Skip to content

GitLab

Commit 81028572 authored by luopl's avatar luopl
Browse files

init

parents
Pipeline #1722 canceled with stages
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 1030 additions and 0 deletions
.gitignore 0 → 100644
View file @ 81028572
.idea/
__pycache__/
*.egg-info/
*.args
LICENSE 0 → 100644
View file @ 81028572
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.
README.md 0 → 100644
View file @ 81028572
# Ovis
## 论文
Ovis: Structural Embedding Alignment for Multimodal Large Language Model
https://arxiv.org/abs/2405.20797
## 模型结构
Ovis (Open VISion) 是一种新颖的多模态大型语言模型 (MLLM) 架构，旨在结构化地对齐视觉和文本嵌入。Ovis借鉴了大语言模型中的文本嵌入策略，引入了可学习的视觉嵌入表，将连续的视觉特征先转换为概率化的视觉token，再经由视觉嵌入表多次索引加权得到结构化的视觉嵌入。
<div align=center>
<img src="./assets/ovis-illustration.png"/>
</div>
## 算法原理
如上图所示，Ovis通过设计一种新的多模态架构，将视觉和文本信息融合在同一个嵌入空间中。这意味着模型能够学习到如何将图片和文本的信息统一映射到相同的向量表示，这种对齐的目的是为了在视觉和文本之间实现更好的交互和信息传递。视觉嵌入通常通过视觉编码器（例如CLIP、ViT）生成，文本嵌入通过LLM（如GPT、BERT）生成，Ovis则通过特殊的对齐层或映射模块进行对齐。
与传统简单的多模态对齐不同，Ovis特别强调视觉和文本嵌入的结构性对齐。这种对齐不仅仅是将两种模态映射到同一向量空间，而是保留了每种模态特有的结构信息。例如，文本的语法结构和图像的空间信息会在对齐过程中保持，以确保模型在进行推理时能够利用这些结构性信息。
Ovis模型采用层次化的多模态融合策略，这意味着视觉和文本信息的交互在多个层次上进行。不同的层次负责捕捉不同的语义信息，从低层的局部特征到高层的全局语义。这样能够确保模型在处理复杂多模态任务时，有足够的表达能力来捕捉模态间的细微差异和关联。
Ovis引入了指令微调技术，通过给模型提供明确的任务指令，帮助其更好地理解不同任务需求，并在推理过程中实现更强的通用性。结合DPO（Direct Preference Optimization）训练方法，模型能够通过对比学习更精细地优化多模态任务中的决策，提升推理效果。
为了提高模型的泛化能力，Ovis在训练过程中采用了大量多样化的数据，包括高分辨率图像、不同领域的文本描述以及细粒度的视觉特征。这种多样化数据的使用，帮助模型在面对不同模态和领域的任务时都能表现出较强的适应能力。
## 环境配置
### Docker（方法一）
推荐使用docker方式运行， 此处提供[光源](https://www.sourcefind.cn/#/service-details)拉取docker镜像的地址与使用步骤
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
docker run -it --shm-size=1024G -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name ovis_pytorch <your IMAGE ID> bash # <your IMAGE ID>为以上拉取的docker的镜像ID替换，本镜像为：a4dd5be0ca23
cd /path/your_code_data/
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
pip install e .
cd VLMEvalKit
pip install e .
```
Tips:以上dtk驱动、python、torch、vllm等DCU相关工具版本需要严格一一对应。
### Dockerfile（方法二）
此处提供dockerfile的使用方法
```
docker build -t ovis:latest .
docker run -it --shm-size=1024G -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name ovis_pytorch ovis bash
cd /path/your_code_data/
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
pip install e .
cd VLMEvalKit
pip install e .
```
### Anaconda（方法三）
此处提供本地配置、编译的详细步骤，例如：
关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
```
DTK驱动:dtk24.04.1
python:3.10
torch:2.1.0
deepspeed:0.12.3
```
`Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应`
其它非深度学习库参照requirement.txt安装：
```
cd /path/your_code_data/
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
pip install e .
cd VLMEvalKit
pip install e .
```
## 数据集
多模态精度评估可使用VLMEvalKit库进行测试，测试运行时会自动下载MMStar、OCRBench、AID2、HallusionBench等数据，
默认路径为/root/LMUData，数据下载[SCNet链接](http://113.200.138.88:18080/aidatasets/project-dependency/lmudata/-/tree/main)
精度评估数据目录结构如下：
```
── LMUData
├── AI2D_TEST.tsv
├── MMStar.tsv
├── OCRBench.tsv
└── ...
```
## 训练
官方暂未提供
## 推理
infer:
```
#注意：根据自己的模型切换文件中的模型位置并调整其他参数
cd /path/your_code_data/
python ovis/serve/runner.py
```
根据自己的要求输入image和text。
eval:
若使用本地下载好的模型权重，注意修改VLMEvalKit/vlmeval/vlm/config.py文件中以下代码行中的model_path为自己的本地模型地址
'Ovis1.6-Gemma2-9B': partial(Ovis1_6, model_path='AIDC-AI/Ovis1.6-Gemma2-9B')
```
cd VLMEvalKit
python run.py --data MMStar AI2D_TEST OCRBench HallusionBench --model Ovis1.6-Gemma2-9B --verbose
```
## result
使用的加速卡:1张 K100_AI 模型：Ovis1.6-Gemma2-9B
输入：
image :
<div align=left>
<img src="./OST_120.png"/>
</div>
text:
'Please describe this image'
output:
<div align=left>
<img src="./assets/result.png"/>
</div>
### 精度
使用的加速卡:1张 K100_AI 模型：Ovis1.6-Gemma2-9B
| MLLM | AI2D | OCRBench | MMStar | HallusionBench |
|------------|------|----------|--------|----------------|
| Ovis1.6-Gemma2-9B | 84.6 | 82.6 | 62.1 | 67.7 |
## 应用场景
### 算法类别
`对话问答`
### 热点应用行业
`科研,教育,政府,金融`
## 预训练权重
模型Huggingface下载链接[Ovis1.6-Gemma2-9B|HF](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B)
模型SCNet快速下载链接[Ovis1.6-Gemma2-9B|SCNet](http://113.200.138.88:18080/aimodels/aidc-ai/-/tree/main/Ovis1.6-Gemma2-9B?ref_type=heads)
## 源码仓库及问题反馈
- https://developer.hpccube.com/codes/modelzoo/ovis_pytorch
## 参考资料
- https://github.com/AIDC-AI/Ovis
- https://github.com/open-compass/VLMEvalKit
README_ori.md 0 → 100644
View file @ 81028572
# Ovis: Structural Embedding Alignment for Multimodal Large Language Model
Ovis (Open VISion) is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings. For a comprehensive introduction, please refer to the [Ovis paper](https://arxiv.org/abs/2405.20797).
<div style="text-align: center;">
<img style="max-width: 100%;" src="docs/ovis-illustration.png" alt="Ovis Illustration"/>
</div>
## Release
- [09/19] 🔥 Announcing Ovis1.6 ([Model](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B), [Demo](https://huggingface.co/spaces/AIDC-AI/Ovis1.6-Gemma2-9B))! This latest release further enhances high-resolution image processing, is trained on a larger, more diverse, and higher-quality dataset, and refines the training process with DPO training following instruction-tuning.
- [07/24] 🔥 Introducing Ovis1.5, featuring improved high-resolution image processing and optimized training data for enhanced performance.
- [06/14] 🔥 Launch of Ovis1.0, the inaugural version of the Ovis model.
## Contents
- [Install](#install)
- [Model](#model)
- [Performance](#performance)
- [Finetune](#finetune)
- [Inference](#inference)
- [Citation](#citation)
- [Team](#team)
- [License](#license)
## Install
Ovis has been tested with Python 3.10, Torch 2.2.0, Transformers 4.44.2, and DeepSpeed 0.14.4. For a comprehensive list of package dependencies, please consult the `requirements.txt` file. Before finetuning or inference, please install Ovis as follows.
```bash
git clone git@github.com:AIDC-AI/Ovis.git
conda create -n ovis python=3.10 -y
conda activate ovis
cd Ovis
pip install -r requirements.txt
pip install -e .
```
## Model
Ovis can be instantiated with popular LLMs. We provide the following Ovis MLLMs:
| Ovis MLLMs | ViT | LLM | Model Weights |
|:------------------|:-----------:|:------------------:|:---------------------------------------------------------------:|
| Ovis1.6-Gemma2-9B | Siglip-400M | Gemma2-9B-It | [Huggingface](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B) |
## Performance
With just **10B** parameters, Ovis1.6-Gemma2-9B leads the [OpenCompass](https://github.com/open-compass/VLMEvalKit) benchmark among open-source MLLMs within **30B** parameters.
![performance-Ovis1_6-Gemma2-9B](docs/performance/Ovis1_6-Gemma2-9B.png)
## Finetune
Coming soon
## Inference
We provide an inference wrapper in `ovis/serve/runner.py`, which can be used as:
```python
from PIL import Image
from ovis.serve.runner import RunnerArguments, OvisRunner
image = Image.open('IMAGE_PATH')
text = 'PROMPT'
runner_args = RunnerArguments(model_path='MODEL_PATH')
runner = OvisRunner(runner_args)
generation = runner.run([image, text])
```
Based on [Gradio](https://github.com/gradio-app/gradio), Ovis can also be accessed via a web user interface:
```bash
python ovis/serve/server.py --model_path MODEL_PATH --port PORT
```
## Citation
If you find Ovis useful, please cite the paper
```
@article{lu2024ovis,
title={Ovis: Structural Embedding Alignment for Multimodal Large Language Model},
author={Shiyin Lu and Yang Li and Qing-Guo Chen and Zhao Xu and Weihua Luo and Kaifu Zhang and Han-Jia Ye},
year={2024},
journal={arXiv:2405.20797}
}
```
## Team
This work is a collaborative effort by the MarcoVL team. We would also like to provide links to the following MLLM papers from our team:
- [Parrot: Multilingual Visual Instruction Tuning](https://arxiv.org/abs/2406.02539)
- [Wings: Learning Multimodal LLMs without Text-only Forgetting](https://arxiv.org/abs/2406.03496)
## License
The project is licensed under the Apache 2.0 License and is restricted to uses that comply with the license agreements of Gemma2 and Siglip.
VLMEvalKit/.github/workflows/lint.yml 0 → 100644
View file @ 81028572
name: lint
on: [push, pull_request]
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
lint:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
- name: Set up Python 3.7
uses: actions/setup-python@v2
with:
python-version: 3.7
- name: Install pre-commit hook
run: |
pip install pre-commit
pre-commit install
- name: Linting
run: pre-commit run --all-files
VLMEvalKit/.gitignore 0 → 100644
View file @ 81028572
.idea/
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
.vscode/
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/#use-with-ide
.pdm.toml
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
# Images
images/
scripts/*ttf
.history
cache_dir/*
# Evaluation Outputs
outputs/*
VLMEvalKit/.pre-commit-config.yaml 0 → 100644
View file @ 81028572
exclude: |
(?x)^(
scripts/|
assets/|
vlmeval/config.py
)
repos:
- repo: https://github.com/PyCQA/flake8
rev: 5.0.4
hooks:
- id: flake8
args: ["--max-line-length=120", "--ignore=F401,F403,F405,E402,E722,E741,W503"]
exclude: ^configs/
- repo: https://github.com/pre-commit/mirrors-yapf
rev: v0.30.0
hooks:
- id: yapf
args: ["--style={column_limit=120}"]
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v3.1.0
hooks:
- id: trailing-whitespace
- id: check-yaml
- id: end-of-file-fixer
- id: requirements-txt-fixer
- id: double-quote-string-fixer
- id: check-merge-conflict
- id: fix-encoding-pragma
args: ["--remove"]
- id: mixed-line-ending
args: ["--fix=lf"]
VLMEvalKit/LICENSE 0 → 100644
View file @ 81028572
Copyright 2023 VLMEvalKit Authors. All rights reserved.
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 2023 VLMEvalKit Authors.
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.
VLMEvalKit/README.md 0 → 100644
View file @ 81028572
This diff is collapsed.
VLMEvalKit/assets/LOGO.svg 0 → 100644
View file @ 81028572
This diff is collapsed.
VLMEvalKit/docs/en/.readthedocs.yaml 0 → 100644
View file @ 81028572
version: 2
# Set the version of Python and other tools you might need
build:
os: ubuntu-22.04
tools:
python: "3.8"
formats:
- epub
sphinx:
configuration: docs/en/conf.py
python:
install:
- requirements: requirements/docs.txt
VLMEvalKit/docs/en/Makefile 0 → 100644
View file @ 81028572
# Minimal makefile for Sphinx documentation
#
# You can set these variables from the command line, and also
# from the environment for the first two.
SPHINXOPTS ?=
SPHINXBUILD ?= sphinx-build
SOURCEDIR = .
BUILDDIR = _build
# Put it first so that "make" without argument is like "make help".
help:
@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
.PHONY: help Makefile
# Catch-all target: route all unknown targets to Sphinx using the new
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
%: Makefile
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
VLMEvalKit/docs/en/_static/css/readthedocs.css 0 → 100644
View file @ 81028572
.header-logo {
background-image: url("../image/logo.svg");
background-size: 275px 80px;
height: 80px;
width: 275px;
}
@media screen and (min-width: 1100px) {
.header-logo {
top: -25px;
}
}
pre {
white-space: pre;
}
@media screen and (min-width: 2000px) {
.pytorch-content-left {
width: 1200px;
margin-left: 30px;
}
article.pytorch-article {
max-width: 1200px;
}
.pytorch-breadcrumbs-wrapper {
width: 1200px;
}
.pytorch-right-menu.scrolling-fixed {
position: fixed;
top: 45px;
left: 1580px;
}
}
article.pytorch-article section code {
padding: .2em .4em;
background-color: #f3f4f7;
border-radius: 5px;
}
/* Disable the change in tables */
article.pytorch-article section table code {
padding: unset;
background-color: unset;
border-radius: unset;
}
table.autosummary td {
width: 50%
}
img.align-center {
display: block;
margin-left: auto;
margin-right: auto;
}
article.pytorch-article p.rubric {
font-weight: bold;
}
VLMEvalKit/docs/en/_static/image/logo.svg 0 → 100644
View file @ 81028572
This diff is collapsed.
VLMEvalKit/docs/en/_static/image/logo_icon.svg 0 → 100644
View file @ 81028572
<?xml version="1.0" encoding="UTF-8"?>
<svg id="_图层_2" data-name="图层 2" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 34.59 36">
<defs>
<style>
.cls-1 {
fill: #36569b;
}
.cls-2 {
fill: #1b3882;
}
.cls-3 {
fill: #5878b4;
}
</style>
</defs>
<g id="_图层_1-2" data-name="图层 1">
<g>
<g id="_3" data-name="3">
<path class="cls-3" d="m16.53,22.65l-6.37,3.07,5.27-.16,1.1-2.91Zm-4.19,10.95l1.12-2.91-5.27.17,4.15,2.74Zm9.3-.29l6.37-3.07-5.27.16-1.1,2.91Zm4.19-10.95l-1.12,2.91,5.27-.17-4.15-2.74Zm5.72,3.81l-7.08.23-1.73-1.14,1.5-3.95-2.06-1.36-3.16,1.53-1.48,3.89-2.67,1.29-7.14.23-3.16,1.53,2.07,1.36,7.13-.23h0s1.69,1.11,1.69,1.11l-1.51,3.98,2.06,1.36,3.16-1.53,1.5-3.95h0s2.56-1.24,2.56-1.24h0s7.23-.24,7.23-.24l3.16-1.53-2.06-1.36Zm-11.29,2.56c-.99.48-2.31.52-2.96.1-.65-.42-.37-1.15.62-1.63.99-.48,2.31-.52,2.96-.1.65.42.37,1.15-.62,1.63Z"/>
</g>
<g id="_2" data-name="2">
<path class="cls-1" d="m33.5,19.84l-1.26-6.51-1.46,1.88,2.72,4.63Zm-6.05-14.69l-4.16-2.74,2.71,4.64,1.45-1.89Zm-6.73.58l1.26,6.51,1.46-1.88-2.72-4.63Zm6.05,14.69l4.16,2.74-2.71-4.64-1.45,1.89Zm7.19,1.91l-3.63-6.2h0s-.53-2.74-.53-2.74l1.96-2.56-.63-3.23-2.07-1.36-1.96,2.56-1.69-1.11-3.71-6.33-2.07-1.36.63,3.23,3.68,6.28h0s.51,2.62.51,2.62h0s-1.99,2.6-1.99,2.6l.63,3.23,2.06,1.36,1.95-2.54,1.73,1.14,3.69,6.29,2.07,1.36-.63-3.23Zm-6.47-7.7c-.65-.42-1.33-1.59-1.52-2.6-.2-1.01.17-1.49.81-1.06.65.42,1.33,1.59,1.52,2.6.2,1.01-.17,1.49-.81,1.06Z"/>
</g>
<g id="_1" data-name="1">
<path class="cls-2" d="m11.96,2.82l-6.37,3.07,3.81,1.74,2.55-4.81ZM1.07,14.37l1.26,6.53,2.56-4.8-3.82-1.73Zm7.99,9.59l6.37-3.07-3.81-1.74-2.55,4.81Zm10.89-11.55l-1.26-6.53-2.56,4.8,3.82,1.73Zm.45,2.53l-5.13-2.32h0s-.53-2.71-.53-2.71l3.47-6.53-.63-3.24-3.16,1.53-3.42,6.43-2.67,1.29h0s-5.17-2.34-5.17-2.34l-3.16,1.53.63,3.24,5.17,2.33.51,2.65h0s-3.49,6.57-3.49,6.57l.63,3.24,3.16-1.53,3.46-6.52,2.56-1.24h0s5.24,2.37,5.24,2.37l3.16-1.53-.63-3.24Zm-9.52.24c-.99.48-1.95.04-2.14-.97-.2-1.01.44-2.22,1.43-2.69.99-.48,1.95-.04,2.14.97.2,1.01-.44,2.22-1.43,2.7Z"/>
</g>
</g>
</g>
</svg>
VLMEvalKit/docs/en/_static/js/custom.js 0 → 100644
View file @ 81028572
var collapsedSections = [];
$(document).ready(function () {
$('.model-summary').DataTable({
"stateSave": false,
"lengthChange": false,
"pageLength": 20,
"order": []
});
});
VLMEvalKit/docs/en/_templates/404.html 0 → 100644
View file @ 81028572
{% extends "layout.html" %}
{% block body %}
<h1>Page Not Found</h1>
<p>
The page you are looking for cannot be found.
</p>
<p>
If you just switched documentation versions, it is likely that the page you were on is moved. You can look for it in
the content table left, or go to <a href="{{ pathto(root_doc) }}">the homepage</a>.
</p>
<!-- <p>
If you cannot find documentation you want, please <a
href="">open an issue</a> to tell us!
</p> -->
{% endblock %}
VLMEvalKit/docs/en/_templates/autosummary/class.rst 0 → 100644
View file @ 81028572
.. role:: hidden
:class: hidden-section
.. currentmodule:: {{ module }}
{{ name | underline}}
.. autoclass:: {{ name }}
:members:
..
autogenerated from _templates/autosummary/class.rst
note it does not have :inherited-members:
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment