97 |
+
"vision_start_token_id": 248053
|
| 98 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248046,
|
| 5 |
+
248044
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 248044,
|
| 8 |
+
"temperature": 0.2,
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.8,
|
| 11 |
+
"transformers_version": "5.5.0",
|
| 12 |
+
"use_cache": true
|
| 13 |
+
}
|
javi03-cover.png
ADDED
|
Git LFS Details
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors-00001-of-00001.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c886decdf0d52732a2dbb7846a392bd87d840311662ba91ede86e386dfffaad2
|
| 3 |
+
size 4548221488
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,639 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 4548144832
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.language_model.embed_tokens.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 7 |
+
"model.visual.merger.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 8 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 9 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 10 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 11 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 12 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 13 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 14 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 15 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 16 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 17 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 18 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 19 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 20 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 21 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 22 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 23 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 24 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 25 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 26 |
+
"mtp.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 27 |
+
"mtp.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 28 |
+
"mtp.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 29 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 30 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 31 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 32 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 33 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 34 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 35 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 36 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 37 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 38 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 39 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 40 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 41 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 42 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 43 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 44 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 45 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 46 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 47 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 48 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 49 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 50 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 51 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 52 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 53 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 54 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 55 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 56 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 57 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 58 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 59 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 60 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 61 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 62 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 63 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 64 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 66 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 67 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 68 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 69 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 70 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 71 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 72 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 73 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 74 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 75 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 76 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 77 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 78 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 79 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 80 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 81 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 82 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 83 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 84 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 85 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 86 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 87 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 88 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 89 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 90 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 91 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 92 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 93 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 94 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 95 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 96 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 97 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 98 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 99 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 100 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 101 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 102 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 103 |
+
"mtp.fc.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 104 |
+
"mtp.layers.0.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 105 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 106 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 107 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 108 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 109 |
+
"model.visual.merger.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 110 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 111 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 112 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 113 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 114 |
+
"mtp.layers.0.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 115 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 116 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 117 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 118 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 119 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 120 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 121 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 122 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 123 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 124 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 125 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 126 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 127 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 128 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 129 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 130 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 131 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 132 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 133 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 134 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 135 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 136 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 137 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 138 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 139 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 140 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 141 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 142 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 143 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 144 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 145 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 146 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 147 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 148 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 149 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 150 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 151 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 152 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 153 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 154 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 155 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 156 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 157 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 158 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 159 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 160 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 161 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 162 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 163 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 164 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 165 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 166 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 167 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 168 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 169 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 170 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 171 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 172 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 173 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 174 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 175 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 176 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 177 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 178 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 179 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 180 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 181 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 182 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 183 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 184 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 185 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 186 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 187 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 188 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 189 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 190 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 191 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 192 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 193 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 194 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 195 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 196 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 197 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 198 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 199 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 200 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 201 |
+
"model.visual.blocks.0.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 202 |
+
"model.visual.blocks.1.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 203 |
+
"model.visual.blocks.10.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 204 |
+
"model.visual.blocks.11.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 205 |
+
"model.visual.blocks.12.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 206 |
+
"model.visual.blocks.13.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 207 |
+
"model.visual.blocks.14.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 208 |
+
"model.visual.blocks.15.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 209 |
+
"model.visual.blocks.16.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 210 |
+
"model.visual.blocks.17.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 211 |
+
"model.visual.blocks.18.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 212 |
+
"model.visual.blocks.19.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 213 |
+
"model.visual.blocks.2.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 214 |
+
"model.visual.blocks.20.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 215 |
+
"model.visual.blocks.21.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 216 |
+
"model.visual.blocks.22.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 217 |
+
"model.visual.blocks.23.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 218 |
+
"model.visual.blocks.3.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 219 |
+
"model.visual.blocks.4.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 220 |
+
"model.visual.blocks.5.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 221 |
+
"model.visual.blocks.6.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 222 |
+
"model.visual.blocks.7.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 223 |
+
"model.visual.blocks.8.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 224 |
+
"model.visual.blocks.9.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 225 |
+
"model.visual.pos_embed.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 226 |
+
"model.visual.patch_embed.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 227 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 228 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 229 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 230 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 231 |
+
"mtp.layers.0.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 232 |
+
"mtp.layers.0.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 233 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 234 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 235 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 236 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 237 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 238 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 239 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 240 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 241 |
+
"model.visual.blocks.0.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 242 |
+
"model.visual.blocks.1.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 243 |
+
"model.visual.blocks.10.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 244 |
+
"model.visual.blocks.11.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 245 |
+
"model.visual.blocks.12.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 246 |
+
"model.visual.blocks.13.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 247 |
+
"model.visual.blocks.14.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 248 |
+
"model.visual.blocks.15.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 249 |
+
"model.visual.blocks.16.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 250 |
+
"model.visual.blocks.17.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 251 |
+
"model.visual.blocks.18.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 252 |
+
"model.visual.blocks.19.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 253 |
+
"model.visual.blocks.2.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 254 |
+
"model.visual.blocks.20.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 255 |
+
"model.visual.blocks.21.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 256 |
+
"model.visual.blocks.22.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 257 |
+
"model.visual.blocks.23.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 258 |
+
"model.visual.blocks.3.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 259 |
+
"model.visual.blocks.4.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 260 |
+
"model.visual.blocks.5.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 261 |
+
"model.visual.blocks.6.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 262 |
+
"model.visual.blocks.7.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 263 |
+
"model.visual.blocks.8.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 264 |
+
"model.visual.blocks.9.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 265 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 266 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 267 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 268 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 269 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 270 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 271 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 272 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 273 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 274 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 275 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 276 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 277 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 278 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 279 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 280 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 281 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 282 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 283 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 284 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 285 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 286 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 287 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 288 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 289 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 290 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 291 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 292 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 293 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 294 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 295 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 296 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 297 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 298 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 299 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 300 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 301 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 302 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 303 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 304 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 305 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 306 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 307 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 308 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 309 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 310 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 311 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 312 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 313 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 314 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 315 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 316 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 317 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 318 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 319 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 320 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 321 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 322 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 323 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 324 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 325 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 326 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 327 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 328 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 329 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 330 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 331 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 332 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 333 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 334 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 335 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 336 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 337 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 338 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 339 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 340 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 341 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 342 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 343 |
+
"model.visual.merger.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 344 |
+
"model.visual.blocks.0.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 345 |
+
"model.visual.blocks.1.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 346 |
+
"model.visual.blocks.10.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 347 |
+
"model.visual.blocks.11.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 348 |
+
"model.visual.blocks.12.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 349 |
+
"model.visual.blocks.13.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 350 |
+
"model.visual.blocks.14.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 351 |
+
"model.visual.blocks.15.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 352 |
+
"model.visual.blocks.16.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 353 |
+
"model.visual.blocks.17.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 354 |
+
"model.visual.blocks.18.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 355 |
+
"model.visual.blocks.19.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 356 |
+
"model.visual.blocks.2.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 357 |
+
"model.visual.blocks.20.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 358 |
+
"model.visual.blocks.21.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 359 |
+
"model.visual.blocks.22.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 360 |
+
"model.visual.blocks.23.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 361 |
+
"model.visual.blocks.3.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 362 |
+
"model.visual.blocks.4.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 363 |
+
"model.visual.blocks.5.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 364 |
+
"model.visual.blocks.6.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 365 |
+
"model.visual.blocks.7.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 366 |
+
"model.visual.blocks.8.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 367 |
+
"model.visual.blocks.9.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 368 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 369 |
+
"model.language_model.layers.23.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 370 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 371 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 372 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 373 |
+
"model.language_model.layers.7.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 374 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 375 |
+
"model.language_model.layers.8.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 376 |
+
"mtp.layers.0.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 377 |
+
"mtp.layers.0.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 378 |
+
"mtp.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 379 |
+
"mtp.pre_fc_norm_embedding.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 380 |
+
"mtp.pre_fc_norm_hidden.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 381 |
+
"model.language_model.layers.11.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 382 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 383 |
+
"model.language_model.layers.12.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 384 |
+
"model.language_model.layers.3.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 385 |
+
"model.language_model.layers.4.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 386 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 387 |
+
"model.language_model.layers.14.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 388 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 389 |
+
"model.language_model.layers.15.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 390 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 391 |
+
"model.language_model.layers.20.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 392 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 393 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 394 |
+
"model.language_model.layers.18.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 395 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 396 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 397 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 398 |
+
"model.language_model.layers.13.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 399 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 400 |
+
"model.language_model.layers.19.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 401 |
+
"model.language_model.layers.2.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 402 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 403 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 404 |
+
"model.language_model.layers.10.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 405 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 406 |
+
"model.language_model.layers.16.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 407 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 408 |
+
"model.language_model.layers.17.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 409 |
+
"model.language_model.layers.5.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 410 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 411 |
+
"model.language_model.layers.6.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 412 |
+
"model.language_model.layers.21.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 413 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 414 |
+
"model.language_model.layers.22.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 415 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 416 |
+
"model.language_model.layers.9.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 417 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 418 |
+
"model.language_model.layers.0.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 419 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 420 |
+
"model.language_model.layers.1.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 421 |
+
"model.language_model.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 422 |
+
"model.visual.merger.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 423 |
+
"model.visual.blocks.0.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 424 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 425 |
+
"model.visual.blocks.0.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 426 |
+
"model.visual.blocks.0.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 427 |
+
"model.visual.blocks.0.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 428 |
+
"model.visual.blocks.0.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 429 |
+
"model.visual.blocks.1.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 430 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 431 |
+
"model.visual.blocks.1.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 432 |
+
"model.visual.blocks.1.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 433 |
+
"model.visual.blocks.1.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 434 |
+
"model.visual.blocks.1.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 435 |
+
"model.visual.blocks.10.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 437 |
+
"model.visual.blocks.10.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 441 |
+
"model.visual.blocks.11.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 442 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 443 |
+
"model.visual.blocks.11.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 444 |
+
"model.visual.blocks.11.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 445 |
+
"model.visual.blocks.11.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 446 |
+
"model.visual.blocks.11.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 447 |
+
"model.visual.blocks.12.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 448 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 449 |
+
"model.visual.blocks.12.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 450 |
+
"model.visual.blocks.12.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 451 |
+
"model.visual.blocks.12.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 452 |
+
"model.visual.blocks.12.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 453 |
+
"model.visual.blocks.13.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 454 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 455 |
+
"model.visual.blocks.13.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 456 |
+
"model.visual.blocks.13.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 457 |
+
"model.visual.blocks.13.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 458 |
+
"model.visual.blocks.13.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 459 |
+
"model.visual.blocks.14.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 460 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 461 |
+
"model.visual.blocks.14.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 462 |
+
"model.visual.blocks.14.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 463 |
+
"model.visual.blocks.14.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 464 |
+
"model.visual.blocks.14.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 465 |
+
"model.visual.blocks.15.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 466 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 467 |
+
"model.visual.blocks.15.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 468 |
+
"model.visual.blocks.15.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 469 |
+
"model.visual.blocks.15.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 470 |
+
"model.visual.blocks.15.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 471 |
+
"model.visual.blocks.16.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 472 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 473 |
+
"model.visual.blocks.16.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 474 |
+
"model.visual.blocks.16.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 475 |
+
"model.visual.blocks.16.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 476 |
+
"model.visual.blocks.16.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 477 |
+
"model.visual.blocks.17.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 478 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 479 |
+
"model.visual.blocks.17.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 480 |
+
"model.visual.blocks.17.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 481 |
+
"model.visual.blocks.17.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 482 |
+
"model.visual.blocks.17.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 483 |
+
"model.visual.blocks.18.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 484 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 485 |
+
"model.visual.blocks.18.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 486 |
+
"model.visual.blocks.18.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 487 |
+
"model.visual.blocks.18.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 488 |
+
"model.visual.blocks.18.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 489 |
+
"model.visual.blocks.19.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 490 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 491 |
+
"model.visual.blocks.19.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 492 |
+
"model.visual.blocks.19.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 493 |
+
"model.visual.blocks.19.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 494 |
+
"model.visual.blocks.19.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 495 |
+
"model.visual.blocks.2.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 496 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 497 |
+
"model.visual.blocks.2.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 498 |
+
"model.visual.blocks.2.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 499 |
+
"model.visual.blocks.2.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 500 |
+
"model.visual.blocks.2.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 501 |
+
"model.visual.blocks.20.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 502 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 503 |
+
"model.visual.blocks.20.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 504 |
+
"model.visual.blocks.20.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 505 |
+
"model.visual.blocks.20.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 506 |
+
"model.visual.blocks.20.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 507 |
+
"model.visual.blocks.21.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 508 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 509 |
+
"model.visual.blocks.21.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 510 |
+
"model.visual.blocks.21.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 511 |
+
"model.visual.blocks.21.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 512 |
+
"model.visual.blocks.21.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 513 |
+
"model.visual.blocks.22.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 514 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 515 |
+
"model.visual.blocks.22.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 516 |
+
"model.visual.blocks.22.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 517 |
+
"model.visual.blocks.22.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 518 |
+
"model.visual.blocks.22.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 519 |
+
"model.visual.blocks.23.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 520 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 521 |
+
"model.visual.blocks.23.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 522 |
+
"model.visual.blocks.23.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 523 |
+
"model.visual.blocks.23.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 524 |
+
"model.visual.blocks.23.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 525 |
+
"model.visual.blocks.3.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 526 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 527 |
+
"model.visual.blocks.3.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 528 |
+
"model.visual.blocks.3.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 529 |
+
"model.visual.blocks.3.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 530 |
+
"model.visual.blocks.3.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 531 |
+
"model.visual.blocks.4.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 532 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 533 |
+
"model.visual.blocks.4.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 534 |
+
"model.visual.blocks.4.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 535 |
+
"model.visual.blocks.4.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 536 |
+
"model.visual.blocks.4.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 537 |
+
"model.visual.blocks.5.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 538 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 539 |
+
"model.visual.blocks.5.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 540 |
+
"model.visual.blocks.5.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 541 |
+
"model.visual.blocks.5.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 542 |
+
"model.visual.blocks.5.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 543 |
+
"model.visual.blocks.6.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 544 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 545 |
+
"model.visual.blocks.6.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 546 |
+
"model.visual.blocks.6.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 547 |
+
"model.visual.blocks.6.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 548 |
+
"model.visual.blocks.6.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 549 |
+
"model.visual.blocks.7.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 550 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 551 |
+
"model.visual.blocks.7.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 552 |
+
"model.visual.blocks.7.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 553 |
+
"model.visual.blocks.7.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 554 |
+
"model.visual.blocks.7.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 555 |
+
"model.visual.blocks.8.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 556 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 557 |
+
"model.visual.blocks.8.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 558 |
+
"model.visual.blocks.8.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 559 |
+
"model.visual.blocks.8.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 560 |
+
"model.visual.blocks.8.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 561 |
+
"model.visual.blocks.9.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 562 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 563 |
+
"model.visual.blocks.9.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 564 |
+
"model.visual.blocks.9.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 565 |
+
"model.visual.blocks.9.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 566 |
+
"model.visual.blocks.9.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 567 |
+
"model.visual.merger.norm.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 568 |
+
"model.visual.merger.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 569 |
+
"model.visual.patch_embed.proj.bias": "model.safetensors-00001-of-00001.safetensors",
|
| 570 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 571 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 572 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 573 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 574 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 575 |
+
"mtp.layers.0.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 576 |
+
"mtp.layers.0.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 577 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 578 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 579 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 580 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 581 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 582 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 583 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 584 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 585 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 586 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 587 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 588 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 589 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 590 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 591 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 592 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 593 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 594 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 595 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 596 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 597 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 598 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 599 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 600 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 601 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
|
| 602 |
+
"model.language_model.layers.8.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 603 |
+
"model.language_model.layers.12.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 604 |
+
"model.language_model.layers.4.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 605 |
+
"model.language_model.layers.5.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 606 |
+
"model.language_model.layers.16.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 607 |
+
"model.language_model.layers.20.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 608 |
+
"model.language_model.layers.21.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 609 |
+
"model.language_model.layers.18.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 610 |
+
"model.language_model.layers.13.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 611 |
+
"model.language_model.layers.14.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 612 |
+
"model.language_model.layers.2.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 613 |
+
"model.language_model.layers.10.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 614 |
+
"model.language_model.layers.17.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 615 |
+
"model.language_model.layers.6.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 616 |
+
"model.language_model.layers.22.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 617 |
+
"model.language_model.layers.9.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 618 |
+
"model.language_model.layers.0.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 619 |
+
"model.language_model.layers.1.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
|
| 620 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 621 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 622 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 623 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 624 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 625 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 626 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 627 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 628 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 629 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 630 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 631 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 632 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 633 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 634 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 635 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 636 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
|
| 637 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors"
|
| 638 |
+
}
|
| 639 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
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 sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"padding_side": "left",
|
| 25 |
+
"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+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "TokenizersBackend",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>",
|
| 33 |
+
"added_tokens_decoder": {
|
| 34 |
+
"248044": {
|
| 35 |
+
"content": "<|endoftext|>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
"248045": {
|
| 43 |
+
"content": "<|im_start|>",
|
| 44 |
+
"single_word": false,
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"special": true
|
| 49 |
+
},
|
| 50 |
+
"248046": {
|
| 51 |
+
"content": "<|im_end|>",
|
| 52 |
+
"single_word": false,
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"rstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"special": true
|
| 57 |
+
},
|
| 58 |
+
"248047": {
|
| 59 |
+
"content": "<|object_ref_start|>",
|
| 60 |
+
"single_word": false,
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"rstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"special": true
|
| 65 |
+
},
|
| 66 |
+
"248048": {
|
| 67 |
+
"content": "<|object_ref_end|>",
|
| 68 |
+
"single_word": false,
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"special": true
|
| 73 |
+
},
|
| 74 |
+
"248049": {
|
| 75 |
+
"content": "<|box_start|>",
|
| 76 |
+
"single_word": false,
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"rstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"special": true
|
| 81 |
+
},
|
| 82 |
+
"248050": {
|
| 83 |
+
"content": "<|box_end|>",
|
| 84 |
+
"single_word": false,
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"rstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"special": true
|
| 89 |
+
},
|
| 90 |
+
"248051": {
|
| 91 |
+
"content": "<|quad_start|>",
|
| 92 |
+
"single_word": false,
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"rstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"special": true
|
| 97 |
+
},
|
| 98 |
+
"248052": {
|
| 99 |
+
"content": "<|quad_end|>",
|
| 100 |
+
"single_word": false,
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"rstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"special": true
|
| 105 |
+
},
|
| 106 |
+
"248053": {
|
| 107 |
+
"content": "<|vision_start|>",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
"248054": {
|
| 115 |
+
"content": "<|vision_end|>",
|
| 116 |
+
"single_word": false,
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"rstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"special": true
|
| 121 |
+
},
|
| 122 |
+
"248055": {
|
| 123 |
+
"content": "<|vision_pad|>",
|
| 124 |
+
"single_word": false,
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"special": true
|
| 129 |
+
},
|
| 130 |
+
"248056": {
|
| 131 |
+
"content": "<|image_pad|>",
|
| 132 |
+
"single_word": false,
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"rstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"special": true
|
| 137 |
+
},
|
| 138 |
+
"248057": {
|
| 139 |
+
"content": "<|video_pad|>",
|
| 140 |
+
"single_word": false,
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"rstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"special": true
|
| 145 |
+
},
|
| 146 |
+
"248058": {
|
| 147 |
+
"content": "<tool_call>",
|
| 148 |
+
"single_word": false,
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"rstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"special": false
|
| 153 |
+
},
|
| 154 |
+
"248059": {
|
| 155 |
+
"content": "</tool_call>",
|
| 156 |
+
"single_word": false,
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"rstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"special": false
|
| 161 |
+
},
|
| 162 |
+
"248060": {
|
| 163 |
+
"content": "<|fim_prefix|>",
|
| 164 |
+
"single_word": false,
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"rstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"special": false
|
| 169 |
+
},
|
| 170 |
+
"248061": {
|
| 171 |
+
"content": "<|fim_middle|>",
|
| 172 |
+
"single_word": false,
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"rstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"special": false
|
| 177 |
+
},
|
| 178 |
+
"248062": {
|
| 179 |
+
"content": "<|fim_suffix|>",
|
| 180 |
+
"single_word": false,
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"special": false
|
| 185 |
+
},
|
| 186 |
+
"248063": {
|
| 187 |
+
"content": "<|fim_pad|>",
|
| 188 |
+
"single_word": false,
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"rstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"special": false
|
| 193 |
+
},
|
| 194 |
+
"248064": {
|
| 195 |
+
"content": "<|repo_name|>",
|
| 196 |
+
"single_word": false,
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"rstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"special": false
|
| 201 |
+
},
|
| 202 |
+
"248065": {
|
| 203 |
+
"content": "<|file_sep|>",
|
| 204 |
+
"single_word": false,
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"rstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"special": false
|
| 209 |
+
},
|
| 210 |
+
"248066": {
|
| 211 |
+
"content": "<tool_response>",
|
| 212 |
+
"single_word": false,
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"rstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"special": false
|
| 217 |
+
},
|
| 218 |
+
"248067": {
|
| 219 |
+
"content": "</tool_response>",
|
| 220 |
+
"single_word": false,
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"rstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"special": false
|
| 225 |
+
},
|
| 226 |
+
"248068": {
|
| 227 |
+
"content": "<think>",
|
| 228 |
+
"single_word": false,
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"rstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"special": false
|
| 233 |
+
},
|
| 234 |
+
"248069": {
|
| 235 |
+
"content": "</think>",
|
| 236 |
+
"single_word": false,
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"rstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"special": false
|
| 241 |
+
},
|
| 242 |
+
"248070": {
|
| 243 |
+
"content": "<|audio_start|>",
|
| 244 |
+
"single_word": false,
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"rstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"special": true
|
| 249 |
+
},
|
| 250 |
+
"248071": {
|
| 251 |
+
"content": "<|audio_end|>",
|
| 252 |
+
"single_word": false,
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"rstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"special": true
|
| 257 |
+
},
|
| 258 |
+
"248072": {
|
| 259 |
+
"content": "<tts_pad>",
|
| 260 |
+
"single_word": false,
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"rstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"special": true
|
| 265 |
+
},
|
| 266 |
+
"248073": {
|
| 267 |
+
"content": "<tts_text_bos>",
|
| 268 |
+
"single_word": false,
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"rstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"special": true
|
| 273 |
+
},
|
| 274 |
+
"248074": {
|
| 275 |
+
"content": "<tts_text_eod>",
|
| 276 |
+
"single_word": false,
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"rstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"special": true
|
| 281 |
+
},
|
| 282 |
+
"248075": {
|
| 283 |
+
"content": "<tts_text_bos_single>",
|
| 284 |
+
"single_word": false,
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"rstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"special": true
|
| 289 |
+
},
|
| 290 |
+
"248076": {
|
| 291 |
+
"content": "<|audio_pad|>",
|
| 292 |
+
"single_word": false,
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"rstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"special": true
|
| 297 |
+
}
|
| 298 |
+
},
|
| 299 |
+
"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 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\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 true %}\n {{- '<think>\\n' }}\n {%- else %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}"
|
| 300 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|