初始化项目，由ModelHub XC社区提供模型
Model: FudanNLP/MagicGUI_RFT Source: Original Platform
This commit is contained in:
ModelHub XC
51
.gitattributes
vendored
Normal file
51
.gitattributes
vendored
Normal file
@@ -0,0 +1,51 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||||
201
LICENSE.txt
Normal file
201
LICENSE.txt
Normal file
@@ -0,0 +1,201 @@
|
|||||||
|
Apache License
|
||||||
|
Version 2.0, January 2004
|
||||||
|
http://www.apache.org/licenses/
|
||||||
|
|
||||||
|
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||||
|
|
||||||
|
1. Definitions.
|
||||||
|
|
||||||
|
"License" shall mean the terms and conditions for use, reproduction,
|
||||||
|
and distribution as defined by Sections 1 through 9 of this document.
|
||||||
|
|
||||||
|
"Licensor" shall mean the copyright owner or entity authorized by
|
||||||
|
the copyright owner that is granting the License.
|
||||||
|
|
||||||
|
"Legal Entity" shall mean the union of the acting entity and all
|
||||||
|
other entities that control, are controlled by, or are under common
|
||||||
|
control with that entity. For the purposes of this definition,
|
||||||
|
"control" means (i) the power, direct or indirect, to cause the
|
||||||
|
direction or management of such entity, whether by contract or
|
||||||
|
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||||
|
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||||
|
|
||||||
|
"You" (or "Your") shall mean an individual or Legal Entity
|
||||||
|
exercising permissions granted by this License.
|
||||||
|
|
||||||
|
"Source" form shall mean the preferred form for making modifications,
|
||||||
|
including but not limited to software source code, documentation
|
||||||
|
source, and configuration files.
|
||||||
|
|
||||||
|
"Object" form shall mean any form resulting from mechanical
|
||||||
|
transformation or translation of a Source form, including but
|
||||||
|
not limited to compiled object code, generated documentation,
|
||||||
|
and conversions to other media types.
|
||||||
|
|
||||||
|
"Work" shall mean the work of authorship, whether in Source or
|
||||||
|
Object form, made available under the License, as indicated by a
|
||||||
|
copyright notice that is included in or attached to the work
|
||||||
|
(an example is provided in the Appendix below).
|
||||||
|
|
||||||
|
"Derivative Works" shall mean any work, whether in Source or Object
|
||||||
|
form, that is based on (or derived from) the Work and for which the
|
||||||
|
editorial revisions, annotations, elaborations, or other modifications
|
||||||
|
represent, as a whole, an original work of authorship. For the purposes
|
||||||
|
of this License, Derivative Works shall not include works that remain
|
||||||
|
separable from, or merely link (or bind by name) to the interfaces of,
|
||||||
|
the Work and Derivative Works thereof.
|
||||||
|
|
||||||
|
"Contribution" shall mean any work of authorship, including
|
||||||
|
the original version of the Work and any modifications or additions
|
||||||
|
to that Work or Derivative Works thereof, that is intentionally
|
||||||
|
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||||
|
or by an individual or Legal Entity authorized to submit on behalf of
|
||||||
|
the copyright owner. For the purposes of this definition, "submitted"
|
||||||
|
means any form of electronic, verbal, or written communication sent
|
||||||
|
to the Licensor or its representatives, including but not limited to
|
||||||
|
communication on electronic mailing lists, source code control systems,
|
||||||
|
and issue tracking systems that are managed by, or on behalf of, the
|
||||||
|
Licensor for the purpose of discussing and improving the Work, but
|
||||||
|
excluding communication that is conspicuously marked or otherwise
|
||||||
|
designated in writing by the copyright owner as "Not a Contribution."
|
||||||
|
|
||||||
|
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||||
|
on behalf of whom a Contribution has been received by Licensor and
|
||||||
|
subsequently incorporated within the Work.
|
||||||
|
|
||||||
|
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||||
|
this License, each Contributor hereby grants to You a perpetual,
|
||||||
|
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||||
|
copyright license to reproduce, prepare Derivative Works of,
|
||||||
|
publicly display, publicly perform, sublicense, and distribute the
|
||||||
|
Work and such Derivative Works in Source or Object form.
|
||||||
|
|
||||||
|
3. Grant of Patent License. Subject to the terms and conditions of
|
||||||
|
this License, each Contributor hereby grants to You a perpetual,
|
||||||
|
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||||
|
(except as stated in this section) patent license to make, have made,
|
||||||
|
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||||
|
where such license applies only to those patent claims licensable
|
||||||
|
by such Contributor that are necessarily infringed by their
|
||||||
|
Contribution(s) alone or by combination of their Contribution(s)
|
||||||
|
with the Work to which such Contribution(s) was submitted. If You
|
||||||
|
institute patent litigation against any entity (including a
|
||||||
|
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||||
|
or a Contribution incorporated within the Work constitutes direct
|
||||||
|
or contributory patent infringement, then any patent licenses
|
||||||
|
granted to You under this License for that Work shall terminate
|
||||||
|
as of the date such litigation is filed.
|
||||||
|
|
||||||
|
4. Redistribution. You may reproduce and distribute copies of the
|
||||||
|
Work or Derivative Works thereof in any medium, with or without
|
||||||
|
modifications, and in Source or Object form, provided that You
|
||||||
|
meet the following conditions:
|
||||||
|
|
||||||
|
(a) You must give any other recipients of the Work or
|
||||||
|
Derivative Works a copy of this License; and
|
||||||
|
|
||||||
|
(b) You must cause any modified files to carry prominent notices
|
||||||
|
stating that You changed the files; and
|
||||||
|
|
||||||
|
(c) You must retain, in the Source form of any Derivative Works
|
||||||
|
that You distribute, all copyright, patent, trademark, and
|
||||||
|
attribution notices from the Source form of the Work,
|
||||||
|
excluding those notices that do not pertain to any part of
|
||||||
|
the Derivative Works; and
|
||||||
|
|
||||||
|
(d) If the Work includes a "NOTICE" text file as part of its
|
||||||
|
distribution, then any Derivative Works that You distribute must
|
||||||
|
include a readable copy of the attribution notices contained
|
||||||
|
within such NOTICE file, excluding those notices that do not
|
||||||
|
pertain to any part of the Derivative Works, in at least one
|
||||||
|
of the following places: within a NOTICE text file distributed
|
||||||
|
as part of the Derivative Works; within the Source form or
|
||||||
|
documentation, if provided along with the Derivative Works; or,
|
||||||
|
within a display generated by the Derivative Works, if and
|
||||||
|
wherever such third-party notices normally appear. The contents
|
||||||
|
of the NOTICE file are for informational purposes only and
|
||||||
|
do not modify the License. You may add Your own attribution
|
||||||
|
notices within Derivative Works that You distribute, alongside
|
||||||
|
or as an addendum to the NOTICE text from the Work, provided
|
||||||
|
that such additional attribution notices cannot be construed
|
||||||
|
as modifying the License.
|
||||||
|
|
||||||
|
You may add Your own copyright statement to Your modifications and
|
||||||
|
may provide additional or different license terms and conditions
|
||||||
|
for use, reproduction, or distribution of Your modifications, or
|
||||||
|
for any such Derivative Works as a whole, provided Your use,
|
||||||
|
reproduction, and distribution of the Work otherwise complies with
|
||||||
|
the conditions stated in this License.
|
||||||
|
|
||||||
|
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||||
|
any Contribution intentionally submitted for inclusion in the Work
|
||||||
|
by You to the Licensor shall be under the terms and conditions of
|
||||||
|
this License, without any additional terms or conditions.
|
||||||
|
Notwithstanding the above, nothing herein shall supersede or modify
|
||||||
|
the terms of any separate license agreement you may have executed
|
||||||
|
with Licensor regarding such Contributions.
|
||||||
|
|
||||||
|
6. Trademarks. This License does not grant permission to use the trade
|
||||||
|
names, trademarks, service marks, or product names of the Licensor,
|
||||||
|
except as required for reasonable and customary use in describing the
|
||||||
|
origin of the Work and reproducing the content of the NOTICE file.
|
||||||
|
|
||||||
|
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||||
|
agreed to in writing, Licensor provides the Work (and each
|
||||||
|
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||||
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||||
|
implied, including, without limitation, any warranties or conditions
|
||||||
|
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||||
|
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||||
|
appropriateness of using or redistributing the Work and assume any
|
||||||
|
risks associated with Your exercise of permissions under this License.
|
||||||
|
|
||||||
|
8. Limitation of Liability. In no event and under no legal theory,
|
||||||
|
whether in tort (including negligence), contract, or otherwise,
|
||||||
|
unless required by applicable law (such as deliberate and grossly
|
||||||
|
negligent acts) or agreed to in writing, shall any Contributor be
|
||||||
|
liable to You for damages, including any direct, indirect, special,
|
||||||
|
incidental, or consequential damages of any character arising as a
|
||||||
|
result of this License or out of the use or inability to use the
|
||||||
|
Work (including but not limited to damages for loss of goodwill,
|
||||||
|
work stoppage, computer failure or malfunction, or any and all
|
||||||
|
other commercial damages or losses), even if such Contributor
|
||||||
|
has been advised of the possibility of such damages.
|
||||||
|
|
||||||
|
9. Accepting Warranty or Additional Liability. While redistributing
|
||||||
|
the Work or Derivative Works thereof, You may choose to offer,
|
||||||
|
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||||
|
or other liability obligations and/or rights consistent with this
|
||||||
|
License. However, in accepting such obligations, You may act only
|
||||||
|
on Your own behalf and on Your sole responsibility, not on behalf
|
||||||
|
of any other Contributor, and only if You agree to indemnify,
|
||||||
|
defend, and hold each Contributor harmless for any liability
|
||||||
|
incurred by, or claims asserted against, such Contributor by reason
|
||||||
|
of your accepting any such warranty or additional liability.
|
||||||
|
|
||||||
|
END OF TERMS AND CONDITIONS
|
||||||
|
|
||||||
|
APPENDIX: How to apply the Apache License to your work.
|
||||||
|
|
||||||
|
To apply the Apache License to your work, attach the following
|
||||||
|
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||||
|
replaced with your own identifying information. (Don't include
|
||||||
|
the brackets!) The text should be enclosed in the appropriate
|
||||||
|
comment syntax for the file format. We also recommend that a
|
||||||
|
file or class name and description of purpose be included on the
|
||||||
|
same "printed page" as the copyright notice for easier
|
||||||
|
identification within third-party archives.
|
||||||
|
|
||||||
|
Copyright [yyyy] [name of copyright owner]
|
||||||
|
|
||||||
|
Licensed under the Apache License, Version 2.0 (the "License");
|
||||||
|
you may not use this file except in compliance with the License.
|
||||||
|
You may obtain a copy of the License at
|
||||||
|
|
||||||
|
http://www.apache.org/licenses/LICENSE-2.0
|
||||||
|
|
||||||
|
Unless required by applicable law or agreed to in writing, software
|
||||||
|
distributed under the License is distributed on an "AS IS" BASIS,
|
||||||
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||||
|
See the License for the specific language governing permissions and
|
||||||
|
limitations under the License.
|
||||||
508
README.md
Normal file
508
README.md
Normal file
@@ -0,0 +1,508 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
datasets:
|
||||||
|
- GUIAgent/Magic-RICH
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
base_model:
|
||||||
|
- Qwen/Qwen2-VL-7B-Instruct
|
||||||
|
---
|
||||||
|
## News
|
||||||
|
|
||||||
|
* [2025-07-20] 📄📄📄 We have released the **technical report** of MagicGUI! Check it out [here](https://arxiv.org/abs/2508.03700).
|
||||||
|
* [2025-07-20] 🚀🚀🚀 We have open-sourced **MagicGUI**, an on-device GUI agent capable of operating Chinese & English apps and equipped with RFT-enhanced reasoning abilities.
|
||||||
|
|
||||||
|
## Overview
|
||||||
|
|
||||||
|
MagicGUI is an open-source GUI agent model developed by Honor, built on Qwen2-VL with 7 billion parameters. It demonstrates outstanding capabilities in visual grounding, screen question answering, and action sequence planning and execution. MagicGUI enables multimodal perception, understanding, and automated execution of user tasks on mobile devices.
|
||||||
|
|
||||||
|
**Data Collection Framework**: Propose a scalable and modular framework for GUI data collection that efficiently gathers high-quality data on mobile devices.
|
||||||
|
|
||||||
|
**Powerful Perception and Grounding Capabilities**: Enhance the perception and grounding abilities on mobile device screens by integrating large-scale knowledge through tasks such as element referring, element grounding, and screen captioning.
|
||||||
|
|
||||||
|
**Unified Action Space**: Develop a comprehensive and unified action space for various mobile platforms, encompassing fundamental operations like Tap, Text Input, and Scroll, while also supporting more complex actions such as Wait, Drag, and Takeover.
|
||||||
|
|
||||||
|
**Planning-Oriented Reasoning**: Implement a planning-oriented reasoning mechanism to improve the stability of task execution and enhance the accuracy of action decisions in dynamic environments.
|
||||||
|
|
||||||
|
**Two-Stage Training Paradigm**: Strengthen core perception, localization, and navigation capabilities through Continued Pre-training (CPT), while enhancing model robustness and generalization via Reinforcement Fine-tuning (RFT).
|
||||||
|
|
||||||
|
## Framework
|
||||||
|
The overall training framework of our MagicGUI contains two stages:
|
||||||
|
|
||||||
|
**Stage I**: Continue Pre-training (CPT), which involves training a
|
||||||
|
foundational model on a large and diverse dataset followed by an annealing phase using a balanced and high-quality
|
||||||
|
dataset.
|
||||||
|
|
||||||
|
**Stage II**: Reinforcement Fine-tuning (RFT), aimed at further enhancing the
|
||||||
|
model’s robustness and generalization capabilities.
|
||||||
|
|
||||||
|
## Quick Start
|
||||||
|
### Install dependencies
|
||||||
|
|
||||||
|
```bash
|
||||||
|
git clone https://github.com/MagicAgent-GUI
|
||||||
|
cd MagicGUI
|
||||||
|
conda create -n gui_agent python=3.11
|
||||||
|
conda activate gui_agent
|
||||||
|
pip install -r requirements.txt
|
||||||
|
```
|
||||||
|
### Download the model
|
||||||
|
|
||||||
|
Download [MagicGUI-RFT](https://huggingface.co/GUIAgent/MagicGUI_RFT) and [MagicGUI-CPT](https://huggingface.co/GUIAgent/MagicGUI_CPT).
|
||||||
|
|
||||||
|
#### Huggingface Inference
|
||||||
|
|
||||||
|
```python
|
||||||
|
import torch
|
||||||
|
from utils.model import Qwen2VLChat
|
||||||
|
|
||||||
|
# 1. Load the model and tokenizer
|
||||||
|
model_path = "./models/RFT" # model path
|
||||||
|
model = Qwen2VLChat.from_pretrained(model_path, min_pixels=4*28*28, max_pixels=768*28*28)
|
||||||
|
model = model.to("cuda:0")
|
||||||
|
|
||||||
|
# 2. Build the input
|
||||||
|
instruction = """你是一个训练有素的手机智能体，能够帮助用户进行单步导航任务。已知当前智能手机的截图<image>，和用户指令"查看会员信息"请输出正确的函数调用以实现用户指令。除了函数调用之外，你不能输出任何其他内容。你可以调用以下函数来控制智能手机：- UI基础操作：1. tap(x: float,y: float) 该函数用于在智能手机屏幕上点击特定点。坐标 x 和 y 表示待点击控件的中心位置。2. scroll(x: float,y: float,direction: str) 该函数用于从起始坐标 (x,y) 开始在智能手机屏幕上滑动操作，方向为手指滑动的方向。坐标 x 和 y 表示屏幕上待滑动控件的中心位置。方向可以是 "up"、"down"、"left" 或 "right"。3. text(x: float,y: float,text_input: str) 该函数用于在智能手机屏幕上输入指定的text。坐标 x 和 y 表示待点击控件的中心位置。- 手机按键操作：4. navigate_back() 该函数用于返回智能手机的上一个屏幕。5. navigate_home() 该函数用于返回手机的home screen或关闭当前应用。- 其他操作：6. long_press(x: float,y: float) 该函数用于在智能手机屏幕上的特定点执行长按操作。坐标 x 和 y 表示待点击控件的中心位置。7. wait() 该函数表示在当前页面等候。8. enter() 该函数表示按下enter键。9. take_over(text_input: str) 该函数用于提示用户接管智能手机，其中 text_input 是提示用户接管手机的原因。如果原因不确定，请填写“请您接管当前界面”。10. drag(x1: float,y1: float,x2: float,y2: float) 该函数执行一个对起始和终点敏感的拖动操作，表示手指从点1拖到点2。常见的场景包括滑块拖动、滚动选择器拖动和图片裁剪。11. screen_shot() 该函数用于截图。12. long_screen_shot() 该函数执行长截图。13. call_api(api_name: str,params: str) 调用指定的API并传入给定的参数。api_name是API的名称。params包含API所需的输入参数。例如，call_api(Amazon, open)意味着打开亚马逊APP。如果你发现当前指令无法在当前页面上执行，你需要输出no_answer。如果你发现当前指令已完成，你需要输出action_completed。"""
|
||||||
|
|
||||||
|
image_path = "./assets/test_action.png"
|
||||||
|
|
||||||
|
# 3. Build the message format
|
||||||
|
messages = [{"type": "image", "value":f"{image_path}",
|
||||||
|
{"type": "text", "value":f"{instruction}"]
|
||||||
|
|
||||||
|
# 4. Inference
|
||||||
|
response = model.generate(
|
||||||
|
message = messages,
|
||||||
|
)
|
||||||
|
|
||||||
|
print(response)
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected output:
|
||||||
|
|
||||||
|
```JSON
|
||||||
|
{"tap(700,964)"}
|
||||||
|
```
|
||||||
|
|
||||||
|
### Action Space
|
||||||
|
|
||||||
|
At each step, the agent outputs is a single JSON object that contains:
|
||||||
|
- One (and only one) primitive action, chosen from the list below;
|
||||||
|
- Optional modifiers (`duration`, `thought`) and/or a task-level flag (`STATUS`).
|
||||||
|
|
||||||
|
Note that all keywords are **case-sensitive**, and we use **compact JSON** (i.e., no extra whitespace), which affects the tokenizer’s behavior.
|
||||||
|
|
||||||
|
<table>
|
||||||
|
<thead>
|
||||||
|
<tr>
|
||||||
|
<th>Action</th>
|
||||||
|
<th>Description</th>
|
||||||
|
<th>Conditions for R<sub>acc</sub> = +2</th>
|
||||||
|
<th>Example</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody>
|
||||||
|
<tr>
|
||||||
|
<td><b>Tap</b></td>
|
||||||
|
<td>Click at coordinate (x, y)</td>
|
||||||
|
<td>dist([x, y], [x<sub>c</sub>, y<sub>c</sub>]) ≤ 14%</td>
|
||||||
|
<td><code>tap(x,y)</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Scroll</b></td>
|
||||||
|
<td>Scroll at coordinate (x, y) with<br>direction up / down / left / right</td>
|
||||||
|
<td>dist([x, y], [x<sub>c</sub>, y<sub>c</sub>]) ≤ 14%<br>and direction = gt[direction]</td>
|
||||||
|
<td><code>scroll(x,y,direction)</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Text Input</b></td>
|
||||||
|
<td>Type <i>text</i> at coordinate (x, y)</td>
|
||||||
|
<td>dist([x, y], [x<sub>c</sub>, y<sub>c</sub>]) ≤ 14%<br>and F1(text, gt[text]) > 0.5</td>
|
||||||
|
<td><code>text(x,y,text_input)</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Navigation Back</b></td>
|
||||||
|
<td>Adb command to go back to the previous page</td>
|
||||||
|
<td>–</td>
|
||||||
|
<td><code>navigate_back()</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Navigation Home</b></td>
|
||||||
|
<td>Adb command to go to the home screen of the mobile</td>
|
||||||
|
<td>–</td>
|
||||||
|
<td><code>navigate_home()</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Long Press</b></td>
|
||||||
|
<td>Long press at coordinate (x, y)</td>
|
||||||
|
<td>dist([x, y], [x<sub>c</sub>, y<sub>c</sub>]) ≤ 14%</td>
|
||||||
|
<td><code>long_press(x,y)</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Finish</b></td>
|
||||||
|
<td>Indicate that navigation task has been completed</td>
|
||||||
|
<td>–</td>
|
||||||
|
<td><code>finish()</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>w
|
||||||
|
<td><b>Wait</b></td>
|
||||||
|
<td>Wait for several seconds</td>
|
||||||
|
<td>–</td>
|
||||||
|
<td><code>wait()</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Enter</b></td>
|
||||||
|
<td>Adb command to press enter</td>
|
||||||
|
<td>–</td>
|
||||||
|
<td><code>enter()</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Takeover</b></td>
|
||||||
|
<td>Request user takeover</td>
|
||||||
|
<td>–</td>
|
||||||
|
<td><code>take_over(message)</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Drag</b></td>
|
||||||
|
<td>Drag from coordinate (x₁, y₁) to (x₂, y₂)</td>
|
||||||
|
<td>
|
||||||
|
dist([x₁, y₁], [x<sub>1c</sub>, y<sub>1c</sub>]) ≤ 7.5%<br>
|
||||||
|
and dist([x₂, y₂], [x<sub>2c</sub>, y<sub>2c</sub>]) ≤ 7.5%
|
||||||
|
</td>
|
||||||
|
<td><code>drag(x1,y1,x2,y2)</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Call API</b></td>
|
||||||
|
<td>Adb command to <i>open</i> or <i>kill</i> app</td>
|
||||||
|
<td>app = gt[app]<br>and open/kill = gt[operation]</td>
|
||||||
|
<td><code>call_api(api_name,operation)</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Screenshot</b></td>
|
||||||
|
<td>Adb command to take a screenshot</td>
|
||||||
|
<td>–</td>
|
||||||
|
<td><code>screen_shot()</code></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Long Screenshot</b></td>
|
||||||
|
<td>Adb command to take a long screenshot</td>
|
||||||
|
<td>–</td>
|
||||||
|
<td><code>long_screen_shot()</code></td>
|
||||||
|
</tr>
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
|
||||||
|
## Evaluation
|
||||||
|
### 1.Data preparation
|
||||||
|
Please download the four compressed files from the [Magic-RICH dataset](https://huggingface.co/datasets/GUIAgent/Magic-RICH) and extract them into the .datasets/ directory.
|
||||||
|
|
||||||
|
- `assets/`
|
||||||
|
- `datasets/`
|
||||||
|
- `Routine`
|
||||||
|
- `Instruction`
|
||||||
|
- `Complex`
|
||||||
|
- `Handing_Exception`
|
||||||
|
- `utils/`
|
||||||
|
|
||||||
|
For the preparation of other open-source datasets, please refer to [Other datasets preparation](datasets/eval_data_process/readme.md).
|
||||||
|
|
||||||
|
### 2. Param
|
||||||
|
We use run_eval.py for evaluation.
|
||||||
|
|
||||||
|
- `--data`: Name of a eval dataset
|
||||||
|
- `--model`: Path to the model
|
||||||
|
- `--work-dir (str, default to '.')`: Directory to save evaluation results
|
||||||
|
- `--mode (str, default: 'all', choices: ['all', 'infer'])`: If set to "all", the script performs both inference and evaluation; if set to "infer", it performs inference only.
|
||||||
|
- `--eval_model_path (str, default: 'None')`:'Path to eval model (required if mode is 'all' and data is 'ScreenQA-short')'
|
||||||
|
|
||||||
|
### 3. Run
|
||||||
|
```python
|
||||||
|
# Referring Benchmark
|
||||||
|
python run_eval.py --data ScreenQA-short --model MagicGUI_Path --mode all --eval_model_path Eval_Model_Path
|
||||||
|
python run_eval.py --data ScreenSpot_v2_mobile --model MagicGUI_Path --mode all
|
||||||
|
python run_eval.py --data Os-Atlas-mobile --model MagicGUI_Path --mode all
|
||||||
|
# Magic-RICH dataset
|
||||||
|
python run_eval.py --data Routine --model MagicGUI_Path --mode all
|
||||||
|
python run_eval.py --data Complex --model MagicGUI_Path --mode all
|
||||||
|
python run_eval.py --data Instruction --model MagicGUI_Path --mode all
|
||||||
|
python run_eval.py --data Handling_Exception --model MagicGUI_Path --mode all
|
||||||
|
# Open-source AndroidControl and GUI-Odyssey
|
||||||
|
python run_eval.py --data AC-Low --model MagicGUI_Path --mode all
|
||||||
|
python run_eval.py --data AC-High --model MagicGUI_Path --mode all
|
||||||
|
python run_eval.py --data GUI-Odyssey --model MagicGUI_Path --mode all
|
||||||
|
```
|
||||||
|
|
||||||
|
## Performance Evaluation
|
||||||
|
|
||||||
|
### Performance comparison on the Referring Benchmark
|
||||||
|
<table>
|
||||||
|
<thead>
|
||||||
|
<tr>
|
||||||
|
<th rowspan="1">Agent Models</th>
|
||||||
|
<th colspan="1">ScreenQA-short</th>
|
||||||
|
<th colspan="1">ScreenSpot v2 mobile</th>
|
||||||
|
<th colspan="1">Os-Atlas-mobile</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody>
|
||||||
|
<!-- Closed-source Models -->
|
||||||
|
<tr><td colspan="4"><em>Closed-source Models</em></td></tr>
|
||||||
|
<tr>
|
||||||
|
<td>GPT-4o (Hurst et al., 2024)</td>
|
||||||
|
<td>90.3</td><td>10.6</td><td>4.6</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Gemini 2.0 (Pichai et al., 2024)</td>
|
||||||
|
<td>90.4</td><td>10.6</td><td>5.8</td>
|
||||||
|
</tr>
|
||||||
|
<!-- Open-source Models -->
|
||||||
|
<tr><td colspan="4"><em>Open-source Models</em></td></tr>
|
||||||
|
<tr>
|
||||||
|
<td>InternVL-2-8B (Chen et al., 2024)</td>
|
||||||
|
<td>88.4</td><td>4.2</td><td>2.4</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Qwen2-VL-7B (Wang et al., 2024)</td>
|
||||||
|
<td>92.6</td><td>70.7</td><td>27.2</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Qwen2.5-VL-7B (Bai et al., 2025)</td>
|
||||||
|
<td>92.1</td><td>56.1</td><td>26.6</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>UI-TARS-7B (Qin et al., 2025)</td>
|
||||||
|
<td><b>95.4</b></td><td>88.6</td><td>82.5</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>UI-TARS-1.5-7B (Seed, 2025)</td>
|
||||||
|
<td>93.0</td><td>85.8</td><td>79.3</td>
|
||||||
|
</tr>
|
||||||
|
<!-- MagicGUI -->
|
||||||
|
<tr style="background-color:#e8eafc;">
|
||||||
|
<td>MagicGUI-CPT</td>
|
||||||
|
<td>94.6</td><td><b>90.2</b></td><td><b>95.2</b></td>
|
||||||
|
</tr>
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
|
||||||
|
### Performance comparison on the Magic-RICH dataset
|
||||||
|
|
||||||
|
<table>
|
||||||
|
<thead>
|
||||||
|
<tr>
|
||||||
|
<th rowspan="2">Agent Models</th>
|
||||||
|
<th colspan="3">Routine</th>
|
||||||
|
<th colspan="3">Instruction</th>
|
||||||
|
<th colspan="3">Complex</th>
|
||||||
|
<th rowspan="2">Handing Exception</th>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>Type</th><th>Grd</th><th>SR</th>
|
||||||
|
<th>Type</th><th>Grd</th><th>SR</th>
|
||||||
|
<th>Type</th><th>Grd</th><th>SR</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody>
|
||||||
|
<!-- Closed-source Models -->
|
||||||
|
<tr><td colspan="11"><em>Closed-source Models</em></td></tr>
|
||||||
|
<tr>
|
||||||
|
<td>GPT-4o (Hurst et al., 2024)</td>
|
||||||
|
<td>49.3</td><td>16.7</td><td>4.6</td>
|
||||||
|
<td>56.6</td><td>13.5</td><td>19.8</td>
|
||||||
|
<td>49.0</td><td>14.6</td><td>7.4</td>
|
||||||
|
<td>85.1</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Gemini 2.0 (Pichai et al., 2024)</td>
|
||||||
|
<td>89.2</td><td>49.4</td><td>34.7</td>
|
||||||
|
<td>84.1</td><td>54.2</td><td>51.4</td>
|
||||||
|
<td>83.3</td><td>50.3</td><td>42.0</td>
|
||||||
|
<td>73.7</td>
|
||||||
|
</tr>
|
||||||
|
<!-- Open-source Models -->
|
||||||
|
<tr><td colspan="11"><em>Open-source Models</em></td></tr>
|
||||||
|
<tr>
|
||||||
|
<td>InternVL-2-8B (Chen et al., 2024)</td>
|
||||||
|
<td>30.1</td><td>2.8</td><td>1.3</td>
|
||||||
|
<td>37.1</td><td>4.0</td><td>15.8</td>
|
||||||
|
<td>17.1</td><td>6.0</td><td>1.3</td>
|
||||||
|
<td>70.8</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Qwen2-VL-7B (Wang et al., 2024)</td>
|
||||||
|
<td>71.7</td><td>41.0</td><td>28.1</td>
|
||||||
|
<td>73.6</td><td>43.9</td><td>41.5</td>
|
||||||
|
<td>65.6</td><td>28.7</td><td>21.2</td>
|
||||||
|
<td>68.3</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Qwen2.5-VL-7B (Bai et al., 2025)</td>
|
||||||
|
<td>94.3</td><td>92.6</td><td>76.3</td>
|
||||||
|
<td>89.3</td><td><u>95.7</u></td><td>83.6</td>
|
||||||
|
<td>86.6</td><td>69.6</td><td>60.0</td>
|
||||||
|
<td>67.0</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>UI-TARS-7B (Qin et al., 2025)</td>
|
||||||
|
<td>83.5</td><td>84.9</td><td>73.3</td>
|
||||||
|
<td>76.6</td><td>85.6</td><td>69.8</td>
|
||||||
|
<td>91.4</td><td>69.1</td><td>67.0</td>
|
||||||
|
<td>3.6</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>UI-TARS-1.5-7B (Seed, 2025)</td>
|
||||||
|
<td>85.6</td><td>96.2</td><td>81.5</td>
|
||||||
|
<td>78.6</td><td>92.1</td><td>72.2</td>
|
||||||
|
<td><b>94.7</b></td><td>74.3</td><td>71.1</td>
|
||||||
|
<td>1.0</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>MiMo-VL-7B-SFT (Xiaomi, 2025)</td>
|
||||||
|
<td>93.0</td><td>77.9</td><td>65.3</td>
|
||||||
|
<td>89.7</td><td>85.7</td><td>75.4</td>
|
||||||
|
<td>89.1</td><td>80.1</td><td>71.0</td>
|
||||||
|
<td>57.0</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>AgentCPM-GUI (Zhang et al., 2025)</td>
|
||||||
|
<td>84.3</td><td>92.2</td><td>75.1</td>
|
||||||
|
<td>70.4</td><td>80.7</td><td>56.0</td>
|
||||||
|
<td>72.3</td><td>54.6</td><td>39.4</td>
|
||||||
|
<td>2.4</td>
|
||||||
|
</tr>
|
||||||
|
<!-- MagicGUI -->
|
||||||
|
<tr style="background-color:#e8eafc;">
|
||||||
|
<td>MagicGUI-CPT</td>
|
||||||
|
<td><b>98.5</b></td><td><b>98.5</b></td><td><b>97.2</b></td>
|
||||||
|
<td><b>95.5</b></td><td><b>96.3</b></td><td><b>92.9</b></td>
|
||||||
|
<td>88.5</td><td><b>82.3</b></td><td><b>72.9</b></td>
|
||||||
|
<td><b>93.2</b></td>
|
||||||
|
</tr>
|
||||||
|
<tr style="background-color:#e8eafc;">
|
||||||
|
<td>MagicGUI-RFT</td>
|
||||||
|
<td><b>99.7</b></td><td>97.5</td><td><b>97.5</b></td>
|
||||||
|
<td><b>97.2</b></td><td>95.6</td><td><b>94.0</b></td>
|
||||||
|
<td>92.1</td><td>80.4</td><td><b>74.1</b></td>
|
||||||
|
<td>92.1</td>
|
||||||
|
</tr>
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Performance comparison on open-source AndroidControl and GUI-Odyssey datasets.
|
||||||
|
|
||||||
|
<table>
|
||||||
|
<thead>
|
||||||
|
<tr>
|
||||||
|
<th rowspan="2">Agent Models</th>
|
||||||
|
<th colspan="2">AC-Low</th>
|
||||||
|
<th colspan="2">AC-High</th>
|
||||||
|
<th colspan="2">GUI-Odyssey</th>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>Type</th><th>SR</th>
|
||||||
|
<th>Type</th><th>SR</th>
|
||||||
|
<th>Type</th><th>SR</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody>
|
||||||
|
<!-- Closed-source Models -->
|
||||||
|
<tr><td colspan="7"><em>Closed-source Models</em></td></tr>
|
||||||
|
<tr>
|
||||||
|
<td>GPT-4o (Hurst et al., 2024)</td>
|
||||||
|
<td>-</td><td>19.5</td>
|
||||||
|
<td>-</td><td>20.8</td>
|
||||||
|
<td>-</td><td>20.4</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Gemini 2.0 (Pichai et al., 2024)</td>
|
||||||
|
<td>-</td><td>28.5</td>
|
||||||
|
<td>-</td><td>60.2</td>
|
||||||
|
<td>-</td><td>3.3</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Claude 2.0 (Anthropic, 2024)</td>
|
||||||
|
<td>-</td><td>28.5</td>
|
||||||
|
<td>-</td><td>12.5</td>
|
||||||
|
<td>60.9</td><td>-</td>
|
||||||
|
</tr>
|
||||||
|
<!-- Open-source Models -->
|
||||||
|
<tr><td colspan="7"><em>Open-source Models</em></td></tr>
|
||||||
|
<tr>
|
||||||
|
<td>Qwen2-VL-7B (Wang et al., 2024)</td>
|
||||||
|
<td>55.7</td><td>36.2</td>
|
||||||
|
<td>45.8</td><td>21.2</td>
|
||||||
|
<td>58.6</td><td>13.3</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Qwen2.5-VL-7B (Bai et al., 2025)</td>
|
||||||
|
<td>94.1</td><td>85.0</td>
|
||||||
|
<td>75.1</td><td>62.9</td>
|
||||||
|
<td>59.5</td><td>46.3</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Aguvis-7B (Xu et al., 2024)</td>
|
||||||
|
<td>93.9</td><td>89.4</td>
|
||||||
|
<td>65.6</td><td>54.2</td>
|
||||||
|
<td>26.7</td><td>13.5</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>OS-Atlas-7B (Wu et al., 2024)</td>
|
||||||
|
<td>73.0</td><td>67.3</td>
|
||||||
|
<td>70.4</td><td>56.5</td>
|
||||||
|
<td>91.8*</td><td>76.8*</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>UI-TARS-7B (Qin et al., 2025)</td>
|
||||||
|
<td>95.2</td><td>91.8</td>
|
||||||
|
<td>81.6</td><td>74.4</td>
|
||||||
|
<td>86.1</td><td>67.9</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>AgentCPM-GUI (Zhang et al., 2025)</td>
|
||||||
|
<td>94.4</td><td>90.2</td>
|
||||||
|
<td>77.7</td><td>69.2</td>
|
||||||
|
<td><b>90.9</b></td><td><b>75.0</b></td>
|
||||||
|
</tr>
|
||||||
|
<!-- MagicGUI -->
|
||||||
|
<tr style="background-color:#e8eafc;">
|
||||||
|
<td>MagicGUI-CPT</td>
|
||||||
|
<td>94.5</td><td>86.7</td>
|
||||||
|
<td>84.6</td><td>73.1</td>
|
||||||
|
<td><b>90.4</b></td><td>73.5</td>
|
||||||
|
</tr>
|
||||||
|
<tr style="background-color:#e8eafc;">
|
||||||
|
<td>MagicGUI-RFT</td>
|
||||||
|
<td><b>97.2</b></td><td><b>93.5</b></td>
|
||||||
|
<td><b>84.7</b></td><td><b>76.3</b></td>
|
||||||
|
<td>89.7</td><td><b>74.3</b></td>
|
||||||
|
</tr>
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
## License
|
||||||
|
|
||||||
|
* This project is licensed under the [Apache-2.0](./LICENSE) license. The model weights are fully open for academic research, and commercial use licenses can be applied for by contacting magicgui@honor.com. This project uses the pre-trained Qwen2VL-7B-Instruct for initialization, which is also licensed under the Apache- 2.0 License.
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
If **MagicGUI** is useful for your research, please cite:
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@misc{tang2025magicguifoundationalmobilegui,
|
||||||
|
title={MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning},
|
||||||
|
author={Liujian Tang and Shaokang Dong and Yijia Huang and Minqi Xiang and Hongtao Ruan and Bin Wang and Shuo Li and Zhiheng Xi and Zhihui Cao and Hailiang Pang and Heng Kong and He Yang and Mingxu Chai and Zhilin Gao and Xingyu Liu and Yingnan Fu and Jiaming Liu and Xuanjing Huang and Yu-Gang Jiang and Tao Gui and Qi Zhang and Kang Wang and Yunke Zhang and Yuran Wang},
|
||||||
|
year={2025},
|
||||||
|
eprint={2508.03700},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.HC},
|
||||||
|
url={https://arxiv.org/abs/2508.03700},
|
||||||
|
}
|
||||||
|
```
|
||||||
16
added_tokens.json
Normal file
16
added_tokens.json
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
{
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
{
|
||||||
|
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||||
|
}
|
||||||
49
config.json
Normal file
49
config.json
Normal file
@@ -0,0 +1,49 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "/opt/nas/p/mm/ie_env/ruanhongtao/work_dirs/Qwen2_VL_checkpoints/Qwen2-VL-7B_RPA_Aug_annealing_v702_20250705/qwen2-vl-7b-instruct/v1-20250708-001845/checkpoint-1783",
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 3584,
|
||||||
|
"image_token_id": 151655,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 18944,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen2_vl",
|
||||||
|
"num_attention_heads": 28,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 4,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": {
|
||||||
|
"mrope_section": [
|
||||||
|
16,
|
||||||
|
24,
|
||||||
|
24
|
||||||
|
],
|
||||||
|
"rope_type": "default",
|
||||||
|
"type": "default"
|
||||||
|
},
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": 32768,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.50.0.dev0",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"video_token_id": 151656,
|
||||||
|
"vision_config": {
|
||||||
|
"in_chans": 3,
|
||||||
|
"model_type": "qwen2_vl",
|
||||||
|
"spatial_patch_size": 14,
|
||||||
|
"torch_dtype": "bfloat16"
|
||||||
|
},
|
||||||
|
"vision_end_token_id": 151653,
|
||||||
|
"vision_start_token_id": 151652,
|
||||||
|
"vision_token_id": 151654,
|
||||||
|
"vocab_size": 152064
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
11
generation_config.json
Normal file
11
generation_config.json
Normal file
@@ -0,0 +1,11 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"max_new_tokens": 2048,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.01,
|
||||||
|
"top_k": 1,
|
||||||
|
"top_p": 0.001,
|
||||||
|
"transformers_version": "4.50.0.dev0"
|
||||||
|
}
|
||||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1a630664b92c0264b403a54404707001ba374c619e558e8dc99546edfa24f0bc
|
||||||
|
size 4966659944
|
||||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:06b80214431ec0222329616c76a270b6c9265ca12de94d6e3879ba2d5fb9147c
|
||||||
|
size 4991495816
|
||||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e66d7af94dcc4c32c862b2c9fbc742cbf8f14ccc7be98c6b3cb1f69ac8bc2654
|
||||||
|
size 4932751040
|
||||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e905a6dab8eee5b2811ecb1c522182e401d67cb7c99c01562671e0f9dd43a700
|
||||||
|
size 1691924384
|
||||||
737
model.safetensors.index.json
Normal file
737
model.safetensors.index.json
Normal file
@@ -0,0 +1,737 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 16582751232
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.merger.ln_q.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
29
preprocessor_config.json
Normal file
29
preprocessor_config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"do_convert_rgb": true,
|
||||||
|
"do_normalize": true,
|
||||||
|
"do_rescale": true,
|
||||||
|
"do_resize": true,
|
||||||
|
"image_mean": [
|
||||||
|
0.48145466,
|
||||||
|
0.4578275,
|
||||||
|
0.40821073
|
||||||
|
],
|
||||||
|
"image_processor_type": "Qwen2VLImageProcessor",
|
||||||
|
"image_std": [
|
||||||
|
0.26862954,
|
||||||
|
0.26130258,
|
||||||
|
0.27577711
|
||||||
|
],
|
||||||
|
"max_pixels": 12845056,
|
||||||
|
"merge_size": 2,
|
||||||
|
"min_pixels": 3136,
|
||||||
|
"patch_size": 14,
|
||||||
|
"processor_class": "Qwen2VLProcessor",
|
||||||
|
"resample": 3,
|
||||||
|
"rescale_factor": 0.00392156862745098,
|
||||||
|
"size": {
|
||||||
|
"longest_edge": 12845056,
|
||||||
|
"shortest_edge": 3136
|
||||||
|
},
|
||||||
|
"temporal_patch_size": 2
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
|
||||||
|
size 11420371
|
||||||
145
tokenizer_config.json
Normal file
145
tokenizer_config.json
Normal file
@@ -0,0 +1,145 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 32768,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"processor_class": "Qwen2VLProcessor",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user