Qwen3.5-4B-RustCoder: round 5 LoRA SFT, bf16 safetensors
Browse files- .gitattributes +1 -0
- LICENSE +202 -0
- README.md +108 -0
- chat_template.jinja +154 -0
- config.json +104 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +730 -0
- preprocessor_config.json +21 -0
- tokenizer.json +3 -0
- tokenizer_config.json +305 -0
- video_preprocessor_config.json +21 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
Apache License
|
| 3 |
+
Version 2.0, January 2004
|
| 4 |
+
http://www.apache.org/licenses/
|
| 5 |
+
|
| 6 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 7 |
+
|
| 8 |
+
1. Definitions.
|
| 9 |
+
|
| 10 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 11 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 12 |
+
|
| 13 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 14 |
+
the copyright owner that is granting the License.
|
| 15 |
+
|
| 16 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 17 |
+
other entities that control, are controlled by, or are under common
|
| 18 |
+
control with that entity. For the purposes of this definition,
|
| 19 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 20 |
+
direction or management of such entity, whether by contract or
|
| 21 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 22 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 23 |
+
|
| 24 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 25 |
+
exercising permissions granted by this License.
|
| 26 |
+
|
| 27 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 28 |
+
including but not limited to software source code, documentation
|
| 29 |
+
source, and configuration files.
|
| 30 |
+
|
| 31 |
+
"Object" form shall mean any form resulting from mechanical
|
| 32 |
+
transformation or translation of a Source form, including but
|
| 33 |
+
not limited to compiled object code, generated documentation,
|
| 34 |
+
and conversions to other media types.
|
| 35 |
+
|
| 36 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 37 |
+
Object form, made available under the License, as indicated by a
|
| 38 |
+
copyright notice that is included in or attached to the work
|
| 39 |
+
(an example is provided in the Appendix below).
|
| 40 |
+
|
| 41 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 42 |
+
form, that is based on (or derived from) the Work and for which the
|
| 43 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 44 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 45 |
+
of this License, Derivative Works shall not include works that remain
|
| 46 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 47 |
+
the Work and Derivative Works thereof.
|
| 48 |
+
|
| 49 |
+
"Contribution" shall mean any work of authorship, including
|
| 50 |
+
the original version of the Work and any modifications or additions
|
| 51 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 52 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 53 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 54 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 55 |
+
means any form of electronic, verbal, or written communication sent
|
| 56 |
+
to the Licensor or its representatives, including but not limited to
|
| 57 |
+
communication on electronic mailing lists, source code control systems,
|
| 58 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 59 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 60 |
+
excluding communication that is conspicuously marked or otherwise
|
| 61 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 62 |
+
|
| 63 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 64 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 65 |
+
subsequently incorporated within the Work.
|
| 66 |
+
|
| 67 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 68 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 69 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 70 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 71 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 72 |
+
Work and such Derivative Works in Source or Object form.
|
| 73 |
+
|
| 74 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 75 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 76 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 77 |
+
(except as stated in this section) patent license to make, have made,
|
| 78 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 79 |
+
where such license applies only to those patent claims licensable
|
| 80 |
+
by such Contributor that are necessarily infringed by their
|
| 81 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 82 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 83 |
+
institute patent litigation against any entity (including a
|
| 84 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 85 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 86 |
+
or contributory patent infringement, then any patent licenses
|
| 87 |
+
granted to You under this License for that Work shall terminate
|
| 88 |
+
as of the date such litigation is filed.
|
| 89 |
+
|
| 90 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 91 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 92 |
+
modifications, and in Source or Object form, provided that You
|
| 93 |
+
meet the following conditions:
|
| 94 |
+
|
| 95 |
+
(a) You must give any other recipients of the Work or
|
| 96 |
+
Derivative Works a copy of this License; and
|
| 97 |
+
|
| 98 |
+
(b) You must cause any modified files to carry prominent notices
|
| 99 |
+
stating that You changed the files; and
|
| 100 |
+
|
| 101 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 102 |
+
that You distribute, all copyright, patent, trademark, and
|
| 103 |
+
attribution notices from the Source form of the Work,
|
| 104 |
+
excluding those notices that do not pertain to any part of
|
| 105 |
+
the Derivative Works; and
|
| 106 |
+
|
| 107 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 108 |
+
distribution, then any Derivative Works that You distribute must
|
| 109 |
+
include a readable copy of the attribution notices contained
|
| 110 |
+
within such NOTICE file, excluding those notices that do not
|
| 111 |
+
pertain to any part of the Derivative Works, in at least one
|
| 112 |
+
of the following places: within a NOTICE text file distributed
|
| 113 |
+
as part of the Derivative Works; within the Source form or
|
| 114 |
+
documentation, if provided along with the Derivative Works; or,
|
| 115 |
+
within a display generated by the Derivative Works, if and
|
| 116 |
+
wherever such third-party notices normally appear. The contents
|
| 117 |
+
of the NOTICE file are for informational purposes only and
|
| 118 |
+
do not modify the License. You may add Your own attribution
|
| 119 |
+
notices within Derivative Works that You distribute, alongside
|
| 120 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 121 |
+
that such additional attribution notices cannot be construed
|
| 122 |
+
as modifying the License.
|
| 123 |
+
|
| 124 |
+
You may add Your own copyright statement to Your modifications and
|
| 125 |
+
may provide additional or different license terms and conditions
|
| 126 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 127 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 128 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 129 |
+
the conditions stated in this License.
|
| 130 |
+
|
| 131 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 132 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 133 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 134 |
+
this License, without any additional terms or conditions.
|
| 135 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 136 |
+
the terms of any separate license agreement you may have executed
|
| 137 |
+
with Licensor regarding such Contributions.
|
| 138 |
+
|
| 139 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 140 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 141 |
+
except as required for reasonable and customary use in describing the
|
| 142 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 143 |
+
|
| 144 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 145 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 146 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 147 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 148 |
+
implied, including, without limitation, any warranties or conditions
|
| 149 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 150 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 151 |
+
appropriateness of using or redistributing the Work and assume any
|
| 152 |
+
risks associated with Your exercise of permissions under this License.
|
| 153 |
+
|
| 154 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 155 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 156 |
+
unless required by applicable law (such as deliberate and grossly
|
| 157 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 158 |
+
liable to You for damages, including any direct, indirect, special,
|
| 159 |
+
incidental, or consequential damages of any character arising as a
|
| 160 |
+
result of this License or out of the use or inability to use the
|
| 161 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 162 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 163 |
+
other commercial damages or losses), even if such Contributor
|
| 164 |
+
has been advised of the possibility of such damages.
|
| 165 |
+
|
| 166 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 167 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 168 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 169 |
+
or other liability obligations and/or rights consistent with this
|
| 170 |
+
License. However, in accepting such obligations, You may act only
|
| 171 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 172 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 173 |
+
defend, and hold each Contributor harmless for any liability
|
| 174 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 175 |
+
of your accepting any such warranty or additional liability.
|
| 176 |
+
|
| 177 |
+
END OF TERMS AND CONDITIONS
|
| 178 |
+
|
| 179 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 180 |
+
|
| 181 |
+
To apply the Apache License to your work, attach the following
|
| 182 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 183 |
+
replaced with your own identifying information. (Don't include
|
| 184 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 185 |
+
comment syntax for the file format. We also recommend that a
|
| 186 |
+
file or class name and description of purpose be included on the
|
| 187 |
+
same "printed page" as the copyright notice for easier
|
| 188 |
+
identification within third-party archives.
|
| 189 |
+
|
| 190 |
+
Copyright 2026 Alibaba Cloud
|
| 191 |
+
|
| 192 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 193 |
+
you may not use this file except in compliance with the License.
|
| 194 |
+
You may obtain a copy of the License at
|
| 195 |
+
|
| 196 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 197 |
+
|
| 198 |
+
Unless required by applicable law or agreed to in writing, software
|
| 199 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 200 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 201 |
+
See the License for the specific language governing permissions and
|
| 202 |
+
limitations under the License.
|
README.md
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3.5-4B
|
| 3 |
+
base_model_relation: finetune
|
| 4 |
+
library_name: transformers
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
pipeline_tag: image-text-to-text
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
+
tags:
|
| 10 |
+
- qwen3.5
|
| 11 |
+
- rust
|
| 12 |
+
- code
|
| 13 |
+
- lora
|
| 14 |
+
- safetensors
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Qwen3.5-4B-RustCoder
|
| 18 |
+
|
| 19 |
+
[Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) fine-tuned to write Rust that compiles, passes tests and is clippy-clean. It keeps its thinking mode. These are bf16 safetensors in the original Qwen3.5 layout, for transformers and the tools that read Hugging Face checkpoints.
|
| 20 |
+
|
| 21 |
+
For Apple Silicon, the MLX 8-bit version is [alan13367/Qwen3.5-4B-RustCoder-MLX-8bit](https://huggingface.co/alan13367/Qwen3.5-4B-RustCoder-MLX-8bit). That is the checkpoint that was trained and evaluated, and these weights are the same model (see [About these weights](#about-these-weights)).
|
| 22 |
+
|
| 23 |
+
Every training answer was checked by a gate that builds the code, runs hidden tests and lints it. Answers that failed it were not used.
|
| 24 |
+
|
| 25 |
+
## Results
|
| 26 |
+
|
| 27 |
+
Pass rate: the share of answers whose code passes the task's hidden tests. Each task was sampled 4 times, with thinking on and no system prompt. The test tiers were never trained on.
|
| 28 |
+
|
| 29 |
+
| Pass rate | Easy (29 tasks) | Hard (40) | Quality (29) | Dev (82) |
|
| 30 |
+
|---|---|---|---|---|
|
| 31 |
+
| Qwen3.5-4B (8-bit) | 41.4% | 7.5% | 8.6% | 20.7% |
|
| 32 |
+
| **Qwen3.5-4B-RustCoder** | **51.7%** | **8.8%** | **17.2%** | **22.9%** |
|
| 33 |
+
|
| 34 |
+
- Pooled over all 180 tasks: +4.3 points over the base (95% CI +0.6 to +8.2) and +0.046 graded reward (CI +0.012 to +0.081).
|
| 35 |
+
- The tiers are small. A single tier only detects a gain of about 9 points (hard, quality) or 14 points (easy), so only the pooled gain is established.
|
| 36 |
+
- Quality covers fixing bugs, refactoring, writing tests and new domains. A refactor counts only if it is also lint-clean. Dev is the tier used to pick checkpoints.
|
| 37 |
+
- At least 1 of the 4 attempts passes on 82.8% of easy tasks and 22.5% of hard tasks.
|
| 38 |
+
|
| 39 |
+
General ability, against the base (subsets of each benchmark):
|
| 40 |
+
|
| 41 |
+
| | MMLU (200) | ARC-Challenge (150) | GSM8K (100) | HellaSwag (150) |
|
| 42 |
+
|---|---|---|---|---|
|
| 43 |
+
| Qwen3.5-4B (8-bit) | 69.5% | 89.3% | 92.0% | 80.7% |
|
| 44 |
+
| Qwen3.5-4B-RustCoder | 69.0% | 90.0% | 92.0% | 82.0% |
|
| 45 |
+
|
| 46 |
+
On general text, its token distribution stays close to the base: KL 0.026 nats/token and 94.2% top-1 agreement.
|
| 47 |
+
|
| 48 |
+
## Usage
|
| 49 |
+
|
| 50 |
+
With [transformers](https://github.com/huggingface/transformers) (a version with Qwen3.5 support):
|
| 51 |
+
|
| 52 |
+
```python
|
| 53 |
+
from transformers import AutoModelForImageTextToText, AutoTokenizer
|
| 54 |
+
|
| 55 |
+
repo = "alan13367/Qwen3.5-4B-RustCoder"
|
| 56 |
+
tok = AutoTokenizer.from_pretrained(repo)
|
| 57 |
+
model = AutoModelForImageTextToText.from_pretrained(repo, dtype="auto", device_map="auto")
|
| 58 |
+
messages = [{"role": "user", "content": "Write in Rust: pub fn median(xs: &mut [i64]) -> Option<f64>"}]
|
| 59 |
+
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=True,
|
| 60 |
+
return_tensors="pt", return_dict=True).to(model.device)
|
| 61 |
+
out = model.generate(**inputs, max_new_tokens=4096, do_sample=True, temperature=0.6, top_p=0.95, top_k=20)
|
| 62 |
+
print(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
|
| 63 |
+
```
|
| 64 |
+
|
| 65 |
+
Recommended:
|
| 66 |
+
|
| 67 |
+
- **Use no system prompt.** Training and evaluation used none. A long style prompt sent the base model into runaway reasoning.
|
| 68 |
+
- **Leave thinking on and cap the output at about 4096 tokens.** Answers that finish take a median of about 1.2k tokens. An attempt that runs to the cap is usually stuck in a reasoning loop, so resampling helps more than raising the cap.
|
| 69 |
+
- **Use temperature 0.6, top-p 0.95 and top-k 20.** These are the settings behind the numbers above.
|
| 70 |
+
|
| 71 |
+
## Training
|
| 72 |
+
|
| 73 |
+
LoRA SFT, one epoch. Rank 16, alpha 32, dropout 0.05, on the last 16 decoder layers. Learning rate 1e-4, batches of up to 4096 tokens. In total 739 samples, 784k trained tokens, 402 steps. Validation loss was 0.411.
|
| 74 |
+
|
| 75 |
+
The data is mostly the model's own work, filtered by the gate:
|
| 76 |
+
|
| 77 |
+
| Source | Records | What it is |
|
| 78 |
+
|---|---|---|
|
| 79 |
+
| Own passing attempts | 238 | The base model's own attempts at the training tasks, kept only if they pass the hidden tests and the test lints |
|
| 80 |
+
| Self-repairs | 277 | The base model fixing its own failed attempts, given the compiler or test output as the next user turn, kept only if the fix passes |
|
| 81 |
+
| Teacher traces | 175 | Passing traces from DeepSeek V4.1 Flash. 159 of them repair the 4B's own failed attempts. Only traces within the 4B's own length and style were kept (completion of at most 2048 tokens, little second-guessing) |
|
| 82 |
+
| Replay | 88 | The base model's own answers to general, non-Rust prompts, to keep its general ability |
|
| 83 |
+
|
| 84 |
+
What the experiments behind this checkpoint showed:
|
| 85 |
+
|
| 86 |
+
- **The model learns best from its own style.** Reference solutions with model-written reasoning made it worse (easy 41.4% → 26.7%). It imitated their dense style and compiled less often.
|
| 87 |
+
- **Unfiltered teacher traces also made it worse** (easy 34.5%). Their long, second-guessing reasoning taught it to never leave thinking: 177 of 720 answers ran to the cap.
|
| 88 |
+
- **Filtering the teacher traces fixed that.** This checkpoint has 36 of 720 answers that run to the cap, against 82 for the base.
|
| 89 |
+
- **The loss covers only the final reply.** In repair records, the failed attempt and the feedback are context, not training targets.
|
| 90 |
+
|
| 91 |
+
## About these weights
|
| 92 |
+
|
| 93 |
+
- **Where they come from.** The fine-tune was trained and merged on the 8-bit MLX model. These weights are that checkpoint dequantized to bf16, so they are exactly the evaluated model: every weight is its 8-bit value. They do not get back the precision the 8-bit quantization lost. Weights the fine-tune left alone differ from the original Qwen3.5-4B bf16 by about 0.7% (relative error), the size of the 8-bit quantization error.
|
| 94 |
+
- **Checks.** Each tensor's name, shape and dtype matches Qwen/Qwen3.5-4B. Tensors that were never quantized (norms, conv1d, `A_log`, the vision tower) match the original exactly.
|
| 95 |
+
- **Tokenizer and config.** Both are Qwen/Qwen3.5-4B's. The tokenizer gives the same ids as the one used in training.
|
| 96 |
+
- **No MTP head.** The 8-bit checkpoint the fine-tune was built on has no multi-token-prediction head, so MTP speculative decoding (vLLM, SGLang) is not available.
|
| 97 |
+
|
| 98 |
+
## Limitations
|
| 99 |
+
|
| 100 |
+
- It is a 4B model and Rust is hard for it. Many of its answers still fail to compile (about half did for the base model and the previous fine-tune), mostly with type, trait-bound and method errors in its own code (E0308, E0277, E0599). Harder multi-part tasks rarely pass (hard tier 8.8%). It does much better with a compiler in the loop: given the error output it fixes a share of its failures, and the best of 4 attempts passes far more often than a single one.
|
| 101 |
+
- It still over-thinks sometimes. Cap the output, and resample when an answer gets stuck.
|
| 102 |
+
- Only the text side was trained. The vision tower is the base's, unchanged and untested here.
|
| 103 |
+
- The evaluation sets are small (29 to 82 tasks per tier), so each per-tier number has a wide margin. Treat the gains as modest.
|
| 104 |
+
- It was trained and evaluated on standalone tasks: a function, a type or a small module checked by hidden tests, plus bug fixes, refactors and test-writing. It has not been measured on multi-file projects or long-context editing.
|
| 105 |
+
|
| 106 |
+
## License
|
| 107 |
+
|
| 108 |
+
Apache 2.0, the license of the base model [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B).
|
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 false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"dtype": "bfloat16",
|
| 12 |
+
"eos_token_id": 248044,
|
| 13 |
+
"full_attention_interval": 4,
|
| 14 |
+
"head_dim": 256,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 2560,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 9216,
|
| 19 |
+
"layer_types": [
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
+
"linear_conv_kernel_dim": 4,
|
| 54 |
+
"linear_key_head_dim": 128,
|
| 55 |
+
"linear_num_key_heads": 16,
|
| 56 |
+
"linear_num_value_heads": 32,
|
| 57 |
+
"linear_value_head_dim": 128,
|
| 58 |
+
"max_position_embeddings": 262144,
|
| 59 |
+
"mlp_only_layers": [],
|
| 60 |
+
"model_type": "qwen3_5_text",
|
| 61 |
+
"mtp_num_hidden_layers": 1,
|
| 62 |
+
"mtp_use_dedicated_embeddings": false,
|
| 63 |
+
"num_attention_heads": 16,
|
| 64 |
+
"num_hidden_layers": 32,
|
| 65 |
+
"num_key_value_heads": 4,
|
| 66 |
+
"rms_norm_eps": 1e-06,
|
| 67 |
+
"tie_word_embeddings": true,
|
| 68 |
+
"use_cache": true,
|
| 69 |
+
"vocab_size": 248320,
|
| 70 |
+
"mamba_ssm_dtype": "float32",
|
| 71 |
+
"rope_parameters": {
|
| 72 |
+
"mrope_interleaved": true,
|
| 73 |
+
"mrope_section": [
|
| 74 |
+
11,
|
| 75 |
+
11,
|
| 76 |
+
10
|
| 77 |
+
],
|
| 78 |
+
"rope_type": "default",
|
| 79 |
+
"rope_theta": 10000000,
|
| 80 |
+
"partial_rotary_factor": 0.25
|
| 81 |
+
}
|
| 82 |
+
},
|
| 83 |
+
"tie_word_embeddings": true,
|
| 84 |
+
"transformers_version": "4.57.0.dev0",
|
| 85 |
+
"video_token_id": 248057,
|
| 86 |
+
"vision_config": {
|
| 87 |
+
"deepstack_visual_indexes": [],
|
| 88 |
+
"depth": 24,
|
| 89 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 90 |
+
"hidden_size": 1024,
|
| 91 |
+
"in_channels": 3,
|
| 92 |
+
"initializer_range": 0.02,
|
| 93 |
+
"intermediate_size": 4096,
|
| 94 |
+
"model_type": "qwen3_5",
|
| 95 |
+
"num_heads": 16,
|
| 96 |
+
"num_position_embeddings": 2304,
|
| 97 |
+
"out_hidden_size": 2560,
|
| 98 |
+
"patch_size": 16,
|
| 99 |
+
"spatial_merge_size": 2,
|
| 100 |
+
"temporal_patch_size": 2
|
| 101 |
+
},
|
| 102 |
+
"vision_end_token_id": 248054,
|
| 103 |
+
"vision_start_token_id": 248053
|
| 104 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94412634d519ebdcf7b76ad26cfb02211bfbe13d80a7ac0617738c81f9494992
|
| 3 |
+
size 5356494160
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d071e74bb4278e565f4dadb69fed8734de5cfbbde29c5a4ef5d8a43d77ea78a3
|
| 3 |
+
size 3722133928
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,730 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 9078538752
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 405 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 408 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 409 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 410 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 411 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 413 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 414 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 415 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 416 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 417 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 418 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 419 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 420 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 421 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 422 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 423 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 425 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 427 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 429 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 729 |
+
}
|
| 730 |
+
}
|
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 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
|
| 3 |
+
size 12807982
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"248044": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"248045": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"248046": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"248047": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"248048": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"248049": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"248050": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"248051": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"248052": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"248053": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"248054": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"248055": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"248056": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"248057": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"248058": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"248059": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"248060": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"248061": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"248062": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"248063": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"248064": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"248065": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"248066": {
|
| 181 |
+
"content": "<tool_response>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"248067": {
|
| 189 |
+
"content": "</tool_response>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"248068": {
|
| 197 |
+
"content": "<think>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"248069": {
|
| 205 |
+
"content": "</think>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"248070": {
|
| 213 |
+
"content": "<|audio_start|>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"248071": {
|
| 221 |
+
"content": "<|audio_end|>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"248072": {
|
| 229 |
+
"content": "<tts_pad>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"248073": {
|
| 237 |
+
"content": "<tts_text_bos>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"248074": {
|
| 245 |
+
"content": "<tts_text_eod>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"248075": {
|
| 253 |
+
"content": "<tts_text_bos_single>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"248076": {
|
| 261 |
+
"content": "<|audio_pad|>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
}
|
| 268 |
+
},
|
| 269 |
+
"additional_special_tokens": [
|
| 270 |
+
"<|im_start|>",
|
| 271 |
+
"<|im_end|>",
|
| 272 |
+
"<|object_ref_start|>",
|
| 273 |
+
"<|object_ref_end|>",
|
| 274 |
+
"<|box_start|>",
|
| 275 |
+
"<|box_end|>",
|
| 276 |
+
"<|quad_start|>",
|
| 277 |
+
"<|quad_end|>",
|
| 278 |
+
"<|vision_start|>",
|
| 279 |
+
"<|vision_end|>",
|
| 280 |
+
"<|vision_pad|>",
|
| 281 |
+
"<|image_pad|>",
|
| 282 |
+
"<|video_pad|>"
|
| 283 |
+
],
|
| 284 |
+
"bos_token": null,
|
| 285 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if 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 false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 286 |
+
"clean_up_tokenization_spaces": false,
|
| 287 |
+
"eos_token": "<|im_end|>",
|
| 288 |
+
"errors": "replace",
|
| 289 |
+
"model_max_length": 262144,
|
| 290 |
+
"pad_token": "<|endoftext|>",
|
| 291 |
+
"split_special_tokens": false,
|
| 292 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 293 |
+
"unk_token": null,
|
| 294 |
+
"add_bos_token": false,
|
| 295 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 296 |
+
"extra_special_tokens": {
|
| 297 |
+
"audio_bos_token": "<|audio_start|>",
|
| 298 |
+
"audio_eos_token": "<|audio_end|>",
|
| 299 |
+
"audio_token": "<|audio_pad|>",
|
| 300 |
+
"image_token": "<|image_pad|>",
|
| 301 |
+
"video_token": "<|video_pad|>",
|
| 302 |
+
"vision_bos_token": "<|vision_start|>",
|
| 303 |
+
"vision_eos_token": "<|vision_end|>"
|
| 304 |
+
}
|
| 305 |
+
}
|
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
|
|
|