Skip to content

GitLab

Commit 34164470 authored by chenzk's avatar chenzk
Browse files

v1.0

parents
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 1310 additions and 0 deletions
LICENSE 0 → 100644
View file @ 34164470
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 @ 34164470
# MobileVLM
MobileVLM V2为移动端部署而设计，在资源受限的设备上展现出出色的性能，计算量1.7B达到普通VLM3B大小的水平，与LLaMA2共享相同分词器，便于知识蒸馏，在精度和性能上达到了一个新的平衡点，以下步骤适于推理。
## 论文
`MobileVLM V2: Faster and Stronger Baseline for Vision Language Model`
- https://arxiv.org/pdf/2402.03766.pdf
## 模型结构
MobileVLM V2的结构采用CLIP ViT-L/14作为视觉编码器，这种编码器经过大规模的图像-文本对比预训练，对VLM非常有效。该模型包括预训练的视觉编码器、MobileLLaMA作为语言模型，以及轻量级的下采样投影器，其中投影器通过特征变换、标记压缩和位置信息增强三个模块实现视觉和语言的对齐。
<div align=center>
<img src="./doc/mobilevlm.png"/>
</div>
## 算法原理
MobileVLM V2的训练过程分为预训练和多任务训练两个阶段：在预训练阶段，只允许投影器和LLM进行训练，MobileVLM V2使用ShareGPT4V-PT数据集，包含120万图像-文本对，该数据集有助于提高模型的图像-文本对齐能力，这是多模态表示学习的一个关键方面；图像-文本对齐学习阶段后，精心选择各种任务数据集训练，赋予模型多任务分析和图像-文本对话的能力。
<div align=center>
<img src="./doc/clip.png"/>
</div>
## 环境配置
```
mv mobilevlm_pytorch MobileVLM # 去框架名后缀
```
### Docker（方法一）
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk23.10-py38
# <your IMAGE ID>为以上拉取的docker的镜像ID替换，本镜像为：ffa1f63239fc
docker run -it --shm-size=32G -v $PWD/MobileVLM:/home/MobileVLM -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name mobilevlm <your IMAGE ID> bash
cd /home/MobileVLM
pip install -r requirements.txt
# flash_attn2、bitsandbytes可从whl.zip文件里获取安装：
pip install flash_attn-2.0.4_torch2.1_dtk2310-cp38-cp38-linux_x86_64.whl
pip install bitsandbytes-0.43.0-py3-none-any.whl
```
### Dockerfile（方法二）
```
cd MobileVLM/docker
docker build --no-cache -t mobilevlm:latest .
docker run --shm-size=32G --name mobilevlm -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video -v $PWD/../../MobileVLM:/home/MobileVLM -it mobilevlm bash
# 若遇到Dockerfile启动的方式安装环境需要长时间等待，可注释掉里面的pip安装，启动容器后再安装python库：pip install -r requirements.txt。
# flash_attn2、bitsandbytes可从whl.zip文件里获取安装：
pip install flash_attn-2.0.4_torch2.1_dtk2310-cp38-cp38-linux_x86_64.whl
pip install bitsandbytes-0.43.0-py3-none-any.whl
```
### Anaconda（方法三）
1、关于本项目DCU显卡所需的特殊深度学习库可从光合开发者社区下载安装：
- https://developer.hpccube.com/tool/
```
DTK驱动:dtk23.10
python:python3.8
torch:2.1.0
torchvision:0.16.0
triton:2.1.0
apex:0.1
deepspeed:0.12.3
flash_attn:2.0.4
bitsandbytes:0.43.0
```
```
# flash_attn2、bitsandbytes可从whl.zip文件里获取安装：
pip install flash_attn-2.0.4_torch2.1_dtk2310-cp38-cp38-linux_x86_64.whl
pip install bitsandbytes-0.43.0-py3-none-any.whl
```
`Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应。`
2、其它非特殊库参照requirements.txt安装
```
pip install -r requirements.txt # requirements.txt
```
## 数据集
- 建立data文件夹放置数据:
- `cd MobileVLM && mkdir -p data/pretrain_data data/finetune_data data/benchmark_data` # work_dir为MobileVLM
- 预训练数据
- `cd ${work_dir}/data/pretrain_data`
- download the ShareGPT4V-PT from [here](https://huggingface.co/datasets/Lin-Chen/ShareGPT4V/blob/main/share-captioner_coco_lcs_sam_1246k_1107.json), which is provided by ShareGPT4V team.
- 多任务训练数据
- `cd ${work_dir}/data/finetune_data`
- download the annotation of our MobileVLM_V2_FT_Mix2M data from huggingface [here](https://huggingface.co/datasets/mtgv/MobileVLM_V2_FT_Mix2M), and download the images from constituting datasets:
[Text-VQA](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip),
[IConQA](https://drive.google.com/file/d/1Xqdt1zMcMZU5N_u1SAIjk-UAclriynGx/edit), [SQA](https://drive.google.com/drive/folders/1w8imCXWYn2LxajmGeGH_g5DaL2rabHev), [SBU](https://huggingface.co/datasets/sbu_captions), follow [ShareGPT4V](https://github.com/InternLM/InternLM-XComposer/blob/main/projects/ShareGPT4V/docs/Data.md) to download images from:
[LAION-CC-SBU-558K](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain/blob/main/images.zip), [COCO](http://images.cocodataset.org/zips/train2017.zip), [WebData](https://drive.google.com/drive/folders/1tCUQ-sq6vdshZVkF0ZeF3K4eztkXJgax?usp=sharing), [SAM](https://drive.google.com/file/d/1dKumdOKSXtV7lIXdrG7jsIK_z2vZv2gs/view?usp=drive_link), [GQA](https://downloads.cs.stanford.edu/nlp/data/gqa/images.zip), [OCR-VQA](https://drive.google.com/drive/folders/1_GYPY5UkUy7HIcR0zq3ZCFgeZN7BAfm_?usp=sharing), [TextVQA](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip), [VisualGnome](https://cs.stanford.edu/people/rak248/VG_100K_2) ([Part1](https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip), [Part2](https://cs.stanford.edu/people/rak248/VG_100K_2/images2.zip))
- benchmark测试数据
- We evaluate models on a diverse set of 6 benchmarks, *i.e.* GQA, MMBench, MME, POPE, SQA, TextVQA. We do not evaluate using beam search to make the inference process consistent with the chat demo of real-time outputs. You should follow these instructions to manage the datasets.
- <details>
<summary> Data Download Instructions </summary>
- download some useful [data/scripts](https://github.com/Meituan-AutoML/MobileVLM/releases/download/v0.1/benchmark_data.zip) pre-collected by us.
- `unzip benchmark_data.zip && cd benchmark_data`
- `bmk_dir=${work_dir}/data/benchmark_data`
- gqa
- download its image data following the official instructions [here](https://cs.stanford.edu/people/dorarad/gqa/download.html)
- `cd ${bmk_dir}/gqa && ln -s /path/to/gqa/images images`
- mme
- download the data following the official instructions [here](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation).
- `cd ${bmk_dir}/mme && ln -s /path/to/MME/MME_Benchmark_release_version images`
- pope
- download coco from POPE following the official instructions [here](https://github.com/AoiDragon/POPE/tree/e3e39262c85a6a83f26cf5094022a782cb0df58d/output/coco).
- `cd ${bmk_dir}/pope && ln -s /path/to/pope/coco coco && ln -s /path/to/coco/val2014 val2014`
- sqa
- download images from the `data/scienceqa` folder of the ScienceQA [repo](https://github.com/lupantech/ScienceQA).
- `cd ${bmk_dir}/sqa && ln -s /path/to/sqa/images images`
- textvqa
- download images following the instructions [here](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip).
- `cd ${bmk_dir}/textvqa && ln -s /path/to/textvqa/train_images train_images`
- mmbench
- no action is needed.
</details>
更多资料可参考源项目的[`README_origin`](./README_origin.md)，由于本项目使用数据集过多，此处不方便提供迷你数据集，读者请根据是否需要自主微调决定是否进行全量下载。
完整数据目录结构如下：
```
data
├── benchmark_data
│   ├── gqa
│   │   ├── convert_gqa_for_eval.py
│   │   ├── eval.py
│   │   ├── images -> /path/to/your/gqa/images
│   │   ├── llava_gqa_testdev_balanced.jsonl
│   │   └── testdev_balanced_questions.json
│   ├── mmbench
│   │   ├── convert_mmbench_for_submission.py
│   │   ├── eval.py
│   │   └── mmbench_dev_en_20231003.tsv
│   ├── mme
│   │   ├── calculation.py
│   │   ├── convert_answer_to_mme.py
│   │   ├── images -> /path/to/your/MME/MME_Benchmark_release_version
│   │   └── llava_mme.jsonl
│   ├── pope
│   │   ├── coco -> /path/to/your/pope/coco
│   │   ├── eval.py
│   │   ├── llava_pope_test.jsonl
│   │   └── val2014 -> /path/to/your/coco/val2014
│   ├── sqa
│   │   ├── eval.py
│   │   ├── images -> /path/to/your/scienceqa/images
│   │   ├── llava_test_CQM-A.json
│   │   ├── pid_splits.json
│   │   └── problems.json
│   └── textvqa
│   ├── eval.py
│   ├── llava_textvqa_val_v051_ocr.jsonl
│   ├── TextVQA_0.5.1_val.json
│   └── train_images -> /path/to/your/textvqa/train_images
├── finetune_data
│ ├── llava_v1_5_mix665k.json
│ ├── MobileVLM_V2_FT_Mix2M.json
│ ├── coco
│ │ ├── train2017
│ │ └── val2017
│ ├── gqa
│ │ └── images
│ ├── iconqa_data
│ │ └── iconqa
│ │    └── train
│ │       ├── choose_img
│ │       ├── choose_txt
│ │       └── fill_in_blank
│ ├── ocr_vqa
│ │ └── images
│ ├── sam
│ │ └── images
│ ├── SBU
│ │ └── images
│ ├── ScienceQA
│ │ └── train
│ ├── share_textvqa
│ │ └── images
│ ├── textvqa
│ │ └── train_images
│ ├── vg
│ │ ├── VG_100K
│ │ └── VG_100K_2
│ ├── web-celebrity
│ │ └── images
│ ├── web-landmark
│ │ └── images
│ └── wikiart
│ └── images
└── pretrain_data
├── share-captioner_coco_lcs_sam_1246k_1107.json
├── blip_laion_cc_sbu_558k.json
├── images
├── coco
│   └── train2017
├── llava
│   └── llava_pretrain
└── sam
   └── images
```
更多资料可参考源项目的[`README_origin`](./README_origin.md)。
## 训练
finetune需要下载预训练权重`mtgv/MobileVLM_V2-1.7B`：https://huggingface.co/mtgv/MobileVLM_V2-1.7B
同时还需要下载图像-文本clip权重`openai/clip-vit-large-patch14-336`：https://huggingface.co/openai/clip-vit-large-patch14-336
### 单机多卡
```
bash run.sh mobilevlm_v2_1.7b pretrain mtgv/MobileVLM_V2-1.7B openai/clip-vit-large-patch14-336 # 或sh pretrain.sh
# 当前bnb库仅支持fp16微调，后期逐渐开放其它微调精度。
# 微调所需深度学习库参见前文环境配置，读者自行下载完整数据集后方可使用。
```
## 推理
```
export HIP_VISIBLE_DEVICES=0
python infer.py # 单机单卡
# 采用官方默认权重推理：代码里设置model_path = "mtgv/MobileVLM_V2-1.7B"
```
## result
```
# 输入
图片：assets/samples/demo.jpg
问题\prompt："Who is the author of this book?\nAnswer the question using a single word or phrase."
# 输出
答案：Susan Wise Bauer
```
### 精度
DCU Z100L与GPU V100S精度一致。
## 应用场景
### 算法类别
`图像理解`
### 热点应用行业
`制造,广媒,金融,能源,医疗,家居,教育`
## 源码仓库及问题反馈
- http://developer.hpccube.com/codes/modelzoo/mobilevlm_pytorch.git
## 参考资料
- https://github.com/Meituan-AutoML/MobileVLM.git
- https://hf-mirror.com/ #Huggingface镜像官网下载教程
- https://hf-mirror.com/datasets #Huggingface镜像数据地址
- https://modelscope.cn/models # ModelZoo上部分算法的权重可尝试从魔搭社区下载
README_origin.md 0 → 100644
View file @ 34164470
This diff is collapsed.
assets/READMEv1.md 0 → 100644
View file @ 34164470
# <center> MobileVLM: A Fast, Strong and Open <br> Vision Language Assistant for Mobile Devices
<a href='https://github.com/Meituan-AutoML/MobileVLM'><img src='https://img.shields.io/badge/Project-Page-Green'></a>
<a href='https://arxiv.org/abs/2312.16886'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
[![Code License](https://img.shields.io/badge/Code%20License-Apache_2.0-green.svg)](https://github.com/tatsu-lab/stanford_alpaca/blob/main/LICENSE)
We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted to run on mobile devices. It is an amalgamation of a myriad of architectural designs and techniques that are mobile-oriented, which comprises a set of language models at the scale of 1.4B and 2.7B parameters, trained from scratch, a multimodal vision model that is pre-trained in the CLIP fashion, cross-modality interaction via an efficient projector. We evaluate MobileVLM on several typical VLM benchmarks. Our models demonstrate on par performance compared with a few much larger models. More importantly, we measure the inference speed on both a Qualcomm Snapdragon 888 CPU and an NVIDIA Jeston Orin GPU, and we obtain state-of-the-art performance of 21.5 tokens and 65.3 tokens per second, respectively.
<p align="center"><img src="assets/mobilevlm_arch.png"></p>
The MobileVLM architecture (right) utilizes MobileLLaMA as its language model, intakes $\mathbf{X}_v$ and $\mathbf{X}_q$ which are image and language instructions as respective inputs and gives $\mathbf{Y}_a$ as the output language response. LDP refers to a lightweight downsample projector (left).
## 📸 Release
* ⏳ MobileLLaMA Pre-training code.
* ⏳ MobileLLaMA SFT training code.
* **`Jan. 23th, 2024`**: 🚀🚀🚀 **MobileVLM** is officially supported by [`llama.cpp`](https://github.com/ggerganov/llama.cpp/blob/master/examples/llava/MobileVLM-README.md) now ! Have a try !
* **`Jan. 15th, 2024`**: Customized `llama.cpp` for **MobileVLM** and its [deployment instruction](#deployment-on-mobile-devices) on mobile devices.
* **`Jan. 11st, 2024`**: The training and evaluation codes of MobileVLM are available now! Follow these step-by-step instructions below to easily train your own mobileVLM in **5 hours** ⚡️ !
* **`Dec. 31st, 2023`**: Our MobileVLM weights are uploaded on the HuggingFace website. We also provide inference examples for the MobileLLaMA/MobileVLM model so that anyone can enjoy [them](https://huggingface.co/mtgv/) early.
* **`Dec. 29th, 2023`**: Our MobileLLaMA weights are uploaded on the HuggingFace website. Enjoy [them](https://huggingface.co/mtgv/) !
* **`Dec. 28th, 2023`:** 🔥🔥🔥 We release **MobileVLM: A Fast, Strong and Open Vision Language Assistant for Mobile Devices** on arxiv. Refer to **[our paper](https://arxiv.org/abs/2312.16886)** for more details !
## 🦙 Model Zoo
- [MobileLLaMA-1.4B-Base](https://huggingface.co/mtgv/MobileLLaMA-1.4B-Base)
- [MobileLLaMA-1.4B-Chat](https://huggingface.co/mtgv/MobileLLaMA-1.4B-Chat)
- [MobileLLaMA-2.7B-Base](https://huggingface.co/mtgv/MobileLLaMA-2.7B-Base)
- [MobileLLaMA-2.7B-Chat](https://huggingface.co/mtgv/MobileLLaMA-2.7B-Chat)
- [MobileVLM-1.7B](https://huggingface.co/mtgv/MobileVLM-1.7B)
- [MobileVLM-3B](https://huggingface.co/mtgv/MobileVLM-3B)
🔔 **Usage and License Notices**: This project utilizes certain datasets and checkpoints that are subject to their respective original licenses. Users must comply with all terms and conditions of these original licenses. This project is licensed permissively under the Apache 2.0 license and does not impose any additional constraints. <sup>[LLaVA](https://github.com/haotian-liu/LLaVA/tree/main?tab=readme-ov-file#release)</sup>
## 🛠️ Install
1. Clone this repository and navigate to MobileVLM folder
```bash
git clone https://github.com/Meituan-AutoML/MobileVLM.git
cd MobileVLM
```
2. Install Package
```Shell
conda create -n mobilevlm python=3.10 -y
conda activate mobilevlm
pip install --upgrade pip
pip install -r requirements.txt
```
## 🗝️ Quick Start
#### Example for MobileLLaMA model inference
```python
import torch
from transformers import LlamaTokenizer, LlamaForCausalLM
model_path = 'mtgv/MobileLLaMA-1.4B-Chat'
tokenizer = LlamaTokenizer.from_pretrained(model_path)
model = LlamaForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float16, device_map='auto',
)
prompt = 'Q: What is the largest animal?\nA:'
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=32
)
print(tokenizer.decode(generation_output[0]))
```
* For more advanced usage, please follow the [transformers LLaMA documentation](https://huggingface.co/docs/transformers/main/model_doc/llama).
#### Example for MobileVLM model inference
```python
from scripts.inference import inference_once
model_path = "mtgv/MobileVLM-1.7B"
image_file = "assets/samples/demo.jpg"
prompt_str = "Who is the author of this book?\nAnswer the question using a single word or phrase."
# (or) What is the title of this book?
# (or) Is this book related to Education & Teaching?
args = type('Args', (), {
"model_path": model_path,
"image_file": image_file,
"prompt": prompt_str,
"conv_mode": "v1",
"temperature": 0,
"top_p": None,
"num_beams": 1,
"max_new_tokens": 512,
"load_8bit": False,
"load_4bit": False,
})()
inference_once(args)
```
## 🪜 Step-by-step Tutorial
### MobileVLM
The training process of MobileVLM is divided into two stages:
- stage I: feature alignment pretrain
- ❄️ frozen vision encoder + 🔥 **learnable** LDP projector + ❄️ frozen LLM
- this training process takes around **1~1.5 hours** for MobileVLM-1.7B/3B on 8x A100 (80G) with a batch size of 256 and an average of approximately 15G/19G of GPU memory required.
- stage II: visual instruction tuning
- ❄️ frozen vision encoder + 🔥 **learnable** LDP projector + 🔥 **learnable** LLM
- this training process takes around **2~3.5 hours** for MobileVLM-1.7B/3B on 8x A100 (80G) with a batch size of 128 and an average of approximately 46G/52G of GPU memory required.
Note: To train on fewer GPU memory or cards, you can reduce the `per_device_train_batch_size` and increase the `gradient_accumulation_steps` accordingly. Always keep the `global batch size` the same: `per_device_train_batch_size` x `gradient_accumulation_steps` x `num_gpus`.
#### 1️⃣ Prepare MobileLLaMA checkpoints
Download MobileLLaMA chatbot checkpoints from huggingface website (🤗 [1.7B](https://huggingface.co/mtgv/MobileLLaMA-1.4B-Chat), [2.7B](https://huggingface.co/mtgv/MobileLLaMA-3B-Chat)). Please note that this is **optional** (it depends on your working environment), run the training script we provide below and the model will be automatically downloaded by the `transformers` library.
#### 2️⃣ Prepare data
- For convenience, assume your working directory `/path/to/project/mobilevlm` as `work_dir`:
- `cd ${work_dir} && mkdir -p data/pretrain_data data/finetune_data data/benchmark_data`
- prepare alignment pre-training data
- `cd ${work_dir}/data/pretrain_data`
- download the LLaVA-558K from [here](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain), which is provided by LLaVA team.
- prepare instruction tuning data
- `cd ${work_dir}/data/finetune_data`
- download the annotation of the LLaVA mixture instruction tuning data [here](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K/blob/main/llava_v1_5_mix665k.json), and download the images from constituting datasets: [COCO](http://images.cocodataset.org/zips/train2017.zip), [GQA](https://downloads.cs.stanford.edu/nlp/data/gqa/images.zip), [OCR-VQA](https://drive.google.com/drive/folders/1_GYPY5UkUy7HIcR0zq3ZCFgeZN7BAfm_?usp=sharing), [TextVQA](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip), [VisualGnome](https://cs.stanford.edu/people/rak248/VG_100K_2) ([Part1](https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip), [Part2](https://cs.stanford.edu/people/rak248/VG_100K_2/images2.zip))
- prepare benchmark data
- We evaluate models on a diverse set of 6 benchmarks, *i.e.* GQA, MMBench, MME, POPE, SQA, TextVQA. We do not evaluate using beam search to make the inference process consistent with the chat demo of real-time outputs. You should follow these instructions to manage the datasets.
- <details>
<summary> Data Download Instructions </summary>
- download some useful [data/scripts](https://github.com/Meituan-AutoML/MobileVLM/releases/download/v0.1/benchmark_data.zip) pre-collected by us.
- `unzip benchmark_data.zip && cd benchmark_data`
- `bmk_dir=${work_dir}/data/benchmark_data`
- gqa
- download its image data following the official instructions [here](https://cs.stanford.edu/people/dorarad/gqa/download.html)
- `cd ${bmk_dir}/gqa && ln -s /path/to/gqa/images images`
- mme
- download the data following the official instructions [here](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation).
- `cd ${bmk_dir}/mme && ln -s /path/to/MME/MME_Benchmark_release_version images`
- pope
- download coco from POPE following the official instructions [here](https://github.com/AoiDragon/POPE/tree/e3e39262c85a6a83f26cf5094022a782cb0df58d/output/coco).
- `cd ${bmk_dir}/pope && ln -s /path/to/pope/coco coco && ln -s /path/to/coco/val2014 val2014`
- sqa
- download images from the `data/scienceqa` folder of the ScienceQA [repo](https://github.com/lupantech/ScienceQA).
- `cd ${bmk_dir}/sqa && ln -s /path/to/sqa/images images`
- textvqa
- download images following the instructions [here](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip).
- `cd ${bmk_dir}/textvqa && ln -s /path/to/textvqa/train_images train_images`
- mmbench
- no action is needed.
</details>
- organize the `data` directory as follows after downloading all of them:
- <details>
<summary> Data Structure Tree </summary>
```
.
├── benchmark_data
│   ├── gqa
│   │   ├── convert_gqa_for_eval.py
│   │   ├── eval.py
│   │   ├── images -> /path/to/your/gqa/images
│   │   ├── llava_gqa_testdev_balanced.jsonl
│   │   └── testdev_balanced_questions.json
│   ├── mmbench
│   │   ├── convert_mmbench_for_submission.py
│   │   ├── eval.py
│   │   └── mmbench_dev_en_20231003.tsv
│   ├── mme
│   │   ├── calculation.py
│   │   ├── convert_answer_to_mme.py
│   │   ├── images -> /path/to/your/MME/MME_Benchmark_release_version
│   │   └── llava_mme.jsonl
│   ├── pope
│   │   ├── coco -> /path/to/your/pope/coco
│   │   ├── eval.py
│   │   ├── llava_pope_test.jsonl
│   │   └── val2014 -> /path/to/your/coco/val2014
│   ├── sqa
│   │   ├── eval.py
│   │   ├── images -> /path/to/your/scienceqa/images
│   │   ├── llava_test_CQM-A.json
│   │   ├── pid_splits.json
│   │   └── problems.json
│   └── textvqa
│   ├── eval.py
│   ├── llava_textvqa_val_v051_ocr.jsonl
│   ├── m4c_evaluator.py
│   ├── TextVQA_0.5.1_val.json
│   └── train_images -> /path/to/your/textvqa/train_images
├── finetune_data
│ ├── llava_v1_5_mix665k.json
│ ├── coco
│ │ └── train2017
│ ├── gqa
│ │ └── images
│ ├── ocr_vqa
│ │ └── images
│ ├── textvqa
│ │ └── train_images
│ └── vg
│ ├── VG_100K
│ └── VG_100K_2
├── pretrain_data
│ ├── images
│ └── blip_laion_cc_sbu_558k.json
```
</details>
#### 3️⃣ Run everything with one click!
```shell
LANGUAGE_MODEL=/path/to/your/MobileLLaMA-1.4B-Chat # or 2.7B
VISION_MODEL=/path/to/your/clip-vit-large-patch14-336
bash run.sh mobilevlm1.7b pretrain-finetune-test ${LANGUAGE_MODEL} ${VISION_MODEL}
# (test-only) bash run.sh mobilevlm1.7b test /path/to/your/own/checkpoint
# (3B) bash run.sh mobilevlm3b pretrain-finetune-test ${LANGUAGE_MODEL} ${VISION_MODEL}
```
- Note 🧭: We place all running commands in `run.sh` so they can be run with one click for simplification. If you would like to modify some super-parameters to observe their impact, please dive into `run.sh` to explore.
## <h2 id="deployment-on-mobile-devices">📲 Deployment on Mobile Devices </h2>
**MobileVLM** now is officially supported by `llama.cpp`. We are looking for more cooperation with open-source communities on the deployment of mobile devices.
- [llama.cpp](https://github.com/ggerganov/llama.cpp): the repository of official `llama.cpp`. Step-by-step deployment instructions are provided [here](https://github.com/ggerganov/llama.cpp/blob/master/examples/llava/MobileVLM-README.md).
## 🤝 Acknowledgments
- [LLaVA](https://github.com/haotian-liu/LLaVA): the codebase we built upon. Thanks for their wonderful work! 👏
- [Vicuna](https://github.com/lm-sys/FastChat): the amazing open-sourced large language model!
- [llama.cpp](https://github.com/ggerganov/llama.cpp): the great open-sourced framework for the inference of LLaMA model in pure C/C++!
## ✏️ Reference
If you find MobileVLM or MobileLLaMA useful in your research or applications, please consider giving a star ⭐ and citing using the following BibTeX:
```
@article{chu2023mobilevlm,
title={Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices},
author={Chu, Xiangxiang and Qiao, Limeng and Lin, Xinyang and Xu, Shuang and Yang, Yang and Hu, Yiming and Wei, Fei and Zhang, Xinyu and Zhang, Bo and Wei, Xiaolin and others},
journal={arXiv preprint arXiv:2312.16886},
year={2023}
}
```
## 🌟 Star History
<picture>
<source
media="(prefers-color-scheme: dark)"
srcset="
https://api.star-history.com/svg?repos=Meituan-AutoML/MobileVLM&type=Date&theme=dark
"
/>
<source
media="(prefers-color-scheme: light)"
srcset="
https://api.star-history.com/svg?repos=Meituan-AutoML/MobileVLM&type=Date
"
/>
<img
alt="Star History Chart"
src="https://api.star-history.com/svg?repos=Meituan-AutoML/MobileVLM&type=Date"
/>
</picture>
docker_start.sh 0 → 100644
View file @ 34164470
docker run -it --shm-size=32G -v $PWD/MobileVLM:/home/MobileVLM -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name mobilevlm ffa1f63239fc bash
# python -m torch.utils.collect_env
infer.py 0 → 100644
View file @ 34164470
from scripts.inference import inference_once
import time
# model_path = "mtgv/MobileVLM-1.7B" # MobileVLM
model_path = "mtgv/MobileVLM_V2-1.7B" # MobileVLM V2
image_file = "assets/samples/demo.jpg"
prompt_str = "Who is the author of this book?\nAnswer the question using a single word or phrase."
# (or) What is the title of this book?
# (or) Is this book related to Education & Teaching?
args = type('Args', (), {
"model_path": model_path,
"image_file": image_file,
"prompt": prompt_str,
"conv_mode": "v1",
"temperature": 0,
"top_p": None,
"num_beams": 1,
"max_new_tokens": 512,
"load_8bit": False,
"load_4bit": False,
})()
start_time = time.time()
inference_once(args)
print("infer time：", time.time() - start_time, "秒")
mobilellama/sft/MobileLLaMA_SFT.md 0 → 100644
View file @ 34164470
# MobileLLaMA SFT
## 🛠️ Installation
Our MobileLLaMA SFT training code is based on [FastChat](https://github.com/lm-sys/FastChat) (commit id: 81785d7ed1d6afb966b464a8ee4689b7413e6313)
### Install From Source.
1. Clone the [FastChat](https://github.com/lm-sys/FastChat) repository and navigate to the FastChat folder
```bash
git clone https://github.com/lm-sys/FastChat.git
cd FastChat
```
If you are running on Mac:
```bash
brew install rust cmake
```
2. Install package
```bash
pip3 install --upgrade pip
pip3 install -e ".[model_worker,webui]"
```
## Model Weights
You can download MobileLLaMA-1.4B-Base / MobileLLaMA-2.7B-Base model from huggingface website to your local path, or run our train.sh directly to download the weights before training:
- [MobileLLaMA-1.4B-Base](https://huggingface.co/mtgv/MobileLLaMA-1.4B-Base)
- [MobileLLaMA-2.7B-Base](https://huggingface.co/mtgv/MobileLLaMA-2.7B-Base)
## Dataset
We use the sft dataset in Vicuna fromat can be download from link: [ShareGPT_Vicuna_dataset](https://huggingface.co/datasets/Aeala/ShareGPT_Vicuna_unfiltered), and follow the steps:
1. download the [json](https://huggingface.co/datasets/Aeala/ShareGPT_Vicuna_unfiltered/blob/main/ShareGPT_V4.3_unfiltered_cleaned_split.json) file to local data path.
2. write the correct "--data_path" in your SFT training scripts.
## 💎 Training
Our training process can be reproduced by runing the scrips:
```bash
cd MobileVLM
# for MobileLLaMA-1.4B
sh mobilellama/sft/sft_MobileLLaMA-1.4B-Base.sh
# for MobileLLaMA-2.7B
sh mobilellama/sft/sft_MobileLLaMA-2.7B-Base.sh
```
Weights after SFT training can be download from:
- [MobileLLaMA-1.4B-Chat](https://huggingface.co/mtgv/MobileLLaMA-1.4B-Chat)
- [MobileLLaMA-2.7B-Chat](https://huggingface.co/mtgv/MobileLLaMA-2.7B-Chat)
## Evaluation results
The performance comparison of the model on several benchmarks before and after Supervised Fine-Tuning (SFT), as illustrated below:
<table>
<tr>
<th style="text-align: center;">models</th>
<th style="text-align: center;" colspan="2">knowledge</th>
<th style="text-align: center;">reasoning</th>
<th style="text-align: center;" colspan="3">Understanding</th>
</tr>
<tr>
<td style="text-align: center;">tasks</td>
<td style="text-align: center;">TriviaQA</td>
<td style="text-align: center;">NQ</td>
<td style="text-align: center;">HellaSwag</td>
<td style="text-align: center;">RACEMiddle</td>
<td style="text-align: center;">RACEHigh</td>
<td style="text-align: center;">XSum</td>
</tr>
<tr>
<td style="text-align: center;">MobileLLaMA 1.4B Base</td>
<td style="text-align: center;">15.7</td>
<td style="text-align: center;">2.9</td>
<td style="text-align: center;">43.0</td>
<td style="text-align: center;">21.5</td>
<td style="text-align: center;">22.7</td>
<td style="text-align: center;">18.0</td>
</tr>
<tr>
<td style="text-align: center;">MobileLLaMA 1.4B sft</td>
<td style="text-align: center;">20.3</td>
<td style="text-align: center;">3.9</td>
<td style="text-align: center;">45.0</td>
<td style="text-align: center;">25.7</td>
<td style="text-align: center;">26.6</td>
<td style="text-align: center;">20.7</td>
</tr>
<tr>
<td style="text-align: center;">MobileLLaMA 2.7B Base</td>
<td style="text-align: center;">23.0</td>
<td style="text-align: center;">4.2</td>
<td style="text-align: center;">48.0</td>
<td style="text-align: center;">23.8</td>
<td style="text-align: center;">24.6</td>
<td style="text-align: center;">16.8</td>
</tr>
<tr>
<td style="text-align: center;">MobileLLaMA 2.7B sft</td>
<td style="text-align: center;">26.4</td>
<td style="text-align: center;">8.3</td>
<td style="text-align: center;">50.0</td>
<td style="text-align: center;">26.7</td>
<td style="text-align: center;">27.2</td>
<td style="text-align: center;">23.8</td>
</tr>
</table>
## 🤝 Acknowledgments
- [Vicuna](https://github.com/lm-sys/FastChat): the SFT codebase we utilize. Thanks for their wonderful work! 👏
- [ShareGPT_Vicuna_dataset](https://huggingface.co/datasets/Aeala/ShareGPT_Vicuna_unfiltered): the dataset we train our chat model, Thanks for their well collection! 👏!
mobilellama/sft/sft_MobileLLaMA-1.4B-Base.sh 0 → 100644
View file @ 34164470
# CUDA_VISIBLE_DEVICES=1 torchrun --nproc_per_node=1 --master_port=20001 fastchat/train/train_mem.py \
torchrun --nproc_per_node=8 --master_port=20001 fastchat/train/train_mem.py \
--model_name_or_path mtgv/MobileLLaMA-1.4B-Base \
--data_path ShareGPT_2023.05.04v0_Wasteland_Edition.json \
--bf16 True \
--output_dir output_dir \
--num_train_epochs 3 \
--per_device_train_batch_size 16 \
--per_device_eval_batch_size 16 \
--gradient_accumulation_steps 2 \
--evaluation_strategy "steps" \
--eval_steps 2000 \
--save_strategy "steps" \
--save_steps 1800 \
--save_total_limit 8 \
--learning_rate 2e-5 \
--weight_decay 0. \
--warmup_ratio 0.04 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--fsdp "full_shard auto_wrap" \
--fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
--tf32 True \
--model_max_length 2048 \
--gradient_checkpointing True \
--lazy_preprocess True \
--report_to none
## --data_path /mnt/dolphinfs/ssd_pool/docker/user/hadoop-automl/common/LM_data/data/NLP/sft_data/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split_no_imsorry_.json \
mobilellama/sft/sft_MobileLLaMA-2.7B-Base.sh 0 → 100644
View file @ 34164470
# CUDA_VISIBLE_DEVICES=1 torchrun --nproc_per_node=1 --master_port=20001 fastchat/train/train_mem.py \
torchrun --nproc_per_node=8 --master_port=20001 fastchat/train/train_mem.py \
--model_name_or_path mtgv/MobileLLaMA-2.7B-Base \
--data_path ShareGPT_V4.3_unfiltered_cleaned_split.json \
--bf16 True \
--output_dir output_dir \
--num_train_epochs 2 \
--per_device_train_batch_size 16 \
--per_device_eval_batch_size 16 \
--gradient_accumulation_steps 2 \
--evaluation_strategy "steps" \
--eval_steps 2000 \
--save_strategy "steps" \
--save_steps 1800 \
--save_total_limit 8 \
--learning_rate 3e-5 \
--weight_decay 0. \
--warmup_ratio 0.04 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--fsdp "full_shard auto_wrap" \
--fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
--tf32 True \
--model_max_length 2048 \
--gradient_checkpointing True \
--lazy_preprocess True \
--report_to none
## --data_path /mnt/dolphinfs/ssd_pool/docker/user/hadoop-automl/common/LM_data/data/NLP/sft_data/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split_no_imsorry_.json \
mobilevlm/constants.py 0 → 100644
View file @ 34164470
CONTROLLER_HEART_BEAT_EXPIRATION = 30
WORKER_HEART_BEAT_INTERVAL = 15
LOGDIR = "."
# Model Constants
IGNORE_INDEX = -100
IMAGE_TOKEN_INDEX = -200
DEFAULT_IMAGE_TOKEN = "<image>"
DEFAULT_IMAGE_PATCH_TOKEN = "<im_patch>"
DEFAULT_IM_START_TOKEN = "<im_start>"
DEFAULT_IM_END_TOKEN = "<im_end>"
IMAGE_PLACEHOLDER = "<image-placeholder>"
\ No newline at end of file
mobilevlm/conversation.py 0 → 100644
View file @ 34164470
import dataclasses
from enum import auto, Enum
from typing import List, Tuple
class SeparatorStyle(Enum):
"""Different separator style."""
SINGLE = auto()
TWO = auto()
MPT = auto()
PLAIN = auto()
LLAMA_2 = auto()
@dataclasses.dataclass
class Conversation:
"""A class that keeps all conversation history."""
system: str
roles: List[str]
messages: List[List[str]]
offset: int
sep_style: SeparatorStyle = SeparatorStyle.SINGLE
sep: str = "###"
sep2: str = None
version: str = "Unknown"
skip_next: bool = False
def get_prompt(self):
messages = self.messages
if len(messages) > 0 and type(messages[0][1]) is tuple:
messages = self.messages.copy()
init_role, init_msg = messages[0].copy()
init_msg = init_msg[0].replace("<image>", "").strip()
if 'mmtag' in self.version:
messages[0] = (init_role, init_msg)
messages.insert(0, (self.roles[0], "<Image><image></Image>"))
messages.insert(1, (self.roles[1], "Received."))
else:
messages[0] = (init_role, "<image>\n" + init_msg)
if self.sep_style == SeparatorStyle.SINGLE:
ret = self.system + self.sep
for role, message in messages:
if message:
if type(message) is tuple:
message, _, _ = message
ret += role + ": " + message + self.sep
else:
ret += role + ":"
elif self.sep_style == SeparatorStyle.TWO:
seps = [self.sep, self.sep2]
ret = self.system + seps[0]
for i, (role, message) in enumerate(messages):
if message:
if type(message) is tuple:
message, _, _ = message
ret += role + ": " + message + seps[i % 2]
else:
ret += role + ":"
elif self.sep_style == SeparatorStyle.MPT:
ret = self.system + self.sep
for role, message in messages:
if message:
if type(message) is tuple:
message, _, _ = message
ret += role + message + self.sep
else:
ret += role
elif self.sep_style == SeparatorStyle.LLAMA_2:
wrap_sys = lambda msg: f"<<SYS>>\n{msg}\n<</SYS>>\n\n"
wrap_inst = lambda msg: f"[INST] {msg} [/INST]"
ret = ""
for i, (role, message) in enumerate(messages):
if i == 0:
assert message, "first message should not be none"
assert role == self.roles[0], "first message should come from user"
if message:
if type(message) is tuple:
message, _, _ = message
if i == 0: message = wrap_sys(self.system) + message
if i % 2 == 0:
message = wrap_inst(message)
ret += self.sep + message
else:
ret += " " + message + " " + self.sep2
else:
ret += ""
ret = ret.lstrip(self.sep)
elif self.sep_style == SeparatorStyle.PLAIN:
seps = [self.sep, self.sep2]
ret = self.system
for i, (role, message) in enumerate(messages):
if message:
if type(message) is tuple:
message, _, _ = message
ret += message + seps[i % 2]
else:
ret += ""
else:
raise ValueError(f"Invalid style: {self.sep_style}")
return ret
def append_message(self, role, message):
self.messages.append([role, message])
def get_images(self, return_pil=False):
images = []
for i, (role, msg) in enumerate(self.messages[self.offset:]):
if i % 2 == 0:
if type(msg) is tuple:
import base64
from io import BytesIO
from PIL import Image
msg, image, image_process_mode = msg
if image_process_mode == "Pad":
def expand2square(pil_img, background_color=(122, 116, 104)):
width, height = pil_img.size
if width == height:
return pil_img
elif width > height:
result = Image.new(pil_img.mode, (width, width), background_color)
result.paste(pil_img, (0, (width - height) // 2))
return result
else:
result = Image.new(pil_img.mode, (height, height), background_color)
result.paste(pil_img, ((height - width) // 2, 0))
return result
image = expand2square(image)
elif image_process_mode in ["Default", "Crop"]:
pass
elif image_process_mode == "Resize":
image = image.resize((336, 336))
else:
raise ValueError(f"Invalid image_process_mode: {image_process_mode}")
max_hw, min_hw = max(image.size), min(image.size)
aspect_ratio = max_hw / min_hw
max_len, min_len = 800, 400
shortest_edge = int(min(max_len / aspect_ratio, min_len, min_hw))
longest_edge = int(shortest_edge * aspect_ratio)
W, H = image.size
if longest_edge != max(image.size):
if H > W:
H, W = longest_edge, shortest_edge
else:
H, W = shortest_edge, longest_edge
image = image.resize((W, H))
if return_pil:
images.append(image)
else:
buffered = BytesIO()
image.save(buffered, format="PNG")
img_b64_str = base64.b64encode(buffered.getvalue()).decode()
images.append(img_b64_str)
return images
def to_gradio_chatbot(self):
ret = []
for i, (role, msg) in enumerate(self.messages[self.offset:]):
if i % 2 == 0:
if type(msg) is tuple:
import base64
from io import BytesIO
msg, image, image_process_mode = msg
max_hw, min_hw = max(image.size), min(image.size)
aspect_ratio = max_hw / min_hw
max_len, min_len = 800, 400
shortest_edge = int(min(max_len / aspect_ratio, min_len, min_hw))
longest_edge = int(shortest_edge * aspect_ratio)
W, H = image.size
if H > W:
H, W = longest_edge, shortest_edge
else:
H, W = shortest_edge, longest_edge
image = image.resize((W, H))
buffered = BytesIO()
image.save(buffered, format="JPEG")
img_b64_str = base64.b64encode(buffered.getvalue()).decode()
img_str = f'<img src="data:image/png;base64,{img_b64_str}" alt="user upload image" />'
msg = img_str + msg.replace('<image>', '').strip()
ret.append([msg, None])
else:
ret.append([msg, None])
else:
ret[-1][-1] = msg
return ret
def copy(self):
return Conversation(
system=self.system,
roles=self.roles,
messages=[[x, y] for x, y in self.messages],
offset=self.offset,
sep_style=self.sep_style,
sep=self.sep,
sep2=self.sep2,
version=self.version)
def dict(self):
if len(self.get_images()) > 0:
return {
"system": self.system,
"roles": self.roles,
"messages": [[x, y[0] if type(y) is tuple else y] for x, y in self.messages],
"offset": self.offset,
"sep": self.sep,
"sep2": self.sep2,
}
return {
"system": self.system,
"roles": self.roles,
"messages": self.messages,
"offset": self.offset,
"sep": self.sep,
"sep2": self.sep2,
}
conv_vicuna_v0 = Conversation(
system="A chat between a curious human and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the human's questions.",
roles=("Human", "Assistant"),
messages=(
("Human", "What are the key differences between renewable and non-renewable energy sources?"),
("Assistant",
"Renewable energy sources are those that can be replenished naturally in a relatively "
"short amount of time, such as solar, wind, hydro, geothermal, and biomass. "
"Non-renewable energy sources, on the other hand, are finite and will eventually be "
"depleted, such as coal, oil, and natural gas. Here are some key differences between "
"renewable and non-renewable energy sources:\n"
"1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable "
"energy sources are finite and will eventually run out.\n"
"2. Environmental impact: Renewable energy sources have a much lower environmental impact "
"than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, "
"and other negative effects.\n"
"3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically "
"have lower operational costs than non-renewable sources.\n"
"4. Reliability: Renewable energy sources are often more reliable and can be used in more remote "
"locations than non-renewable sources.\n"
"5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different "
"situations and needs, while non-renewable sources are more rigid and inflexible.\n"
"6. Sustainability: Renewable energy sources are more sustainable over the long term, while "
"non-renewable sources are not, and their depletion can lead to economic and social instability.\n")
),
offset=2,
sep_style=SeparatorStyle.SINGLE,
sep="###",
)
conv_vicuna_v1 = Conversation(
system="A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions.",
roles=("USER", "ASSISTANT"),
version="v1",
messages=(),
offset=0,
sep_style=SeparatorStyle.TWO,
sep=" ",
sep2="</s>",
)
# add by me
conv_vicuna_extra = Conversation(
system="A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions.",
roles=("USER", "ASSISTANT"),
version="extra",
messages=(),
offset=0,
sep_style=SeparatorStyle.TWO,
sep="<ques_end>",
sep2="</s>",
)
conv_llama_2 = Conversation(
system="""You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.""",
roles=("USER", "ASSISTANT"),
version="llama_v2",
messages=(),
offset=0,
sep_style=SeparatorStyle.LLAMA_2,
sep="<s>",
sep2="</s>",
)
conv_llava_llama_2 = Conversation(
system="You are a helpful language and vision assistant. "
"You are able to understand the visual content that the user provides, "
"and assist the user with a variety of tasks using natural language.",
roles=("USER", "ASSISTANT"),
version="llama_v2",
messages=(),
offset=0,
sep_style=SeparatorStyle.LLAMA_2,
sep="<s>",
sep2="</s>",
)
conv_mpt = Conversation(
system="""<|im_start|>system
A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""",
roles=("<|im_start|>user\n", "<|im_start|>assistant\n"),
version="mpt",
messages=(),
offset=0,
sep_style=SeparatorStyle.MPT,
sep="<|im_end|>",
)
conv_llava_plain = Conversation(
system="",
roles=("", ""),
messages=(
),
offset=0,
sep_style=SeparatorStyle.PLAIN,
sep="\n",
)
conv_llava_v0 = Conversation(
system="A chat between a curious human and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the human's questions.",
roles=("Human", "Assistant"),
messages=(
),
offset=0,
sep_style=SeparatorStyle.SINGLE,
sep="###",
)
conv_llava_v0_mmtag = Conversation(
system="A chat between a curious user and an artificial intelligence assistant. "
"The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language."
"The visual content will be provided with the following format: <Image>visual content</Image>.",
roles=("Human", "Assistant"),
messages=(
),
offset=0,
sep_style=SeparatorStyle.SINGLE,
sep="###",
version="v0_mmtag",
)
conv_llava_v1 = Conversation(
system="A chat between a curious human and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the human's questions.",
roles=("USER", "ASSISTANT"),
version="v1",
messages=(),
offset=0,
sep_style=SeparatorStyle.TWO,
sep=" ",
sep2="</s>",
)
conv_llava_v1_mmtag = Conversation(
system="A chat between a curious user and an artificial intelligence assistant. "
"The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language."
"The visual content will be provided with the following format: <Image>visual content</Image>.",
roles=("USER", "ASSISTANT"),
messages=(),
offset=0,
sep_style=SeparatorStyle.TWO,
sep=" ",
sep2="</s>",
version="v1_mmtag",
)
default_conversation = conv_vicuna_v0
conv_templates = {
"default": conv_vicuna_v0,
"llama_2": conv_llama_2,
"plain": conv_llava_plain,
"llava_llama_2": conv_llava_llama_2,
"v1": conv_vicuna_v1,
"vicuna_v1": conv_vicuna_v1,
}
if __name__ == "__main__":
print(default_conversation.get_prompt())
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